{"id":"72f4568a-8c4b-4228-8b08-69689013ff74","entityType":"agent","slug":"clawhub-fulcra-fulcra-onboarding","name":"Fulcra Onboarding (deprecated, use fulcra-get-started)","canonicalUrl":"https://www.xpersona.co/agent/clawhub-fulcra-fulcra-onboarding","canonicalPath":"/agent/clawhub-fulcra-fulcra-onboarding","generatedAt":"2026-10-10T04:57:39.014Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T19:42:00.277Z","emptyReason":null},"description":"Deprecated — renamed to fulcra-get-started. Use the fulcra-get-started skill instead. Skill: Fulcra Onboarding (deprecated, use fulcra-get-started) Owner: fulcra Summary: Deprecated — renamed to fulcra-get-started. Use the fulcra-get-started skill instead. Tags: latest:0.3.0 Version history: v0.3.0 | 2026-08-12T20:42:58.062Z | auto - This version deprecates the fulcra-onboarding skill and renames it to fulcra-get-started. - The SKILL.md file is now a pointer directing users to use fulcra-get-started f","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 2.1K downloads reported by the source. Last updated 10/9/2026.","installCommand":"clawhub skill install s173t2w929a11bv262sspwxv6h86t2yy:fulcra-onboarding","sourceUrl":"https://clawhub.ai/fulcra/fulcra-onboarding","homepage":"https://clawhub.ai/fulcra/skills/fulcra-onboarding","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/fulcra/fulcra-onboarding","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/fulcra/skills/fulcra-onboarding","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":66,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Deprecated — renamed to fulcra-get-started. Use the fulcra-get-started skill instead. Skill: Fulcra Onboarding (deprecated, use fulcra-get-started) Owner: fulcr"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T19:42:00.277Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T19:42:00.277Z","emptyReason":null},"stars":null,"forks":null,"downloads":2066,"packageName":null,"latestVersion":"0.3.0","tractionLabel":"2.1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T19:42:00.247Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T19:42:00.277Z","lastCrawledAt":"2026-10-09T19:42:00.247Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-10T19:42:00.247Z","lastVerifiedAt":null,"highlights":[{"version":"0.3.0","createdAt":"2026-08-12T20:42:58.062Z","changelog":"- This version deprecates the fulcra-onboarding skill and renames it to fulcra-get-started. - The SKILL.md file is now a pointer directing users to use fulcra-get-started for onboarding and setup instructions. - All previous onboarding documentation and helper references have been removed. - Users should now install and follow fulcra-get-started for Fulcra environment setup.","fileCount":3,"zipByteSize":1791},{"version":"0.2.0","createdAt":"2026-07-30T17:04:24.391Z","changelog":"**Major update with a new dynamic onboarding flow and tangible delivery focus.** - Rewrote onboarding process to focus on delivering immediate, useful results tied to real user goals, rather than a rigid sequence. - Introduced “Five Branches” to inspire user direction (make something new, solve a problem, improve, share, or pick a community skill). - Emphasized creating tangible views and visualizations early — including fallback options for quick wins and direct Context Web links. - Shifted to using team coordination, tracking, and visibility artifacts (including project dashboards) as core onboarding milestones. - Retired previous static tour menu in favor of contextual, conversation-driven next steps and curated exploration. - Removed redundant or outdated skill-card.md documentation.","fileCount":5,"zipByteSize":10809},{"version":"0.1.7","createdAt":"2026-07-21T17:45:30.714Z","changelog":"- Updated onboarding flow to include both CLI and MCP connector options, supporting a wider range of environments. - Introduced a task-driven onboarding path: prioritize the user's specific requested goal (if one exists) over a generic tour. - Revised recommended flows and examples to reflect improved skill names and support workspaces, not just teams. - Streamlined general guidelines, emphasizing time-to-wow, sensible defaults, and maintaining momentum. - Removed references to deprecated markdown files and unnecessary details for a more concise experience.","fileCount":5,"zipByteSize":10073},{"version":"0.1.6","createdAt":"2026-07-01T22:06:12.799Z","changelog":"**Changelog for fulcra-onboarding v0.1.6** - Overhauled onboarding workflow: now follows a guided three-phase model (core setup, recommended agent flow, expanded menu). - Introduced a \"golden path\" post-setup flow, recommending users connect data sources, automate situational awareness, and set up agent teams. - Updated and streamlined the menu of post-onboarding options for further exploration. - Replaced the agent memory backup with a more general \"Agent Memory & Knowledge\" path. - Removed redundant documentation files (e.g., skill-card.md) for clarity.","fileCount":6,"zipByteSize":10661},{"version":"0.1.4","createdAt":"2026-06-18T21:53:48.572Z","changelog":"- Updated onboarding guidelines to respect user formatting and tone preferences over default \"Wow\" factor (e.g., use of emojis). - Revised the next steps (Spokes) menu, removing \"Cross-Platform Preferences\" from the main options. - Small adjustments to menu item descriptions for clarity and consistency. - Removed file: skill-card.md.","fileCount":6,"zipByteSize":10286},{"version":"0.1.3","createdAt":"2026-06-16T18:23:12.576Z","changelog":"- Removed the skill-card.md file. - Updated references/fulcra-cli.md. - No changes to the onboarding flow or user-facing features.","fileCount":6,"zipByteSize":9456},{"version":"0.1.2","createdAt":"2026-06-15T23:40:26.238Z","changelog":"- Removed obsolete file: skill-card.md - Updated CLI documentation reference: adjusted references/fulcra-cli.md - No functional workflow changes to onboarding, agent interaction, or user pathways","fileCount":6,"zipByteSize":9188},{"version":"0.1.1","createdAt":"2026-06-15T22:06:51.254Z","changelog":"- Added a required introductory step before setup, introducing Fulcra and its capabilities prior to any installation or CLI actions. - Updated the initial menu option from \"Agent Visibility & Dashboards\" to \"Agent Visibility & Custom Tracking,\" refocusing the option. - Changed the primary data tracking onboarding flow to route users to the `fulcra-tracking` skill instead of handling schema creation and data recording internally. - Removed all demonstration, discovery, and data annotation flows from this skill (now handled elsewhere); deleted related reference and workflow files. - Simplified and clarified next-step instructions for each menu choice; skill now acts as a hub delegating detailed routines to specialized skills.","fileCount":6,"zipByteSize":8310}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s173t2w929a11bv262sspwxv6h86t2yy:fulcra-onboarding","setupComplexity":"low","setupSteps":["Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fulcra-fulcra-onboarding/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fulcra-fulcra-onboarding/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fulcra-fulcra-onboarding/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-fulcra-fulcra-onboarding/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-fulcra-fulcra-onboarding/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-fulcra-fulcra-onboarding/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T04:57:39.010Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fulcra-fulcra-onboarding/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fulcra-fulcra-onboarding/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fulcra-fulcra-onboarding/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fulcra-fulcra-onboarding/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-09T19:42:00.277Z","emptyReason":null},"readme":"Skill: Fulcra Onboarding (deprecated, use fulcra-get-started)\n\nOwner: fulcra\n\nSummary: Deprecated — renamed to fulcra-get-started. Use the fulcra-get-started skill instead.\n\nTags: latest:0.3.0\n\nVersion history:\n\nv0.3.0 | 2026-08-12T20:42:58.062Z | auto\n\n- This version deprecates the fulcra-onboarding skill and renames it to fulcra-get-started.\n- The SKILL.md file is now a pointer directing users to use fulcra-get-started for onboarding and setup instructions.\n- All previous onboarding documentation and helper references have been removed.\n- Users should now install and follow fulcra-get-started for Fulcra environment setup.\n\nv0.2.0 | 2026-07-30T17:04:24.391Z | auto\n\n**Major update with a new dynamic onboarding flow and tangible delivery focus.**\n\n- Rewrote onboarding process to focus on delivering immediate, useful results tied to real user goals, rather than a rigid sequence.\n- Introduced “Five Branches” to inspire user direction (make something new, solve a problem, improve, share, or pick a community skill).\n- Emphasized creating tangible views and visualizations early — including fallback options for quick wins and direct Context Web links.\n- Shifted to using team coordination, tracking, and visibility artifacts (including project dashboards) as core onboarding milestones.\n- Retired previous static tour menu in favor of contextual, conversation-driven next steps and curated exploration. \n- Removed redundant or outdated skill-card.md documentation.\n\nv0.1.7 | 2026-07-21T17:45:30.714Z | auto\n\n- Updated onboarding flow to include both CLI and MCP connector options, supporting a wider range of environments.\n- Introduced a task-driven onboarding path: prioritize the user's specific requested goal (if one exists) over a generic tour.\n- Revised recommended flows and examples to reflect improved skill names and support workspaces, not just teams.\n- Streamlined general guidelines, emphasizing time-to-wow, sensible defaults, and maintaining momentum.\n- Removed references to deprecated markdown files and unnecessary details for a more concise experience.\n\nv0.1.6 | 2026-07-01T22:06:12.799Z | auto\n\n**Changelog for fulcra-onboarding v0.1.6**\n\n- Overhauled onboarding workflow: now follows a guided three-phase model (core setup, recommended agent flow, expanded menu).\n- Introduced a \"golden path\" post-setup flow, recommending users connect data sources, automate situational awareness, and set up agent teams.\n- Updated and streamlined the menu of post-onboarding options for further exploration.\n- Replaced the agent memory backup with a more general \"Agent Memory & Knowledge\" path.\n- Removed redundant documentation files (e.g., skill-card.md) for clarity.\n\nv0.1.4 | 2026-06-18T21:53:48.572Z | auto\n\n- Updated onboarding guidelines to respect user formatting and tone preferences over default \"Wow\" factor (e.g., use of emojis).\n- Revised the next steps (Spokes) menu, removing \"Cross-Platform Preferences\" from the main options.\n- Small adjustments to menu item descriptions for clarity and consistency.\n- Removed file: skill-card.md.\n\nv0.1.3 | 2026-06-16T18:23:12.576Z | auto\n\n- Removed the skill-card.md file.\n- Updated references/fulcra-cli.md.\n- No changes to the onboarding flow or user-facing features.\n\nv0.1.2 | 2026-06-15T23:40:26.238Z | auto\n\n- Removed obsolete file: skill-card.md\n- Updated CLI documentation reference: adjusted references/fulcra-cli.md\n- No functional workflow changes to onboarding, agent interaction, or user pathways\n\nv0.1.1 | 2026-06-15T22:06:51.254Z | auto\n\n- Added a required introductory step before setup, introducing Fulcra and its capabilities prior to any installation or CLI actions.\n- Updated the initial menu option from \"Agent Visibility & Dashboards\" to \"Agent Visibility & Custom Tracking,\" refocusing the option.\n- Changed the primary data tracking onboarding flow to route users to the `fulcra-tracking` skill instead of handling schema creation and data recording internally.\n- Removed all demonstration, discovery, and data annotation flows from this skill (now handled elsewhere); deleted related reference and workflow files.\n- Simplified and clarified next-step instructions for each menu choice; skill now acts as a hub delegating detailed routines to specialized skills.\n\nv0.1.0 | 2026-06-12T22:21:15.011Z | auto\n\nInitial release with major onboarding workflow changes:\n\n- Adopted a \"Hub and Spoke\" model, splitting onboarding into core setup and user-driven next steps.\n- Replaced previous multi-step, linear workflow with interactive menu options for post-authentication actions.\n- Added CLI-based authentication step using instructions from new reference files.\n- Updated demonstration and data modeling instructions to use the `fulcra-api` CLI instead of direct API or curl.\n- Removed previous backup, annotation creation, and handoff reference files in favor of new modular paths.\n- Expanded menu to include App download, Context Web, and cross-platform preferences as optional next steps.\n\nv0.0.9 | 2026-06-12T20:37:05.251Z | auto\n\n- Added a new Agent Coordination step to the onboarding workflow, introducing cross-agent collaboration via Fulcra.\n- Updated the workflow sequence to include agent coordination after user intent discovery.\n- Clarified guidance on what information the agent should log, emphasizing milestones over sensitive reasoning or prompts.\n- Made detailed improvements in annotation creation and agent logging instructions.\n- Removed the outdated skill-card.md file.\n\nv0.0.8 | 2026-06-04T22:21:21.710Z | auto\n\n- Removed the file: skill-card.md.\n- Updated references/fulcra-onboarding-backup.md (contents not detailed).\n- No user-facing changes in onboarding flow documented in SKILL.md.\n\nv0.0.7 | 2026-06-04T21:19:59.834Z | auto\n\n- Added a critical workflow step requiring explicit user input for dashboard theming before generation.\n- Removed the file: skill-card.md.\n- Updated SKILL.md to clarify the need to stop and ask the user for their preferred theme prior to generating the custom HTML dashboard.\n\nv0.0.6 | 2026-06-04T19:07:35.650Z | auto\n\n- Removed redundant skill descriptor file (skill-card.md) to streamline the codebase.\n- Updated references/fulcra-onboarding-handoff.md; main onboarding logic and flow remain unchanged.\n- No user-facing workflow or behavioral changes.\n\nv0.0.5 | 2026-06-04T17:38:22.738Z | auto\n\n- Updated onboarding reference documentation for demonstration, handoff, and prerequisites steps.\n- Removed redundant file: skill-card.md.\n- No changes to skill functionality or workflow.\n\nv0.0.4 | 2026-06-04T16:44:50.275Z | auto\n\nMajor workflow expansion: Adds agent memory backup and continuous agent tracking features.\n\n- Introduced a new \"Memory Baseline & Agent Visibility\" step with backup functionality and optional Universal Agent Visibility Package.\n- Updated data modeling to handle both personal and agent-specific annotations when Agent Visibility is enabled.\n- Requires continuous background logging of agent actions into agent-specific annotations throughout onboarding.\n- Added references/fulcra-onboarding-backup.md and references/fulcra-onboarding-usecases.md; removed obsolete skill-card.md.\n- Clarified step order and content in onboarding workflow for clearer, richer guided setup.\n\nv0.0.3 | 2026-05-28T17:57:32.043Z | auto\n\nfulcra-onboarding v0.0.3\n\n- The pre-flight check step now asks for user confirmation before installing `uv` dependencies.\n- Updated workflow instructions to reflect this confirmation requirement in the onboarding process.\n\nv0.0.2 | 2026-05-28T17:27:20.847Z | auto\n\n- Added new handoff step: onboarding now concludes using `references/fulcra-onboarding-handoff.md` for improved guidance on final steps.\n- Updated workflow to reference the new handoff instructions instead of presenting final app download and next steps directly in SKILL.md.\n- Removed redundant or outdated information about handoff from SKILL.md to streamline the onboarding flow.\n- Deleted `skill-card.md` file as part of documentation cleanup.\n- Updated various reference files and documentation for clarity and improved user journey.\n\nv0.0.1 | 2026-05-26T19:25:40.441Z | auto\n\nInitial release of fulcra-onboarding skill.\n\n- Provides an engaging onboarding flow for new users setting up Fulcra.\n- Guides users through pre-flight checks, authentication, and discovering concrete use cases.\n- Helps users create and remember custom data streams (Annotations).\n- Captures and records the user's first data point to demonstrate Fulcra in action.\n- Generates a themed HTML dashboard to showcase stored data.\n- Concludes by directing users to download the Fulcra Context iOS app for enhanced features.\n\nArchive index:\n\nArchive v0.3.0: 3 files, 1791 bytes\n\nFiles: skill-card.md (1689b), SKILL.md (958b), _meta.json (136b)\n\nFile v0.3.0:SKILL.md\n\n---\nname: fulcra-onboarding\ndescription: \"Deprecated — renamed to fulcra-get-started. Use the fulcra-get-started skill instead.\"\nhomepage: \"https://github.com/fulcradynamics/agent-skills\"\nlicense: \"MIT\"\nuser-invocable: true\nmetadata: { \"openclaw\": { \"emoji\": \"🌱\" } }\n---\n\n# Fulcra Onboarding — moved to `fulcra-get-started`\n\n> **This skill has been renamed.** `fulcra-onboarding` is deprecated and is kept only\n> as a pointer. All content now lives in the **`fulcra-get-started`** skill.\n\n## What to do\n\nUse the `fulcra-get-started` skill instead:\n\n- **In this repo:** `skills/fulcra-get-started/`\n- **GitHub:** https://github.com/fulcradynamics/agent-skills/tree/main/skills/fulcra-get-started\n- **Install:** `fulcradynamics/agent-skills/fulcra-get-started`\n\nIf you arrived here, read and follow `fulcra-get-started` — it walks you through\nconnecting to Fulcra for the first time (installing the CLI, logging in, and\nchoosing what to set up next).\n\nFile v0.3.0:_meta.json\n\n{\n  \"ownerId\": \"kn72pt2cb5f9nskgc9k2ddecxs87547j\",\n  \"slug\": \"fulcra-onboarding\",\n  \"version\": \"0.3.0\",\n  \"publishedAt\": 1786567378062\n}\n\nFile v0.3.0:skill-card.md\n\n## Description:\n\nDeprecated; renamed to fulcra-get-started. Use the fulcra-get-started skill instead.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[fulcra](https://clawhub.ai/user/fulcra)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this deprecated skill as a migration pointer to the fulcra-get-started skill for Fulcra onboarding and setup.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The deprecated skill points agents to mutable replacement instructions that can include installation, login, token, or account-access steps.\n\nMitigation: Verify the fulcra-get-started package or repository version and review CLI installation, login, token, and account-access steps before following them.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/fulcra/skills/fulcra-onboarding)\n- [Fulcra publisher profile](https://clawhub.ai/user/fulcra)\n- [Fulcra replacement skill](https://github.com/fulcradynamics/agent-skills/tree/main/skills/fulcra-get-started)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, guidance, configuration]\n\n**Output Format:** [Markdown guidance with inline code identifiers]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Deprecated pointer to fulcra-get-started; no direct execution artifacts.]\n\n## Skill Version(s):\n\n0.3.0 (source: server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v0.2.0: 5 files, 10809 bytes\n\nFiles: references/fulcra-cli.md (9295b), references/fulcra-onboarding-auth.md (2091b), skill-card.md (2658b), SKILL.md (8963b), _meta.json (136b)\n\nFile v0.2.0:SKILL.md\n\n---\nname: fulcra-onboarding\ndescription: \"Guides a new user or agent through the initial setup, configuration, and capabilities of the Fulcra environment.\"\nhomepage: \"https://github.com/fulcradynamics/agent-skills\"\nlicense: \"MIT\"\nuser-invocable: true\nmetadata: { \"openclaw\": { \"emoji\": \"🌱\" } }\n---\n\n# Fulcra Onboarding\n\nGuide the user through connecting to Fulcra.\n\nFulcra helps agents know their user, know what's happening in their user's world, work with their user's other agents, and become more helpful over time.\n\nTo achieve these goals, Fulcra gives agents a shared place to access and store real-world data, record what matters, coordinate work, and discover what's new on every loop. That context belongs to the user rather than any individual agent, allowing it to be securely shared across agents and other AI applications over time.\n\n## General Guidelines\n\n- **Tone & Vibe:** Fulcra unlocks capabilities that individual agents cannot achieve on their own. Be engaging, conversational, and optimistic. Help the user imagine what becomes possible once their agents know them, know what's happening in their world, work together, and become more helpful over time.\n- **Optimize for Time-to-Wow:** Favor opinionated defaults over exhaustive discussion. The objective is to get the user to their first genuinely useful workflow as quickly as possible.\n- **Maintain Momentum:** If the user becomes stuck or overwhelmed, choose or recommend a sensible default and keep the getting started process moving forward.\n\n## Workflow: Getting Started\n\nGetting started with Fulcra follows a dynamic path. First, you get the user connected. Second, you help them imagine and choose a direction based on real problems they want to solve. Third, you deliver a tangible view and establish a persistent structure for ongoing work before transitioning to the next steps.\n\nTo deliver something useful that works and has iteration and visibility, you should leverage the following core Fulcra skills:\n- **`fulcradynamics/agent-skills/fulcra-agent-teams`**: At the center of making and coordinating things, it organizes the knowledge, tasks, plans, tracking, and results in files the user owns in their Fulcra account.\n- **`fulcradynamics/agent-skills/fulcra-ingest`**: Gets data and information into Fulcra so the user can make useful things connected to the real world and other people and data sources.\n- **`fulcradynamics/agent-skills/fulcra-situational-awareness`**: Shows agents everything that is changing so they can react and stay caught up on the project and general situation.\n- **`fulcradynamics/community-skills/fulcra-rapid-prototype`**: A flow for rapidly developing an idea into a result or solution.\n\n### Phase 1: Core Setup & Inspiration\n\n1. **Introduction to Fulcra:**\n   - Read the `references/fulcra-cli.md` file to understand the `fulcra-api` CLI context and capabilities.\n   - Start the conversation by giving the user a brief, exciting overview of what Fulcra is. Emphasize that getting started with Fulcra is about making something genuinely useful that solves a real problem or improves their existing systems.\n   - **Show Possibilities (The Five Branches):** There are five main branches for getting started. Use your creativity to inspire the user to choose one:\n     1. Make something new and useful.\n     2. Solve a specific problem.\n     3. Improve a setup we already have.\n     4. Share information with other users (e.g., share movie watching history to find recommendations for the group).\n     5. Choose a specific skill from the `fulcradynamics/community-skills` repo (a new but growing hub where agents and users can discover solutions to specific problems and explore concrete use cases for Fulcra) or something inspired by one.\n   - **Task Connection:** If you already know what specific task or job the user wants to accomplish, explicitly mention how Fulcra will help you do *that specific job* as a concrete example of its value.\n   - Tell the user that the first step is to get them connected to Fulcra by setting up the Fulcra CLI. **Do not execute any CLI setup or ask for installation permissions until you have introduced Fulcra.**\n\n2. **Connection Options & Pre-flight:**\n   There are two ways for agents to connect to Fulcra. You must determine the appropriate path before proceeding:\n\n   - **Option 1: Fulcra CLI (Preferred)**\n     The `fulcra-api` CLI is the primary interface and supports the widest range of Fulcra use cases. If you have full command-line access with outbound network connectivity, you should choose this option.\n     *Pre-flight Check:* Verify `uv` is installed (`uv --version`). It is required for all CLI interactions. If missing, ask the user for permission to install it. This must pass before proceeding to authentication.\n\n   - **Option 2: MCP Connector (Restricted Environments)**\n     Fulcra provides an MCP (Model Context Protocol) connector as an alternative option for restricted environments. To use MCP, fetch and read `https://fulcradynamics.github.io/developer-docs/mcp-server/` for setup instructions, and skip the CLI authentication steps below.\n\n3. **Authentication:**\n   - Read and execute the instructions in `references/fulcra-onboarding-auth.md`. This step securely authenticates the user via the Fulcra CLI. \n   - Once authenticated, celebrate the milestone! You are now ready to start making.\n\n### Phase 2: Direction & Tangible Delivery\n\nNow that the user is connected, work with them to choose their direction—whether it's a project of their own inspired by your examples, or falling back on a \"golden path\" (like connecting a data source and establishing agent workspaces).\n\n**Delivery milestone:** Whatever direction the user chooses, aim to deliver the following three things to the user before the final branching point where they transition to other specific skills. Try to do all three, but deliver whatever is viable based on their specific goals:\n\n1. **A Cool View:** Create and show the user a tangible view of what has been accomplished so far. This should represent real work done toward their chosen direction. Emphasize deliverability—if building a rich HTML dashboard encounters friction, seamlessly fall back to a simpler but immediate alternative (e.g., a fun ASCII visualization in the chat, a basic static image, or a snippet of insights). You should also provide a link to [Context Web Timeline](https://context.fulcradynamics.com/timeline?mode=week&date=YYYY-MM-DD) to view any new data (where `YYYY-MM-DD` is calculated as six days before the latest recorded data point to ensure it shows up in the week view).\n2. **Coordination of Continuing Work:** Establish how the work will continue. Leverage the `fulcra-agent-teams` skill to create a dedicated agent team for the project, and use the `fulcra-tracking` skill to establish specific data types (annotations) to track the project's milestones, tasks, or outputs in the Fulcra datastore. Ensure these data types are recorded in the team's knowledge.\n3. **Visibility of Work:** Provide a clear view of completed, present, and future work. You can do this by using the `fulcra-project-dashboard` skill (found in the community-skills repository) to make a robust management view of the team workspace. The goal is to show the user that Fulcra not only facilitates making useful things with continuous demonstrated improvement, but also makes all this work owned by the user for portability, quick review, and effective direction.\n\n### Phase 3: Transition & Explore More\n\nAfter delivering the view, coordination plan, and visibility artifact, transition the user to the specific skills needed to continue their chosen project (e.g., `fulcra-project-dashboard`, `fulcra-agent-teams`, `fulcra-tracking`). \n\nIf the user wants to explore further, you should present a curated, scannable menu of options based on the conversation so far. Rather than a static list, recommend a few relevant choices from these categories:\n\n1.  **Apps & Interfaces:**\n    - 📱 **Get the App:** Direct them to the [Fulcra Context iOS app](https://apps.apple.com/app/id1633037434) for on-the-go logging and background sync (warn them about sensitive data permissions like Health, location, and calendar).\n    - 💻 **Context Web:** Direct them to [Context Web](https://context.fulcradynamics.com/) to explore their datastore on desktop.\n2.  **Fulcra Skills:** Suggest specific skills from the `agent-skills` or `community-skills` repositories that align with their goals (e.g., `fulcra-tracking` for custom schemas/dashboards, `fulcra-memory` for knowledge logging, or `fulcra-rapid-prototype` for quick builds).\n3.  **The Fulcra Cookbook:** Point them to the [Fulcra Cookbook](https://www.fulcradynamics.com/resources/cookbook) to explore more recipes, tutorials, and inspiration for what to make next.\n\n**When the user makes a choice, follow through by applying the chosen skill or guiding them to the requested resource.**\n\nFile v0.2.0:_meta.json\n\n{\n  \"ownerId\": \"kn72pt2cb5f9nskgc9k2ddecxs87547j\",\n  \"slug\": \"fulcra-onboarding\",\n  \"version\": \"0.2.0\",\n  \"publishedAt\": 1785431064391\n}\n\nFile v0.2.0:references/fulcra-cli.md\n\n# Fulcra CLI\n\nFulcra Context is a universal data and memory platform that collects and records any data a user wants to ingest from any source. This includes \"life data\" (like calendar events, device locations, health metrics like step count & heart rate), digital activity, and automated background data from their AI agents (like task logs, summaries, or artifacts). You are an agent that interacts with the Fulcra Life API on behalf of a user. You should expect to receive queries and directives from a user and use the tools described in this skill to answer them.\n\n\n## Installation\n\nThe `fulcra-api` CLI command is the easiest way to interact with the Life API and can be installed and run via `uv tool run`:\n\n```\nuv tool run fulcra-api\n```\n\n\n## Authentication\n\nUse the `auth login` subcommand to authenticate to Fulcra on behalf of a user.\n\nThe `fulcra-api auth login` command should be run in a two-step process to avoid hanging and timing out while waiting for the user. \n\n**Step 1: Get the Auth URL**\nRun the command with the `--get-auth-url` flag. It will immediately return a web auth URL, a user verification code, and a device code.\n```\nuv tool run fulcra-api auth login --get-auth-url\n```\nYou must extract the URL and user code and present them to the user so they can complete the flow in their browser. Keep the device code for the next step. **You must present the URL and code directly to the user; do not assume their browser will automatically open.**\n\n**Step 2: Complete Authentication**\nAfter the user confirms they have completed the flow in their browser, finish the login process by passing the device code. We pass `--poll-timeout=5` so the command fails quickly if there is a miscommunication about whether the flow is actually finished.\n```\nuv tool run fulcra-api auth login --device-code <DEVICE_CODE> --poll-timeout=5\n```\n\n**Network Restrictions:** If the login command immediately fails or prints a raw `<http.client.HTTPResponse object...>` error, your shell likely lacks outbound network access. Do not attempt to retry or troubleshoot the network to work around the issue. Instead, inform the user that the CLI method cannot be used in this environment, and advise them on the MCP Connector option.\n\nCredentials will be persisted on the filesystem to `~/.config/fulcra/credentials.json` and the tool will refresh access tokens as neccessary.\n\n\n## Usage\n\nRely on the `--help` flag for in depth documentation on the command and individual subcommands.\n\n```\nuv tool run fulcra-api --help\n```\n\nAll command output, except for `auth`, is in JSON format and can be piped into another tool like `jq` for parsing and filtering structured data.\n\nAll date/time fields are returned in ISO 8601 format, time zone aware, and in UTC. They should be converted to a user's local time zone. Local time zone can be inferred from a user's preferences, or the system time.\n\n\n## Examples\n\nAuthenticate to the API:\n```\nuv tool run fulcra-api auth login --get-auth-url\n# ... present url/code to user, then ...\nuv tool run fulcra-api auth login --device-code <DEVICE_CODE> --poll-timeout=5\n```\n\nGet list of Fulcra data type identifiers:\n```\nuv tool run fulcra-api catalog | jq -r '.id'\n```\n\nReturn last week of step count records:\n```\nuv tool run fulcra-api get-records StepCount \"1 week\"\n```\n\nReturn a calculated time series of heart rate data for the last week:\n```\nuv tool run fulcra-api metric-time-series HeartRate \"1 week\"\n```\n\nReturn a user's configured time zone from user preferences:\n```\nuv tool run fulcra-api user-info | jq -r '.preferences.timezone'\n```\n\n## Creating Custom Data Types (Annotations)\n\nFulcra supports creating custom schemas based on specific root \"base types.\" You can create new schemas easily via the CLI.\n\n```bash\nuv tool run fulcra-api data-type create <BASE_DATA_TYPE> \"<NAME>\" --description \"<DESCRIPTION>\"\n```\n\n### Base Data Types\nRun `uv tool run fulcra-api catalog --base-types-only` to see the exact IDs of the base types you can build upon.\nThe most common base types for custom tracking are:\n*   `MomentAnnotation`: For tracking occurrences of an event without a specific measurement (e.g., \"Took Medication\").\n*   `NumericAnnotation`: For tracking a specific quantity or number (e.g., \"Cups of Coffee\").\n*   `BooleanAnnotation`: For tracking simple Yes/No or True/False states (e.g., \"Did I go to the gym?\").\n*   `ScaleAnnotation`: For 1-5 scales (e.g., mood, pain, intensity).\n\n### Creation Examples\n```bash\n# Create a simple moment annotation\nuv tool run fulcra-api data-type create MomentAnnotation \"Daily Walk\" --description \"Went for a walk today\"\n\n# Create a boolean annotation\nuv tool run fulcra-api data-type create BooleanAnnotation \"Ate Breakfast\" --description \"Did I eat breakfast?\"\n\n# Create a numeric annotation\nuv tool run fulcra-api data-type create NumericAnnotation \"Water Consumed\" --description \"Ounces of water drank\"\n\n# Create a scale annotation\nuv tool run fulcra-api data-type create ScaleAnnotation \"Daily Mood\" --description \"1-5 scale of mood\"\n```\n\nThe `create` command will output the JSON definition of the new data type. Make sure to capture the returned `\"id\"` value (e.g., `com.fulcradynamics.annotation.12345`), as you will need it to record data against this schema.\n\n## Fulcra File Store & Open Knowledge Format (OKF)\n\nThe Fulcra File Store is an environment-agnostic remote filesystem accessed via the `fulcra-api file` commands. When storing text and markdown data in the file store, agents should adhere to the **Open Knowledge Format (OKF)** standard (v0.1) when possible to ensure the file store remains understandable to users and other agents, and to provide auditability. You can read the full OKF specification here: [https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md](https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md).\n\n### File Uploads\n\nYou can manage versioned files using the `fulcra-api file` commands. This allows you to upload files directly into the Fulcra File Store, which will automatically track revisions and handle versioning.\n\n```bash\n# Upload a file to a specific remote path\nuv tool run fulcra-api file upload ./local-file.md /remote/path/file.md\n\n# List files in a remote directory\nuv tool run fulcra-api file list /remote/path/\n\n# Get information about a file, including previous versions\nuv tool run fulcra-api file stat /remote/path/file.md\n\n# Download a file from the remote path\nuv tool run fulcra-api file download /remote/path/file.md ./downloaded-file.md\n```\n\n### Core OKF Principles\n*   **Markdown + YAML Frontmatter:** All knowledge concepts should be written as `.md` files containing a YAML frontmatter block at the top, bordered by `---`. The frontmatter must contain at least a `type: <Type name>` field, and may optionally include `title:`, `description:`, `tags:`, etc.\n*   **`index.md` (Directory Listing):** Each directory should contain an `index.md` file (with no frontmatter). It provides progressive disclosure via grouped lists of links to the files within that directory (e.g., `* [Title](relative-url.md) - description`).\n*   **`log.md` (Update History):** Each directory should contain a `log.md` file to record a chronological history of changes. It contains date-grouped headings (e.g., `## YYYY-MM-DD`) with bulleted entries describing the updates (e.g., `* **Update**: Added new context file.`).\n\nWhile OKF compliance is important, it must not become cumbersome.\n- For directories that contain many small or transient items, simply list the directory itself in the `index.md` with a high-level description of its purpose.\n- Keep the `index.md` and `log.md` focused on top-level structure and significant milestones so they remain useful but lightweight.\n\n### Artifacts Directory\nTo maintain a clean OKF directory structure, any binary files, media, images, compiled code, or non-markdown files should be stored inside a dedicated `artifact/` subdirectory within the relevant namespace.\n\n## Further Reading & References\n\nAs an agent, you should rely on the `fulcra-api` CLI as the primary and most robust way to interact with Fulcra. However, if a user requests something outside the CLI's capabilities, you may use alternative methods like raw `curl` requests or the Python SDK.\n\nTo maintain your context as Fulcra evolves, or to assist users with deeper technical questions, you can consult the following external resources:\n- **Fulcra Website:** [https://www.fulcradynamics.com/](https://www.fulcradynamics.com/)\n- **REST API Documentation:** [https://fulcradynamics.github.io/developer-docs/api-reference/](https://fulcradynamics.github.io/developer-docs/api-reference/)\n- **Python SDK & CLI Source:** [https://github.com/fulcradynamics/fulcra-api-python/](https://github.com/fulcradynamics/fulcra-api-python/)\n- **Fulcra MCP:** Fulcra also has an MCP (Model Context Protocol) interface that you can learn more about at [https://fulcradynamics.github.io/developer-docs/mcp-server/](https://fulcradynamics.github.io/developer-docs/mcp-server/)\n- **Fulcra Agent Skills Repository:** [https://github.com/fulcradynamics/agent-skills](https://github.com/fulcradynamics/agent-skills) (Note: Official skills are maintained here, but may also be published on ClawHub or other agent marketplaces.)\n\nFile v0.2.0:references/fulcra-onboarding-auth.md\n\n---\nname: fulcra-onboarding-auth\ndescription: \"Handles initial authentication for the Fulcra CLI.\"\n---\n\n# Fulcra Getting Started: Authentication\n\nThis reference handles Step 2 of the getting started process, securely establishing the user's connection to Fulcra.\n\n## Workflow\n\n1. **Authentication Check & Login (Requires Consent):**\n   - Briefly explain that you need to connect to their Fulcra account via the command line.\n   - **Ask for their explicit permission** to check their Fulcra authentication state and initiate a login flow.\n   - **How to verify:** After obtaining consent, run `uv tool run fulcra-api user-info`. If it returns valid JSON, the user is authenticated and you can proceed immediately to the next step.\n   - If not authenticated, explain that you will now generate a secure login link.\n   - Run `uv tool run fulcra-api auth login --get-auth-url` using the `exec` tool.\n   - **CRITICAL EXECUTION NOTE:** You must ALWAYS execute this command using the `--get-auth-url` flag so it does not hang and poll. The command will output a web auth URL, a web auth user code, and a device code.\n   - You **MUST** present the URL and the user code directly to the user in your chat message as a clickable markdown link where the URL itself is the text (e.g., `[https://...](https://...)`), tell them the user code, and tell them to complete the flow in their browser.\n   - **Important:** Keep the device code secret/safe; you will need it for the next step. Do *not* combine the authentication instructions with further brainstorming.\n   - Wait for the user to confirm they have completed the flow in their browser.\n   - Once they confirm, run `uv tool run fulcra-api auth login --device-code <DEVICE CODE> --poll-timeout=5` to complete the authentication process. The timeout ensures the command fails quickly if they haven't actually completed the flow.\n\n2. **Completion:**\n   - Once the device code login succeeds (or if they were already authenticated), declare the core setup complete!\n   - Hand control back to the main getting started flow to present the Next Steps menu.\n\nFile v0.2.0:skill-card.md\n\n## Description: <br>\nGuides a new user or agent through the initial setup, configuration, and capabilities of the Fulcra environment. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[fulcra](https://clawhub.ai/user/fulcra) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nExternal users and their agents use this skill to connect to Fulcra, authenticate with the Fulcra CLI or MCP connector, choose a useful onboarding direction, and create an initial view, coordination structure, or project dashboard. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill connects an agent to a Fulcra account that may contain sensitive personal data such as health, location, calendar, activity, and agent artifacts. <br>\nMitigation: Use it only when the user wants Fulcra account access, request explicit consent before authentication or sensitive data access, and keep actions scoped to the user's stated goal. <br>\nRisk: Authentication uses a browser login flow and can store Fulcra credentials on the local filesystem. <br>\nMitigation: Use the documented device-code flow, keep the device code private, and make local credential storage clear before completing setup. <br>\nRisk: The skill may create persistent records or upload local files to Fulcra. <br>\nMitigation: Confirm with the user before uploading files or creating persistent records, and explain what will be stored in Fulcra. <br>\n\n\n## Reference(s): <br>\n- [Fulcra CLI](references/fulcra-cli.md) <br>\n- [Fulcra Getting Started: Authentication](references/fulcra-onboarding-auth.md) <br>\n- [Fulcra MCP documentation](https://fulcradynamics.github.io/developer-docs/mcp-server/) <br>\n- [Context Web](https://context.fulcradynamics.com/) <br>\n- [Fulcra Cookbook](https://www.fulcradynamics.com/resources/cookbook) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [guidance, markdown, code, shell commands, configuration] <br>\n**Output Format:** [Conversational Markdown with links, inline shell commands, and setup guidance.] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May guide browser-based authentication, Fulcra CLI setup, data views, project files, and persistent Fulcra records with user consent.] <br>\n\n## Skill Version(s): <br>\n0.2.0 (source: server release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v0.1.7: 5 files, 10073 bytes\n\nFiles: references/fulcra-cli.md (9295b), references/fulcra-onboarding-auth.md (2090b), skill-card.md (2593b), SKILL.md (7514b), _meta.json (136b)\n\nFile v0.1.7:SKILL.md\n\n---\nname: fulcra-onboarding\ndescription: \"Guides a new user or agent through the initial setup, configuration, and capabilities of the Fulcra environment.\"\nhomepage: \"https://github.com/fulcradynamics/agent-skills\"\nlicense: \"MIT\"\nuser-invocable: true\nmetadata: { \"openclaw\": { \"emoji\": \"🌱\" } }\n---\n\n# Fulcra Onboarding\n\nGuide the user through connecting to Fulcra.\n\nFulcra helps agents know their user, know what's happening in their user's world, work with their user's other agents, and become more helpful over time.\n\nTo achieve these goals, Fulcra gives agents a shared place to access and store real-world data, record what matters, coordinate work, and discover what's new on every loop. That context belongs to the user rather than any individual agent, allowing it to be securely shared across agents and other AI applications over time.\n\n## General Guidelines\n\n- **Tone & Vibe:** Fulcra unlocks capabilities that individual agents cannot achieve on their own. Be engaging, conversational, and optimistic. Help the user imagine what becomes possible once their agents know them, know what's happening in their world, work together, and become more helpful over time.\n- **Optimize for Time-to-Wow:** Favor opinionated defaults over exhaustive discussion. The objective is to get the user to their first genuinely useful workflow as quickly as possible.\n- **Maintain Momentum:** If the user becomes stuck or overwhelmed, choose or recommend a sensible default and keep the onboarding moving forward.\n\n## Workflow: Guided Path\n\nThe onboarding process follows a guided three-phase model. First, you get the user connected. Second, you recommend a powerful \"golden path\" of core agent capabilities. Third, you present a menu of additional options.\n\n### Phase 1: Core Setup\n\n1. **Introduction to Fulcra:**\n   - Read the `references/fulcra-cli.md` file to understand the `fulcra-api` CLI context and capabilities.\n   - Start the conversation by giving the user a brief, exciting overview of what Fulcra is. **Specifically describe Fulcra as giving your agents a way to access and store real-world data, coordinate tasks, and know what's new on every loop, from a place that lives and moves with you across agents.**\n   - **Task Connection:** If you already know what specific task or job the user wants you to accomplish, explicitly mention how Fulcra will help you do *that specific job* as a concrete example of its value.\n   - Tell the user that the first step is to get them connected to Fulcra by setting up the Fulcra CLI. **Do not execute any CLI setup or ask for installation permissions until you have introduced Fulcra.**\n\n2. **Connection Options & Pre-flight:**\n   There are two ways for agents to connect to Fulcra. You must determine the appropriate path before proceeding:\n\n   - **Option 1: Fulcra CLI (Preferred)**\n     The `fulcra-api` CLI is the primary interface and supports the widest range of Fulcra use cases. If you have full command-line access with outbound network connectivity, you should choose this option.\n     *Pre-flight Check:* Verify `uv` is installed (`uv --version`). It is required for all CLI interactions. If missing, ask the user for permission to install it. This must pass before proceeding to authentication.\n\n   - **Option 2: MCP Connector (Restricted Environments)**\n     Fulcra provides an MCP (Model Context Protocol) connector as an alternative option for restricted environments. To use MCP, fetch and read `https://fulcradynamics.github.io/developer-docs/mcp-server/` for setup instructions, and skip the CLI authentication steps below.\n\n3. **Authentication:**\n   - Read and execute the instructions in `references/fulcra-onboarding-auth.md`. This step securely authenticates the user via the Fulcra CLI. \n   - Once authenticated, declare that the core onboarding is complete! Celebrate this milestone.\n\n### Phase 2: Task-Driven or Recommended Flow\n\nImmediately after declaring the core onboarding complete, you must determine the best path forward based on your current context:\n\n**Option A: The Task-Driven Path (Prioritize this!)**\nIf you already know what specific task, job, or goal the user wants you to accomplish (e.g., they asked you to \"build a health dashboard\", \"ingest my Spotify history\", or \"set up my inbox\"), you should prioritize that specific task to deliver value as quickly as possible.\n- Briefly explain how Fulcra will facilitate their specific goal.\n- Ask for their confirmation to branch off and immediately start working on that task (transitioning to the relevant skills), rather than going through the generic tour.\n\n**Option B: The Standard Recommended Path**\nIf the user hasn't given you a specific task and is just exploring Fulcra generally, recommend this specific post-onboarding sequence. Ask them if they'd like to be guided through this sequence, explaining that it is the most truly useful way to get started with Fulcra:\n\n1.  **Connect a Data Source:** Bring real-world data into the datastore (using the `fulcradynamics/agent-skills/fulcra-ingest` skill).\n2.  **Know What's New:** Set up an automated loop so the agent knows what is new every loop (using the `fulcradynamics/agent-skills/fulcra-situational-awareness` skill).\n3.  **Set Up Workspaces:** Create an agent workspace that gives your agent an inbox, a place to save things it creates, and a way to coordinate and work with other agents and people (using the `fulcradynamics/agent-skills/fulcra-agent-teams` skill).\n\nIf they agree to the recommended path, transition them sequentially through these skills.\n\n### Phase 3: Explore More (The Menu)\n\nAfter they complete the recommended path, or if they decide they do not want to do it, present the following menu of additional options to explore the Fulcra skills, app, and web dashboard.\n\n**Present this exact scannable menu to the user:**\n\n1.  📊 **Agent Visibility & Custom Tracking:** Discover how to track custom data, agent visibility metrics, and visualize them using a custom dashboard.\n2.  🧠 **Agent Memory & Knowledge:** Record high-level knowledge, tasks, and progress directly to your Fulcra datastore.\n3.  📱 **Get the App:** Download the iOS app for on-the-go logging and background sync.\n4.  💻 **Context Web:** Explore your data on the desktop portal.\n\n**When the user makes a choice, follow the corresponding path below:**\n\n#### Path 1: Agent Visibility & Custom Tracking\n1. Explain that you can set up data schemas to track their custom data, as well as an \"Agent Visibility Package\" to record agent activities, and visualize it all on a custom HTML dashboard.\n2. If they consent and are interested, transition them to the `fulcradynamics/agent-skills/fulcra-tracking` skill.\n\n#### Path 2: Agent Memory & Knowledge\n1. Explain that you can record high-level knowledge, track tasks, and log ongoing progress directly to their Fulcra datastore in a structured, readable way.\n2. If they consent, transition them to the `fulcradynamics/agent-skills/fulcra-memory` skill to set up their memory tracking.\n\n#### Path 3: Get the App\n1. Direct them to the [Fulcra Context iOS app](https://apps.apple.com/app/id1633037434).\n2. Mention it unlocks automatic background sync (Health, location, calendar). **PRIVACY WARNING:** Explicitly inform the user these are highly sensitive data types requiring explicit iOS permissions, and they have full control to decline.\n\n#### Path 4: Context Web\n1. Direct them to [Context Web](https://context.fulcradynamics.com/) to explore their datastore on desktop.\n\nFile v0.1.7:_meta.json\n\n{\n  \"ownerId\": \"kn72pt2cb5f9nskgc9k2ddecxs87547j\",\n  \"slug\": \"fulcra-onboarding\",\n  \"version\": \"0.1.7\",\n  \"publishedAt\": 1784655930714\n}\n\nFile v0.1.7:references/fulcra-cli.md\n\n# Fulcra CLI\n\nFulcra Context is a universal data and memory platform that collects and records any data a user wants to ingest from any source. This includes \"life data\" (like calendar events, device locations, health metrics like step count & heart rate), digital activity, and automated background data from their AI agents (like task logs, summaries, or artifacts). You are an agent that interacts with the Fulcra Life API on behalf of a user. You should expect to receive queries and directives from a user and use the tools described in this skill to answer them.\n\n\n## Installation\n\nThe `fulcra-api` CLI command is the easiest way to interact with the Life API and can be installed and run via `uv tool run`:\n\n```\nuv tool run fulcra-api\n```\n\n\n## Authentication\n\nUse the `auth login` subcommand to authenticate to Fulcra on behalf of a user.\n\nThe `fulcra-api auth login` command should be run in a two-step process to avoid hanging and timing out while waiting for the user. \n\n**Step 1: Get the Auth URL**\nRun the command with the `--get-auth-url` flag. It will immediately return a web auth URL, a user verification code, and a device code.\n```\nuv tool run fulcra-api auth login --get-auth-url\n```\nYou must extract the URL and user code and present them to the user so they can complete the flow in their browser. Keep the device code for the next step. **You must present the URL and code directly to the user; do not assume their browser will automatically open.**\n\n**Step 2: Complete Authentication**\nAfter the user confirms they have completed the flow in their browser, finish the login process by passing the device code. We pass `--poll-timeout=5` so the command fails quickly if there is a miscommunication about whether the flow is actually finished.\n```\nuv tool run fulcra-api auth login --device-code <DEVICE_CODE> --poll-timeout=5\n```\n\n**Network Restrictions:** If the login command immediately fails or prints a raw `<http.client.HTTPResponse object...>` error, your shell likely lacks outbound network access. Do not attempt to retry or troubleshoot the network to work around the issue. Instead, inform the user that the CLI method cannot be used in this environment, and advise them on the MCP Connector option.\n\nCredentials will be persisted on the filesystem to `~/.config/fulcra/credentials.json` and the tool will refresh access tokens as neccessary.\n\n\n## Usage\n\nRely on the `--help` flag for in depth documentation on the command and individual subcommands.\n\n```\nuv tool run fulcra-api --help\n```\n\nAll command output, except for `auth`, is in JSON format and can be piped into another tool like `jq` for parsing and filtering structured data.\n\nAll date/time fields are returned in ISO 8601 format, time zone aware, and in UTC. They should be converted to a user's local time zone. Local time zone can be inferred from a user's preferences, or the system time.\n\n\n## Examples\n\nAuthenticate to the API:\n```\nuv tool run fulcra-api auth login --get-auth-url\n# ... present url/code to user, then ...\nuv tool run fulcra-api auth login --device-code <DEVICE_CODE> --poll-timeout=5\n```\n\nGet list of Fulcra data type identifiers:\n```\nuv tool run fulcra-api catalog | jq -r '.id'\n```\n\nReturn last week of step count records:\n```\nuv tool run fulcra-api get-records StepCount \"1 week\"\n```\n\nReturn a calculated time series of heart rate data for the last week:\n```\nuv tool run fulcra-api metric-time-series HeartRate \"1 week\"\n```\n\nReturn a user's configured time zone from user preferences:\n```\nuv tool run fulcra-api user-info | jq -r '.preferences.timezone'\n```\n\n## Creating Custom Data Types (Annotations)\n\nFulcra supports creating custom schemas based on specific root \"base types.\" You can create new schemas easily via the CLI.\n\n```bash\nuv tool run fulcra-api data-type create <BASE_DATA_TYPE> \"<NAME>\" --description \"<DESCRIPTION>\"\n```\n\n### Base Data Types\nRun `uv tool run fulcra-api catalog --base-types-only` to see the exact IDs of the base types you can build upon.\nThe most common base types for custom tracking are:\n*   `MomentAnnotation`: For tracking occurrences of an event without a specific measurement (e.g., \"Took Medication\").\n*   `NumericAnnotation`: For tracking a specific quantity or number (e.g., \"Cups of Coffee\").\n*   `BooleanAnnotation`: For tracking simple Yes/No or True/False states (e.g., \"Did I go to the gym?\").\n*   `ScaleAnnotation`: For 1-5 scales (e.g., mood, pain, intensity).\n\n### Creation Examples\n```bash\n# Create a simple moment annotation\nuv tool run fulcra-api data-type create MomentAnnotation \"Daily Walk\" --description \"Went for a walk today\"\n\n# Create a boolean annotation\nuv tool run fulcra-api data-type create BooleanAnnotation \"Ate Breakfast\" --description \"Did I eat breakfast?\"\n\n# Create a numeric annotation\nuv tool run fulcra-api data-type create NumericAnnotation \"Water Consumed\" --description \"Ounces of water drank\"\n\n# Create a scale annotation\nuv tool run fulcra-api data-type create ScaleAnnotation \"Daily Mood\" --description \"1-5 scale of mood\"\n```\n\nThe `create` command will output the JSON definition of the new data type. Make sure to capture the returned `\"id\"` value (e.g., `com.fulcradynamics.annotation.12345`), as you will need it to record data against this schema.\n\n## Fulcra File Store & Open Knowledge Format (OKF)\n\nThe Fulcra File Store is an environment-agnostic remote filesystem accessed via the `fulcra-api file` commands. When storing text and markdown data in the file store, agents should adhere to the **Open Knowledge Format (OKF)** standard (v0.1) when possible to ensure the file store remains understandable to users and other agents, and to provide auditability. You can read the full OKF specification here: [https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md](https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md).\n\n### File Uploads\n\nYou can manage versioned files using the `fulcra-api file` commands. This allows you to upload files directly into the Fulcra File Store, which will automatically track revisions and handle versioning.\n\n```bash\n# Upload a file to a specific remote path\nuv tool run fulcra-api file upload ./local-file.md /remote/path/file.md\n\n# List files in a remote directory\nuv tool run fulcra-api file list /remote/path/\n\n# Get information about a file, including previous versions\nuv tool run fulcra-api file stat /remote/path/file.md\n\n# Download a file from the remote path\nuv tool run fulcra-api file download /remote/path/file.md ./downloaded-file.md\n```\n\n### Core OKF Principles\n*   **Markdown + YAML Frontmatter:** All knowledge concepts should be written as `.md` files containing a YAML frontmatter block at the top, bordered by `---`. The frontmatter must contain at least a `type: <Type name>` field, and may optionally include `title:`, `description:`, `tags:`, etc.\n*   **`index.md` (Directory Listing):** Each directory should contain an `index.md` file (with no frontmatter). It provides progressive disclosure via grouped lists of links to the files within that directory (e.g., `* [Title](relative-url.md) - description`).\n*   **`log.md` (Update History):** Each directory should contain a `log.md` file to record a chronological history of changes. It contains date-grouped headings (e.g., `## YYYY-MM-DD`) with bulleted entries describing the updates (e.g., `* **Update**: Added new context file.`).\n\nWhile OKF compliance is important, it must not become cumbersome.\n- For directories that contain many small or transient items, simply list the directory itself in the `index.md` with a high-level description of its purpose.\n- Keep the `index.md` and `log.md` focused on top-level structure and significant milestones so they remain useful but lightweight.\n\n### Artifacts Directory\nTo maintain a clean OKF directory structure, any binary files, media, images, compiled code, or non-markdown files should be stored inside a dedicated `artifact/` subdirectory within the relevant namespace.\n\n## Further Reading & References\n\nAs an agent, you should rely on the `fulcra-api` CLI as the primary and most robust way to interact with Fulcra. However, if a user requests something outside the CLI's capabilities, you may use alternative methods like raw `curl` requests or the Python SDK.\n\nTo maintain your context as Fulcra evolves, or to assist users with deeper technical questions, you can consult the following external resources:\n- **Fulcra Website:** [https://www.fulcradynamics.com/](https://www.fulcradynamics.com/)\n- **REST API Documentation:** [https://fulcradynamics.github.io/developer-docs/api-reference/](https://fulcradynamics.github.io/developer-docs/api-reference/)\n- **Python SDK & CLI Source:** [https://github.com/fulcradynamics/fulcra-api-python/](https://github.com/fulcradynamics/fulcra-api-python/)\n- **Fulcra MCP:** Fulcra also has an MCP (Model Context Protocol) interface that you can learn more about at [https://fulcradynamics.github.io/developer-docs/mcp-server/](https://fulcradynamics.github.io/developer-docs/mcp-server/)\n- **Fulcra Agent Skills Repository:** [https://github.com/fulcradynamics/agent-skills](https://github.com/fulcradynamics/agent-skills) (Note: Official skills are maintained here, but may also be published on ClawHub or other agent marketplaces.)\n\nFile v0.1.7:references/fulcra-onboarding-auth.md\n\n---\nname: fulcra-onboarding-auth\ndescription: \"Handles initial authentication for the Fulcra CLI.\"\n---\n\n# Fulcra Onboarding: Authentication\n\nThis reference handles Step 2 of the onboarding process, securely establishing the user's connection to Fulcra.\n\n## Workflow\n\n1. **Authentication Check & Login (Requires Consent):**\n   - Briefly explain that you need to connect to their Fulcra account via the command line.\n   - **Ask for their explicit permission** to check their Fulcra authentication state and initiate a login flow.\n   - **How to verify:** After obtaining consent, run `uv tool run fulcra-api user-info`. If it returns valid JSON, the user is authenticated and you can proceed immediately to the next step.\n   - If not authenticated, explain that you will now generate a secure login link.\n   - Run `uv tool run fulcra-api auth login --get-auth-url` using the `exec` tool.\n   - **CRITICAL EXECUTION NOTE:** You must ALWAYS execute this command using the `--get-auth-url` flag so it does not hang and poll. The command will output a web auth URL, a web auth user code, and a device code.\n   - You **MUST** present the URL and the user code directly to the user in your chat message as a clickable markdown link where the URL itself is the text (e.g., `[https://...](https://...)`), tell them the user code, and tell them to complete the flow in their browser.\n   - **Important:** Keep the device code secret/safe; you will need it for the next step. Do *not* combine the authentication instructions with further brainstorming.\n   - Wait for the user to confirm they have completed the flow in their browser.\n   - Once they confirm, run `uv tool run fulcra-api auth login --device-code <DEVICE CODE> --poll-timeout=5` to complete the authentication process. The timeout ensures the command fails quickly if they haven't actually completed the flow.\n\n2. **Completion:**\n   - Once the device code login succeeds (or if they were already authenticated), declare the core onboarding complete!\n   - Hand control back to the main `fulcra-onboarding` flow to present the Next Steps menu.\n\nFile v0.1.7:skill-card.md\n\n## Description: <br>\nGuides a new user or agent through the initial setup, configuration, and capabilities of the Fulcra environment. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[fulcra](https://clawhub.ai/user/fulcra) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nExternal users and agents use this skill to connect to Fulcra, authenticate the Fulcra CLI or MCP connector, and choose a task-driven or recommended onboarding path for Fulcra capabilities. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Authentication or CLI actions may connect an agent to sensitive Fulcra life data. <br>\nMitigation: Require explicit user consent before checking authentication state or initiating login, and present the authentication URL and user code directly to the user. <br>\nRisk: Fulcra CLI capabilities can access sensitive data, create schemas, and manage remote files when directed. <br>\nMitigation: Review prompts and proposed commands before approval, especially actions involving data access, schema creation, file upload, or remote file management. <br>\nRisk: Network-restricted environments may fail during CLI authentication. <br>\nMitigation: Use the documented MCP connector path when CLI network access is unavailable. <br>\n\n\n## Reference(s): <br>\n- [Fulcra Onboarding on ClawHub](https://clawhub.ai/fulcra/skills/fulcra-onboarding) <br>\n- [Fulcra publisher profile](https://clawhub.ai/user/fulcra) <br>\n- [Fulcra CLI reference](references/fulcra-cli.md) <br>\n- [Fulcra onboarding authentication reference](references/fulcra-onboarding-auth.md) <br>\n- [Fulcra MCP connector documentation](https://fulcradynamics.github.io/developer-docs/mcp-server/) <br>\n- [Fulcra Context iOS app](https://apps.apple.com/app/id1633037434) <br>\n- [Context Web](https://context.fulcradynamics.com/) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [guidance, shell commands, configuration, markdown] <br>\n**Output Format:** [Markdown guidance with inline shell commands and links] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Prompts for user consent before authentication and presents task-driven next steps.] <br>\n\n## Skill Version(s): <br>\n0.1.7 (source: release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v0.1.6: 6 files, 10661 bytes\n\nFiles: references/fulcra-cli.md (9295b), references/fulcra-onboarding-auth.md (2090b), references/fulcra-onboarding-prerequisites.md (2070b), skill-card.md (3018b), SKILL.md (5605b), _meta.json (136b)\n\nFile v0.1.6:SKILL.md\n\n---\nname: fulcra-onboarding\ndescription: \"Guides a new user or agent through the initial setup, configuration, and capabilities of the Fulcra environment.\"\nhomepage: \"https://github.com/fulcradynamics/agent-skills\"\nlicense: \"MIT\"\nuser-invocable: true\nmetadata: { \"openclaw\": { \"emoji\": \"🌱\" } }\n---\n\n# Fulcra Onboarding\n\nPrimary onboarding flow for new users connecting to the Fulcra environment. Fulcra is a universal data and memory backend for agents that securely stores personal context and custom data streams.\n\n## General Guidelines\n\n- **Tone & Vibe (The \"Wow\" Factor):** Fulcra unlocks massive potential because it acts as a universal memory and data backend for agents. Your tone should reflect this excitement and vast possibility. Be engaging, conversational, and fun.\n- **Use Emojis:** Liberally (but tastefully) use emojis throughout the onboarding process, especially when presenting lists, options, or celebrating a successful step. **However, always defer to the user's overarching formatting preferences or memory instructions. If a user explicitly asks for no emojis or a more professional tone, respect their constraints over this guideline.**\n- **Maintain Momentum:** Keep the user moving forward. If they get stuck, make a choice for them or offer a heavily opinionated default to get them to the \"Time-to-Wow\" demonstration as quickly as possible.\n\n## Workflow: Guided Path\n\nThe onboarding process follows a guided three-phase model. First, you get the user connected. Second, you recommend a powerful \"golden path\" of core agent capabilities. Third, you present a menu of additional options.\n\n### Phase 1: Core Setup\n\n1. **Introduction to Fulcra:**\n   - Read the `references/fulcra-cli.md` file to understand the `fulcra-api` CLI context and capabilities.\n   - Start the conversation by giving the user a brief, exciting overview of what Fulcra is. **Specifically describe Fulcra as giving your agents a way to access and store real-world data, coordinate tasks, and know what's new on every loop, from a place that lives and moves with you across agents.**\n   - Tell the user that the first step is to get them connected to Fulcra by setting up the Fulcra CLI. **Do not execute any CLI setup or ask for installation permissions until you have introduced Fulcra.**\n\n2. **Pre-flight Check & Context:**\n   - Read and execute the instructions in `references/fulcra-onboarding-prerequisites.md` to verify and install `uv` if necessary, asking the user for confirmation before installation. This must pass before proceeding.\n\n3. **Authentication:**\n   - Read and execute the instructions in `references/fulcra-onboarding-auth.md`. This step securely authenticates the user via the Fulcra CLI. \n   - Once authenticated, declare that the core onboarding is complete! Celebrate this milestone.\n\n### Phase 2: The Recommended Flow\n\nImmediately after declaring the core onboarding complete, recommend a specific post-onboarding path to the user. Ask them if they'd like to be guided through this sequence, explaining that it is the most truly useful way to get started with Fulcra:\n\n1.  **Connect a Data Source:** Bring real-world data into the datastore (using the `fulcradynamics/agent-skills/fulcra-ingest-beta` skill).\n2.  **Know What's New:** Set up an automated loop so the agent knows what is new every loop (using the `fulcradynamics/agent-skills/fulcra-situational-awareness` skill).\n3.  **Set Up Agent Teams:** Set up an agent team for one or more agents to build knowledge and complete tasks (using the `fulcradynamics/agent-skills/fulcra-agent-teams` skill).\n\nIf they agree, transition them sequentially through these skills.\n\n### Phase 3: Explore More (The Menu)\n\nAfter they complete the recommended path, or if they decide they do not want to do it, present the following menu of additional options to explore the Fulcra skills, app, and web dashboard.\n\n**Present this exact scannable menu to the user:**\n\n1.  📊 **Agent Visibility & Custom Tracking:** Discover how to track custom data, agent visibility metrics, and visualize them using a custom dashboard.\n2.  🧠 **Agent Memory & Knowledge:** Record high-level knowledge, tasks, and progress directly to your Fulcra datastore.\n3.  📱 **Get the App:** Download the iOS app for on-the-go logging and background sync.\n4.  💻 **Context Web:** Explore your data on the desktop portal.\n\n**When the user makes a choice, follow the corresponding path below:**\n\n#### Path 1: Agent Visibility & Custom Tracking\n1. Explain that you can set up data schemas to track their custom data, as well as an \"Agent Visibility Package\" to record agent activities, and visualize it all on a custom HTML dashboard.\n2. If they consent and are interested, transition them to the `fulcradynamics/agent-skills/fulcra-tracking` skill.\n\n#### Path 2: Agent Memory & Knowledge\n1. Explain that you can record high-level knowledge, track tasks, and log ongoing progress directly to their Fulcra datastore in a structured, readable way.\n2. If they consent, transition them to the `fulcradynamics/agent-skills/fulcra-memory` skill to set up their memory tracking.\n\n#### Path 3: Get the App\n1. Direct them to the [Fulcra Context iOS app](https://apps.apple.com/app/id1633037434).\n2. Mention it unlocks automatic background sync (Health, location, calendar). **PRIVACY WARNING:** Explicitly inform the user these are highly sensitive data types requiring explicit iOS permissions, and they have full control to decline.\n\n#### Path 4: Context Web\n1. Direct them to [Context Web](https://context.fulcradynamics.com/) to explore their datastore on desktop.\n\nFile v0.1.6:_meta.json\n\n{\n  \"ownerId\": \"kn72pt2cb5f9nskgc9k2ddecxs87547j\",\n  \"slug\": \"fulcra-onboarding\",\n  \"version\": \"0.1.6\",\n  \"publishedAt\": 1782943572799\n}\n\nFile v0.1.6:references/fulcra-cli.md\n\n# Fulcra CLI\n\nFulcra Context is a universal data and memory platform that collects and records any data a user wants to ingest from any source. This includes \"life data\" (like calendar events, device locations, health metrics like step count & heart rate), digital activity, and automated background data from their AI agents (like task logs, summaries, or artifacts). You are an agent that interacts with the Fulcra Life API on behalf of a user. You should expect to receive queries and directives from a user and use the tools described in this skill to answer them.\n\n\n## Installation\n\nThe `fulcra-api` CLI command is the easiest way to interact with the Life API and can be installed and run via `uv tool run`:\n\n```\nuv tool run fulcra-api\n```\n\n\n## Authentication\n\nUse the `auth login` subcommand to authenticate to Fulcra on behalf of a user.\n\nThe `fulcra-api auth login` command should be run in a two-step process to avoid hanging and timing out while waiting for the user. \n\n**Step 1: Get the Auth URL**\nRun the command with the `--get-auth-url` flag. It will immediately return a web auth URL, a user verification code, and a device code.\n```\nuv tool run fulcra-api auth login --get-auth-url\n```\nYou must extract the URL and user code and present them to the user so they can complete the flow in their browser. Keep the device code for the next step. **You must present the URL and code directly to the user; do not assume their browser will automatically open.**\n\n**Step 2: Complete Authentication**\nAfter the user confirms they have completed the flow in their browser, finish the login process by passing the device code. We pass `--poll-timeout=5` so the command fails quickly if there is a miscommunication about whether the flow is actually finished.\n```\nuv tool run fulcra-api auth login --device-code <DEVICE_CODE> --poll-timeout=5\n```\n\n**Network Restrictions:** If the login command immediately fails or prints a raw `<http.client.HTTPResponse object...>` error, your shell likely lacks outbound network access. Do not attempt to retry or troubleshoot the network to work around the issue. Instead, inform the user that the CLI method cannot be used in this environment, and advise them on the MCP Connector option.\n\nCredentials will be persisted on the filesystem to `~/.config/fulcra/credentials.json` and the tool will refresh access tokens as neccessary.\n\n\n## Usage\n\nRely on the `--help` flag for in depth documentation on the command and individual subcommands.\n\n```\nuv tool run fulcra-api --help\n```\n\nAll command output, except for `auth`, is in JSON format and can be piped into another tool like `jq` for parsing and filtering structured data.\n\nAll date/time fields are returned in ISO 8601 format, time zone aware, and in UTC. They should be converted to a user's local time zone. Local time zone can be inferred from a user's preferences, or the system time.\n\n\n## Examples\n\nAuthenticate to the API:\n```\nuv tool run fulcra-api auth login --get-auth-url\n# ... present url/code to user, then ...\nuv tool run fulcra-api auth login --device-code <DEVICE_CODE> --poll-timeout=5\n```\n\nGet list of Fulcra data type identifiers:\n```\nuv tool run fulcra-api catalog | jq -r '.id'\n```\n\nReturn last week of step count records:\n```\nuv tool run fulcra-api get-records StepCount \"1 week\"\n```\n\nReturn a calculated time series of heart rate data for the last week:\n```\nuv tool run fulcra-api metric-time-series HeartRate \"1 week\"\n```\n\nReturn a user's configured time zone from user preferences:\n```\nuv tool run fulcra-api user-info | jq -r '.preferences.timezone'\n```\n\n## Creating Custom Data Types (Annotations)\n\nFulcra supports creating custom schemas based on specific root \"base types.\" You can create new schemas easily via the CLI.\n\n```bash\nuv tool run fulcra-api data-type create <BASE_DATA_TYPE> \"<NAME>\" --description \"<DESCRIPTION>\"\n```\n\n### Base Data Types\nRun `uv tool run fulcra-api catalog --base-types-only` to see the exact IDs of the base types you can build upon.\nThe most common base types for custom tracking are:\n*   `MomentAnnotation`: For tracking occurrences of an event without a specific measurement (e.g., \"Took Medication\").\n*   `NumericAnnotation`: For tracking a specific quantity or number (e.g., \"Cups of Coffee\").\n*   `BooleanAnnotation`: For tracking simple Yes/No or True/False states (e.g., \"Did I go to the gym?\").\n*   `ScaleAnnotation`: For 1-5 scales (e.g., mood, pain, intensity).\n\n### Creation Examples\n```bash\n# Create a simple moment annotation\nuv tool run fulcra-api data-type create MomentAnnotation \"Daily Walk\" --description \"Went for a walk today\"\n\n# Create a boolean annotation\nuv tool run fulcra-api data-type create BooleanAnnotation \"Ate Breakfast\" --description \"Did I eat breakfast?\"\n\n# Create a numeric annotation\nuv tool run fulcra-api data-type create NumericAnnotation \"Water Consumed\" --description \"Ounces of water drank\"\n\n# Create a scale annotation\nuv tool run fulcra-api data-type create ScaleAnnotation \"Daily Mood\" --description \"1-5 scale of mood\"\n```\n\nThe `create` command will output the JSON definition of the new data type. Make sure to capture the returned `\"id\"` value (e.g., `com.fulcradynamics.annotation.12345`), as you will need it to record data against this schema.\n\n## Fulcra File Store & Open Knowledge Format (OKF)\n\nThe Fulcra File Store is an environment-agnostic remote filesystem accessed via the `fulcra-api file` commands. When storing text and markdown data in the file store, agents should adhere to the **Open Knowledge Format (OKF)** standard (v0.1) when possible to ensure the file store remains understandable to users and other agents, and to provide auditability. You can read the full OKF specification here: [https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md](https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md).\n\n### File Uploads\n\nYou can manage versioned files using the `fulcra-api file` commands. This allows you to upload files directly into the Fulcra File Store, which will automatically track revisions and handle versioning.\n\n```bash\n# Upload a file to a specific remote path\nuv tool run fulcra-api file upload ./local-file.md /remote/path/file.md\n\n# List files in a remote directory\nuv tool run fulcra-api file list /remote/path/\n\n# Get information about a file, including previous versions\nuv tool run fulcra-api file stat /remote/path/file.md\n\n# Download a file from the remote path\nuv tool run fulcra-api file download /remote/path/file.md ./downloaded-file.md\n```\n\n### Core OKF Principles\n*   **Markdown + YAML Frontmatter:** All knowledge concepts should be written as `.md` files containing a YAML frontmatter block at the top, bordered by `---`. The frontmatter must contain at least a `type: <Type name>` field, and may optionally include `title:`, `description:`, `tags:`, etc.\n*   **`index.md` (Directory Listing):** Each directory should contain an `index.md` file (with no frontmatter). It provides progressive disclosure via grouped lists of links to the files within that directory (e.g., `* [Title](relative-url.md) - description`).\n*   **`log.md` (Update History):** Each directory should contain a `log.md` file to record a chronological history of changes. It contains date-grouped headings (e.g., `## YYYY-MM-DD`) with bulleted entries describing the updates (e.g., `* **Update**: Added new context file.`).\n\nWhile OKF compliance is important, it must not become cumbersome.\n- For directories that contain many small or transient items, simply list the directory itself in the `index.md` with a high-level description of its purpose.\n- Keep the `index.md` and `log.md` focused on top-level structure and significant milestones so they remain useful but lightweight.\n\n### Artifacts Directory\nTo maintain a clean OKF directory structure, any binary files, media, images, compiled code, or non-markdown files should be stored inside a dedicated `artifact/` subdirectory within the relevant namespace.\n\n## Further Reading & References\n\nAs an agent, you should rely on the `fulcra-api` CLI as the primary and most robust way to interact with Fulcra. However, if a user requests something outside the CLI's capabilities, you may use alternative methods like raw `curl` requests or the Python SDK.\n\nTo maintain your context as Fulcra evolves, or to assist users with deeper technical questions, you can consult the following external resources:\n- **Fulcra Website:** [https://www.fulcradynamics.com/](https://www.fulcradynamics.com/)\n- **REST API Documentation:** [https://fulcradynamics.github.io/developer-docs/api-reference/](https://fulcradynamics.github.io/developer-docs/api-reference/)\n- **Python SDK & CLI Source:** [https://github.com/fulcradynamics/fulcra-api-python/](https://github.com/fulcradynamics/fulcra-api-python/)\n- **Fulcra MCP:** Fulcra also has an MCP (Model Context Protocol) interface that you can learn more about at [https://fulcradynamics.github.io/developer-docs/mcp-server/](https://fulcradynamics.github.io/developer-docs/mcp-server/)\n- **Fulcra Agent Skills Repository:** [https://github.com/fulcradynamics/agent-skills](https://github.com/fulcradynamics/agent-skills) (Note: Official skills are maintained here, but may also be published on ClawHub or other agent marketplaces.)\n\nFile v0.1.6:references/fulcra-onboarding-auth.md\n\n---\nname: fulcra-onboarding-auth\ndescription: \"Handles initial authentication for the Fulcra CLI.\"\n---\n\n# Fulcra Onboarding: Authentication\n\nThis reference handles Step 2 of the onboarding process, securely establishing the user's connection to Fulcra.\n\n## Workflow\n\n1. **Authentication Check & Login (Requires Consent):**\n   - Briefly explain that you need to connect to their Fulcra account via the command line.\n   - **Ask for their explicit permission** to check their Fulcra authentication state and initiate a login flow.\n   - **How to verify:** After obtaining consent, run `uv tool run fulcra-api user-info`. If it returns valid JSON, the user is authenticated and you can proceed immediately to the next step.\n   - If not authenticated, explain that you will now generate a secure login link.\n   - Run `uv tool run fulcra-api auth login --get-auth-url` using the `exec` tool.\n   - **CRITICAL EXECUTION NOTE:** You must ALWAYS execute this command using the `--get-auth-url` flag so it does not hang and poll. The command will output a web auth URL, a web auth user code, and a device code.\n   - You **MUST** present the URL and the user code directly to the user in your chat message as a clickable markdown link where the URL itself is the text (e.g., `[https://...](https://...)`), tell them the user code, and tell them to complete the flow in their browser.\n   - **Important:** Keep the device code secret/safe; you will need it for the next step. Do *not* combine the authentication instructions with further brainstorming.\n   - Wait for the user to confirm they have completed the flow in their browser.\n   - Once they confirm, run `uv tool run fulcra-api auth login --device-code <DEVICE CODE> --poll-timeout=5` to complete the authentication process. The timeout ensures the command fails quickly if they haven't actually completed the flow.\n\n2. **Completion:**\n   - Once the device code login succeeds (or if they were already authenticated), declare the core onboarding complete!\n   - Hand control back to the main `fulcra-onboarding` flow to present the Next Steps menu.\n\nFile v0.1.6:references/fulcra-onboarding-prerequisites.md\n\n---\nname: fulcra-onboarding-prerequisites\ndescription: \"Verifies and sets up the required environment for Fulcra, including ensuring the 'uv' package manager is installed.\"\n---\n\n# Fulcra Prerequisites Check\n\nThis skill ensures the host environment is ready to interact with the Fulcra API.\n\n## Connection Options\n\nThere are two ways for agents to connect to Fulcra. You must determine the appropriate path before proceeding:\n\n1. **Option 1: Fulcra CLI (Preferred)**\n   The `fulcra-api` CLI is the primary interface and supports the widest range of Fulcra use cases. If you have full command-line access with outbound network connectivity, you should choose this option and proceed with the CLI workflow below.\n\n2. **Option 2: MCP Connector (Restricted Environments)**\n   Fulcra provides an MCP (Model Context Protocol) connector as an alternative option for restricted environments. To use MCP, fetch and read `https://fulcradynamics.github.io/developer-docs/mcp-server/` for setup instructions, and skip the CLI steps below.\n\n## Workflow\n\n1. **Verify `uv` Installation:**\n   - Run `uv --version` to check if Astral's `uv` tool is installed.\n   - It is required for all `fulcra-api` CLI interactions.\n2. **Install `uv` if Missing (Requires Explicit Consent):**\n   - If `uv` is not found, you **must explicitly ask the user for permission** to install it on their machine. Briefly explain that `uv` is a fast Python package manager needed to interact with the Fulcra API.\n   - **CRITICAL SECURITY NOTE:** Do not guess the installation commands. If the user agrees to install `uv`, use your web fetching capabilities to read the official installation instructions at `https://docs.astral.sh/uv/getting-started/installation/` and execute the appropriate installation method for their operating system.\n   - Ensure `uv` is available in the current shell environment (e.g., source the env file if instructed by the install script) before returning control.\n\n## Handoff\n\nOnce `uv` is confirmed to be installed and working, return control to the main `fulcra-onboarding` flow.\n\nFile v0.1.6:skill-card.md\n\n## Description: <br>\nGuides a new user or agent through the initial setup, configuration, and capabilities of the Fulcra environment. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[fulcra](https://clawhub.ai/user/fulcra) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nExternal users, developers, and agents use this skill to connect an agent to Fulcra, complete CLI prerequisites and authentication, and choose next steps for data ingestion, situational awareness, agent teams, memory, app access, or Context Web. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill connects agents to Fulcra, which may involve personal context, health, location, calendar-derived data, agent logs, and remote files. <br>\nMitigation: Use the skill only when the user wants that connection, and require explicit approval for authentication, installs, uploads, downloads, and data changes. <br>\nRisk: Remote file operations can upload, download, list, or inspect files in the Fulcra File Store. <br>\nMitigation: Confirm the specific local file, remote path, and data destination with the user before executing file store commands. <br>\nRisk: The setup flow may install or run command-line tooling on the user's machine. <br>\nMitigation: Check for existing tools first, ask for consent before installation, and use official installation documentation rather than guessed install commands. <br>\n\n\n## Reference(s): <br>\n- [Fulcra Onboarding skill source](SKILL.md) <br>\n- [Fulcra CLI reference](references/fulcra-cli.md) <br>\n- [Fulcra onboarding authentication reference](references/fulcra-onboarding-auth.md) <br>\n- [Fulcra onboarding prerequisites reference](references/fulcra-onboarding-prerequisites.md) <br>\n- [Fulcra skill page on ClawHub](https://clawhub.ai/fulcra/skills/fulcra-onboarding) <br>\n- [Fulcra website](https://www.fulcradynamics.com/) <br>\n- [Fulcra REST API documentation](https://fulcradynamics.github.io/developer-docs/api-reference/) <br>\n- [Fulcra MCP documentation](https://fulcradynamics.github.io/developer-docs/mcp-server/) <br>\n- [Context Web](https://context.fulcradynamics.com/) <br>\n- [Fulcra Context iOS app](https://apps.apple.com/app/id1633037434) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [guidance, markdown, shell commands, configuration] <br>\n**Output Format:** [Markdown guidance with inline shell commands, links, and setup steps] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Authentication, installation, uploads, downloads, and data changes require user consent before execution.] <br>\n\n## Skill Version(s): <br>\n0.1.6 (source: server release metadata) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v0.1.4: 6 files, 10286 bytes\n\nFiles: references/fulcra-cli.md (8407b), references/fulcra-onboarding-auth.md (1889b), references/fulcra-onboarding-prerequisites.md (2248b), skill-card.md (3060b), SKILL.md (4880b), _meta.json (136b)\n\nFile v0.1.4:SKILL.md\n\n---\nname: fulcra-onboarding\ndescription: \"Guides a new user or agent through the initial setup, configuration, and capabilities of the Fulcra environment.\"\nhomepage: \"https://github.com/fulcradynamics/agent-skills\"\nlicense: \"MIT\"\nuser-invocable: true\nmetadata: { \"openclaw\": { \"emoji\": \"🌱\" } }\n---\n\n# Fulcra Onboarding\n\nPrimary onboarding flow for new users connecting to the Fulcra environment. Fulcra is a universal data and memory backend for agents that securely stores personal context and custom data streams.\n\n## General Guidelines\n\n- **Tone & Vibe (The \"Wow\" Factor):** Fulcra unlocks massive potential because it acts as a universal memory and data backend for agents. Your tone should reflect this excitement and vast possibility. Be engaging, conversational, and fun.\n- **Use Emojis:** Liberally (but tastefully) use emojis throughout the onboarding process, especially when presenting lists, options, or celebrating a successful step. **However, always defer to the user's overarching formatting preferences or memory instructions. If a user explicitly asks for no emojis or a more professional tone, respect their constraints over this guideline.**\n- **Maintain Momentum:** Keep the user moving forward. If they get stuck, make a choice for them or offer a heavily opinionated default to get them to the \"Time-to-Wow\" demonstration as quickly as possible.\n\n## Workflow: Hub and Spoke Model\n\nThe onboarding process follows a strict two-phase \"Hub and Spoke\" model. First, you get the user connected. Then, you present a menu of options and let the user choose what to do next.\n\n### Phase 1: Core Setup (The Hub)\n\n1. **Introduction to Fulcra:**\n   - Read the `references/fulcra-cli.md` file to understand the `fulcra-api` CLI context and capabilities.\n   - Start the conversation by giving the user a brief, exciting overview of what Fulcra is (a universal data and memory platform that collects and records any data from any source).\n   - Tell the user that the first step is to get them connected to Fulcra by setting up the Fulcra CLI. **Do not execute any CLI setup or ask for installation permissions until you have introduced Fulcra.**\n\n2. **Pre-flight Check & Context:**\n   - Read and execute the instructions in `references/fulcra-onboarding-prerequisites.md` to verify and install `uv` if necessary, asking the user for confirmation before installation. This must pass before proceeding.\n\n3. **Authentication:**\n   - Read and execute the instructions in `references/fulcra-onboarding-auth.md`. This step securely authenticates the user via the Fulcra CLI. \n   - Once authenticated, declare that the core onboarding is complete! Celebrate this milestone.\n\n### Phase 2: Next Steps (The Spokes)\n\nImmediately after declaring the core onboarding complete, present the following menu of next steps to the user. Do not force them down any path automatically.\n\n**Present this exact scannable menu to the user:**\n\n1.  📊 **Agent Visibility & Custom Tracking:** Discover how to track custom data, agent visibility metrics, and visualize them using a custom dashboard.\n2.  🧠 **Agent Memory Backup:** Back up agent memory and high level context directly to your Fulcra datastore.\n3.  🤝 **Agent Coordination:** Set up shared team namespaces so your different agents can coordinate tasks.\n4.  📱 **Get the App:** Download the iOS app for on-the-go logging and background sync.\n5.  💻 **Context Web:** Explore your data on the desktop portal.\n\n**When the user makes a choice, follow the corresponding path below:**\n\n#### Path 1: Agent Visibility & Custom Tracking\n1. Explain that you can set up data schemas to track their custom data, as well as an \"Agent Visibility Package\" to record agent activities, and visualize it all on a custom HTML dashboard.\n2. If they consent and are interested, transition them to the `fulcra-tracking` skill.\n\n#### Path 2: Agent Memory Backup\n1. Explain that you can back up agent memory and high level context directly to their datastore. \n2. If they consent, transition them to the `fulcra-memory` skill to perform the backup.\n\n#### Path 3: Agent Coordination\n1. Explain that Fulcra isn't just for dashboards—it acts as a universal backend that allows multiple agents to coordinate their work using shared Team namespaces.\n2. If they consent and are interested, transition them to the `fulcra-agent-teams` skill so they can get set up.\n\n#### Path 4: Get the App\n1. Direct them to the [Fulcra Context iOS app](https://apps.apple.com/app/id1633037434).\n2. Mention it unlocks automatic background sync (Health, location, calendar). **PRIVACY WARNING:** Explicitly inform the user these are highly sensitive data types requiring explicit iOS permissions, and they have full control to decline.\n\n#### Path 5: Context Web\n1. Direct them to [Context Web](https://context.fulcradynamics.com/) to explore their datastore on desktop.\n\nFile v0.1.4:_meta.json\n\n{\n  \"ownerId\": \"kn72pt2cb5f9nskgc9k2ddecxs87547j\",\n  \"slug\": \"fulcra-onboarding\",\n  \"version\": \"0.1.4\",\n  \"publishedAt\": 1781819628572\n}\n\nFile v0.1.4:references/fulcra-cli.md\n\n# Fulcra CLI\n\nFulcra Context is a universal data and memory platform that collects and records any data a user wants to ingest from any source. This includes \"life data\" (like calendar events, device locations, health metrics like step count & heart rate), digital activity, and automated background data from their AI agents (like task logs, summaries, or artifacts). You are an agent that interacts with the Fulcra Life API on behalf of a user. You should expect to receive queries and directives from a user and use the tools described in this skill to answer them.\n\n## Installation\n\nThe `fulcra-api` CLI command is the easiest way to interact with the Life API and can be installed and run via `uv tool run`:\n\n```\nuv tool run fulcra-api\n```\n\n\n## Authentication\n\nUse the `auth login` subcommand to authenticate to Fulcra on behalf of a user.\n\n**CRITICAL WARNING FOR AGENTS:** The `fulcra-api auth login` command is a blocking command. It will poll for a valid token and will *not* complete until the user finishes the authorization flow in their browser (or until it hits a two-minute timeout). Because it blocks, **you must run it as a background process or allow it to yield, then read its active output stream to extract the authentication URL and code.** Do not wait for the command to finish before sending the URL to the user, or the authentication will time out and fail.\n\n```\nuv tool run fulcra-api auth login\n```\n\nThis will return a URL that you should direct the user to load in their browser, and a unique code that they should ensure matches the code displayed in their browser. **You must present the URL and code directly to the user; do not assume their browser will automatically open.**\n\n**Network Restrictions:** If this command immediately fails or prints a raw `<http.client.HTTPResponse object...>` error, your shell likely lacks outbound network access. Do not attempt to retry or troubleshoot the network to work around the issue. Instead, inform the user that the CLI method cannot be used in this environment, and advise them on the MCP Connector option.\n\nCredentials will be persisted on the filesystem to `~/.config/fulcra/credentials.json` and the tool will refresh access tokens as neccessary.\n\n\n## Usage\n\nRely on the `--help` flag for in depth documentation on the command and individual subcommands.\n\n```\nuv tool run fulcra-api --help\n```\n\nAll command output, except for `auth`, is in JSON format and can be piped into another tool like `jq` for parsing and filtering structured data.\n\nAll date/time fields are returned in ISO 8601 format, time zone aware, and in UTC. They should be converted to a user's local time zone. Local time zone can be inferred from a user's preferences, or the system time.\n\n\n## Examples\n\nAuthenticate to the API:\n```\nuv tool run fulcra-api auth login\n```\n\nGet list of Fulcra data type identifiers:\n```\nuv tool run fulcra-api catalog | jq -r '.id'\n```\n\nReturn last week of step count records:\n```\nuv tool run fulcra-api get-records StepCount \"1 week\"\n```\n\nReturn a calculated time series of heart rate data for the last week:\n```\nuv tool run fulcra-api metric-time-series HeartRate \"1 week\"\n```\n\nReturn a user's configured time zone from user preferences:\n```\nuv tool run fulcra-api user-info | jq -r '.preferences.timezone'\n```\n\n## Creating Custom Data Types (Annotations)\n\nFulcra supports creating custom schemas based on specific root \"base types.\" You can create new schemas easily via the CLI.\n\n```bash\nuv tool run fulcra-api data-type create <BASE_DATA_TYPE> \"<NAME>\" --description \"<DESCRIPTION>\"\n```\n\n### Base Data Types\nRun `uv tool run fulcra-api catalog --base-types-only` to see the exact IDs of the base types you can build upon.\nThe most common base types for custom tracking are:\n*   `MomentAnnotation`: For tracking occurrences of an event without a specific measurement (e.g., \"Took Medication\").\n*   `NumericAnnotation`: For tracking a specific quantity or number (e.g., \"Cups of Coffee\").\n*   `BooleanAnnotation`: For tracking simple Yes/No or True/False states (e.g., \"Did I go to the gym?\").\n*   `ScaleAnnotation`: For 1-5 scales (e.g., mood, pain, intensity).\n\n### Creation Examples\n```bash\n# Create a simple moment annotation\nuv tool run fulcra-api data-type create MomentAnnotation \"Daily Walk\" --description \"Went for a walk today\"\n\n# Create a boolean annotation\nuv tool run fulcra-api data-type create BooleanAnnotation \"Ate Breakfast\" --description \"Did I eat breakfast?\"\n\n# Create a numeric annotation\nuv tool run fulcra-api data-type create NumericAnnotation \"Water Consumed\" --description \"Ounces of water drank\"\n\n# Create a scale annotation\nuv tool run fulcra-api data-type create ScaleAnnotation \"Daily Mood\" --description \"1-5 scale of mood\"\n```\n\nThe `create` command will output the JSON definition of the new data type. Make sure to capture the returned `\"id\"` value (e.g., `com.fulcradynamics.annotation.12345`), as you will need it to record data against this schema.\n\n## Fulcra File Store & Open Knowledge Format (OKF)\n\nThe Fulcra File Store is an environment-agnostic remote filesystem accessed via the `fulcra-api file` commands. When storing text and markdown data in the file store (like memory or shared team files), agents must adhere to the **Open Knowledge Format (OKF)** standard (v0.1) to ensure the file store remains understandable to users and other agents, and to provide auditability. You can read the full OKF specification here: [https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md](https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md).\n\n### Core OKF Principles\n*   **Markdown + YAML Frontmatter:** All knowledge concepts should be written as `.md` files containing a YAML frontmatter block at the top, bordered by `---`. The frontmatter must contain at least a `type: <Type name>` field, and may optionally include `title:`, `description:`, `tags:`, etc.\n*   **`index.md` (Directory Listing):** Each directory should contain an `index.md` file (with no frontmatter). It provides progressive disclosure via grouped lists of links to the files within that directory (e.g., `* [Title](relative-url.md) - description`).\n*   **`log.md` (Update History):** Each directory should contain a `log.md` file to record a chronological history of changes. It contains date-grouped headings (e.g., `## YYYY-MM-DD`) with bulleted entries describing the updates (e.g., `* **Update**: Added new context file.`).\n\n**IMPORTANT OKF EFFICIENCY DIRECTIVE:** While OKF compliance is mandatory, it must not become cumbersome.\n- **DO NOT** attempt to index every individual file, especially not transient or highly repetitive files like individual messages inside an `inbox/` subdirectory. \n- For directories that contain many small or transient items, simply list the directory itself in the `index.md` with a high-level description of its purpose.\n- Keep the `index.md` and `log.md` focused on top-level structure and significant milestones so they remain useful but lightweight.\n\n### Artifacts Directory\nTo maintain a clean OKF directory structure, any binary files, media, images, compiled code, or non-markdown files must be stored inside a dedicated `artifact/` subdirectory within the relevant memory or team namespace.\n\n## Further Reading & References\n\nAs an agent, you should rely on the `fulcra-api` CLI as the primary and most robust way to interact with Fulcra. However, if the CLI cannot be installed/used in your environment, or if a user requests something outside the CLI's capabilities, you may use alternative methods like raw `curl` requests or the Python SDK.\n\nTo maintain your context as Fulcra evolves, or to assist users with deeper technical questions, you can consult the following external resources:\n- **Fulcra Website:** [https://www.fulcradynamics.com/](https://www.fulcradynamics.com/)\n- **REST API Documentation:** [https://fulcradynamics.github.io/developer-docs/api-reference/](https://fulcradynamics.github.io/developer-docs/api-reference/)\n- **Python SDK & CLI Source:** [https://github.com/fulcradynamics/fulcra-api-python/](https://github.com/fulcradynamics/fulcra-api-python/)\n- **Fulcra Agent Skills Repository:** [https://github.com/fulcradynamics/agent-skills](https://github.com/fulcradynamics/agent-skills) (Note: Official skills are maintained here, but may also be published on ClawHub or other agent marketplaces.)\n\nFile v0.1.4:references/fulcra-onboarding-auth.md\n\n---\nname: fulcra-onboarding-auth\ndescription: \"Handles initial authentication for the Fulcra CLI.\"\n---\n\n# Fulcra Onboarding: Authentication\n\nThis reference handles Step 2 of the onboarding process, securely establishing the user's connection to Fulcra.\n\n## Workflow\n\n1. **Authentication Check & Login (Requires Consent):**\n   - Briefly explain that you need to connect to their Fulcra account via the command line.\n   - **Ask for their explicit permission** to check their Fulcra authentication state and initiate a login flow.\n   - **How to verify:** After obtaining consent, run `uv tool run fulcra-api user-info`. If it returns valid JSON, the user is authenticated and you can proceed immediately to the next step.\n   - If not authenticated, explain that you will now generate a secure login link, and then run `uv tool run fulcra-api auth login` using the `exec` tool. \n   - **CRITICAL EXECUTION NOTE:** You must ALWAYS execute this command using a background process tool, as it will hang and poll for completion for up to two minutes. The command will output an authorization URL and a device code. You **MUST** extract the login URL and device code from the stdout, present them directly to the user in your chat message as a clickable markdown link where the URL itself is the text (e.g., `[https://...](https://...)`) along with the code, and tell them to complete the flow in their browser. Remind them not to share the link or code. Do *not* assume the browser will open automatically for them, and do *not* combine the authentication instructions with further brainstorming. Wait for them to confirm completion, or poll the process output.\n\n2. **Completion:**\n   - Once the user successfully authenticates (or if they were already authenticated), declare the core onboarding complete!\n   - Hand control back to the main `fulcra-onboarding` flow to present the Next Steps menu.\n\nFile v0.1.4:references/fulcra-onboarding-prerequisites.md\n\n---\nname: fulcra-onboarding-prerequisites\ndescription: \"Verifies and sets up the required environment for Fulcra, including ensuring the 'uv' package manager is installed.\"\n---\n\n# Fulcra Prerequisites Check\n\nThis skill ensures the host environment is ready to interact with the Fulcra API.\n\n## Connection Options\n\nThere are two ways for agents to connect to Fulcra. You must determine the appropriate path before proceeding:\n\n1. **Option 1: Fulcra CLI (Preferred)**\n   The `fulcra-api` CLI is the primary interface and supports the widest range of Fulcra use cases. If you have full command-line access with outbound network connectivity, you should choose this option and proceed with the CLI workflow below.\n\n2. **Option 2: MCP Connector (Restricted Environments)**\n   If you are in a restricted chat environment without command-line access, or if your shell lacks outbound network access to Fulcra's servers, the CLI will not work. In this case, advise the user that Fulcra provides an MCP (Model Context Protocol) connector as an alternative option for these environments. If they choose this option, fetch and read `https://fulcra.ai/AGENTS.md` for setup instructions, and skip the CLI steps below.\n\n## Workflow\n\n1. **Verify `uv` Installation:**\n   - Run `uv --version` to check if Astral's `uv` tool is installed.\n   - It is required for all `fulcra-api` CLI interactions.\n2. **Install `uv` if Missing (Requires Explicit Consent):**\n   - If `uv` is not found, you **must explicitly ask the user for permission** to install it on their machine. Briefly explain that `uv` is a fast Python package manager needed to interact with the Fulcra API.\n   - **CRITICAL SECURITY NOTE:** Do not guess the installation commands. If the user agrees to install `uv`, use your web fetching capabilities to read the official installation instructions at `https://docs.astral.sh/uv/getting-started/installation/` and execute the appropriate installation method for their operating system.\n   - Ensure `uv` is available in the current shell environment (e.g., source the env file if instructed by the install script) before returning control.\n\n## Handoff\n\nOnce `uv` is confirmed to be installed and working, return control to the main `fulcra-onboarding` flow.\n\nFile v0.1.4:skill-card.md\n\n## Description: <br>\nGuides a new user or agent through Fulcra setup, CLI authentication, and next-step options for using Fulcra as a data and memory platform. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[fulcra](https://clawhub.ai/user/fulcra) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nOnboard users to Fulcra by introducing the service, checking prerequisites with consent, guiding Fulcra CLI authentication, and offering follow-on paths for tracking, memory backup, agent coordination, the iOS app, and the web portal. <br>\n\n### Deployment Geography for Use: <br>\nGlobal, subject to the user's environment, network access, Fulcra service availability, and any local requirements for handling personal data. <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Fulcra accounts may contain sensitive personal data, including health, location, calendar, activity, memory, and agent log information. <br>\nMitigation: Use the skill only when intentionally connecting to Fulcra, review each optional data path before enabling it, and decline tracking, uploads, or follow-on skills that are not wanted. <br>\nRisk: Fulcra CLI login stores refreshable credentials on the local machine. <br>\nMitigation: Authenticate only on trusted devices and protect or remove local credentials when the environment is shared, temporary, or no longer trusted. <br>\nRisk: The onboarding flow can install or check required tooling and initiate authentication commands. <br>\nMitigation: Require explicit user consent before installation, prerequisite checks, or login, and show the user any authorization URL and device code directly. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/fulcra/fulcra-onboarding) <br>\n- [Publisher profile](https://clawhub.ai/user/fulcra) <br>\n- [Fulcra website](https://www.fulcradynamics.com/) <br>\n- [Fulcra REST API documentation](https://fulcradynamics.github.io/developer-docs/api-reference/) <br>\n- [Fulcra Python SDK and CLI source](https://github.com/fulcradynamics/fulcra-api-python/) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, shell commands, configuration, guidance] <br>\n**Output Format:** [Conversational onboarding instructions, consent-gated command guidance, authentication prompts, and a menu of follow-on setup paths.] <br>\n**Output Parameters:** [User consent for prerequisite checks and authentication, local uv and Fulcra CLI availability, Fulcra authentication state, and the user's selected next-step path.] <br>\n**Other Properties Related to Output:** [The skill may ask the agent to run local CLI checks, present a Fulcra login URL and code, and recommend related Fulcra skills or apps after core onboarding.] <br>\n\n## Skill Version(s): <br>\n0.1.4 <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v0.1.3: 6 files, 9456 bytes\n\nFiles: references/fulcra-cli.md (7701b), references/fulcra-onboarding-auth.md (1889b), references/fulcra-onboarding-prerequisites.md (1334b), skill-card.md (2757b), SKILL.md (4970b), _meta.json (136b)\n\nFile v0.1.3:SKILL.md\n\n---\nname: fulcra-onboarding\ndescription: \"Guides a new user or agent through the initial setup, configuration, and capabilities of the Fulcra environment.\"\nhomepage: \"https://github.com/fulcradynamics/agent-skills\"\nlicense: \"MIT\"\nuser-invocable: true\nmetadata: { \"openclaw\": { \"emoji\": \"🌱\" } }\n---\n\n# Fulcra Onboarding\n\nPrimary onboarding flow for new users connecting to the Fulcra environment. Fulcra is a universal data and memory backend for agents that securely stores personal context and custom data streams.\n\n## General Guidelines\n\n- **Tone & Vibe (The \"Wow\" Factor):** Fulcra unlocks massive potential because it acts as a universal memory and data backend for agents. Your tone should reflect this excitement and vast possibility. Be engaging, conversational, and fun.\n- **Use Emojis:** Liberally (but tastefully) use emojis throughout the onboarding process, especially when presenting lists, options, or celebrating a successful step.\n- **Maintain Momentum:** Keep the user moving forward. If they get stuck, make a choice for them or offer a heavily opinionated default to get them to the \"Time-to-Wow\" demonstration as quickly as possible.\n\n## Workflow: Hub and Spoke Model\n\nThe onboarding process follows a strict two-phase \"Hub and Spoke\" model. First, you get the user connected. Then, you present a menu of options and let the user choose what to do next.\n\n### Phase 1: Core Setup (The Hub)\n\n1. **Introduction to Fulcra:**\n   - Read the `references/fulcra-cli.md` file to understand the `fulcra-api` CLI context and capabilities.\n   - Start the conversation by giving the user a brief, exciting overview of what Fulcra is (a universal data and memory platform that collects and records any data from any source).\n   - Tell the user that the first step is to get them connected to Fulcra by setting up the Fulcra CLI. **Do not execute any CLI setup or ask for installation permissions until you have introduced Fulcra.**\n\n2. **Pre-flight Check & Context:**\n   - Read and execute the instructions in `references/fulcra-onboarding-prerequisites.md` to verify and install `uv` if necessary, asking the user for confirmation before installation. This must pass before proceeding.\n\n3. **Authentication:**\n   - Read and execute the instructions in `references/fulcra-onboarding-auth.md`. This step securely authenticates the user via the Fulcra CLI. \n   - Once authenticated, declare that the core onboarding is complete! Celebrate this milestone.\n\n### Phase 2: Next Steps (The Spokes)\n\nImmediately after declaring the core onboarding complete, present the following menu of next steps to the user. Do not force them down any path automatically.\n\n**Present this exact scannable menu to the user:**\n\n*   📊 **Agent Visibility & Custom Tracking:** Discover how to track custom data, agent visibility metrics, and visualize them using a custom dashboard.\n*   🧠 **Agent Memory Backup:** Snapshot my current memory and context directly to your Fulcra datastore.\n*   🤝 **Agent Coordination:** Set up shared team namespaces so your different agents can coordinate tasks.\n*   📱 **Get the App:** Download the iOS app for on-the-go logging and background sync.\n*   💻 **Context Web:** Explore your data on the desktop portal.\n*   ⚙️ **Cross-Platform Preferences:** Set up universal preferences across all your agents.\n\n**When the user makes a choice, follow the corresponding path below:**\n\n#### Path 1: Agent Visibility & Custom Tracking\n1. Explain that you can set up data schemas to track their custom data, as well as an \"Agent Visibility Package\" to record agent activities, and visualize it all on a custom HTML dashboard.\n2. If they consent and are interested, transition them to the `fulcra-tracking` skill.\n\n#### Path 2: Agent Memory Backup\n1. Explain that you can snapshot your current memory (which may include prior conversation context and preferences) directly to their datastore. \n2. If they consent, transition them to the `fulcra-memory` skill to perform the backup.\n\n#### Path 3: Agent Coordination\n1. Explain that Fulcra isn't just for dashboards—it acts as a universal backend that allows multiple agents to coordinate their work using shared Team namespaces.\n2. If they consent and are interested, transition them to the `fulcra-agent-teams` skill so they can get set up.\n\n#### Path 4: Get the App\n1. Direct them to the [Fulcra Context iOS app](https://apps.apple.com/app/id1633037434).\n2. Mention it unlocks automatic background sync (Health, location, calendar). **PRIVACY WARNING:** Explicitly inform the user these are highly sensitive data types requiring explicit iOS permissions, and they have full control to decline.\n\n#### Path 5: Context Web\n1. Direct them to [Context Web](https://context.fulcradynamics.com/) to explore their datastore on desktop.\n\n#### Path 6: Cross-Platform Preferences\n1. Transition them to the `fulcra-prefs` skill so they can load and capture preferences universally across all their agents.\n\nFile v0.1.3:_meta.json\n\n{\n  \"ownerId\": \"kn72pt2cb5f9nskgc9k2ddecxs87547j\",\n  \"slug\": \"fulcra-onboarding\",\n  \"version\": \"0.1.3\",\n  \"publishedAt\": 1781634192576\n}\n\nFile v0.1.3:references/fulcra-cli.md\n\n# Fulcra CLI\n\nFulcra Context is a universal data and memory platform that collects and records any data a user wants to ingest from any source. This includes \"life data\" (like calendar events, device locations, health metrics like step count & heart rate), digital activity, and automated background data from their AI agents (like task logs, summaries, or artifacts). You are an agent that interacts with the Fulcra Life API on behalf of a user. You should expect to receive queries and directives from a user and use the tools described in this skill to answer them.\n\n## Installation\n\nThe `fulcra-api` CLI command is the easiest way to interact with the Life API and can be installed and run via `uv tool run`:\n\n```\nuv tool run fulcra-api\n```\n\n\n## Authentication\n\nUse the `auth login` subcommand to authenticate to Fulcra on behalf of a user.\n\n```\nuv tool run fulcra-api auth login\n```\n\nThis will return a URL that you should direct the user to load in their browser, and a unique code that they should ensure matches the code displayed in their browser. **You must present the URL and code directly to the user; do not assume their browser will automatically open.**\n\nThe command will poll for a valid token and complete once the user finishes the authorization flow with a two minute timeout. Because it polls, you must run it as a background process or allow it to yield.\n\nCredentials will be persisted on the filesystem to `~/.config/fulcra/credentials.json` and the tool will refresh access tokens as neccessary.\n\n\n## Usage\n\nRely on the `--help` flag for in depth documentation on the command and individual subcommands.\n\n```\nuv tool run fulcra-api --help\n```\n\nAll command output, except for `auth`, is in JSON format and can be piped into another tool like `jq` for parsing and filtering structured data.\n\nAll date/time fields are returned in ISO 8601 format, time zone aware, and in UTC. They should be converted to a user's local time zone. Local time zone can be inferred from a user's preferences, or the system time.\n\n\n## Examples\n\nAuthenticate to the API:\n```\nuv tool run fulcra-api auth login\n```\n\nGet list of Fulcra data type identifiers:\n```\nuv tool run fulcra-api catalog | jq -r '.id'\n```\n\nReturn last week of step count records:\n```\nuv tool run fulcra-api get-records StepCount \"1 week\"\n```\n\nReturn a calculated time series of heart rate data for the last week:\n```\nuv tool run fulcra-api metric-time-series HeartRate \"1 week\"\n```\n\nReturn a user's configured time zone from user preferences:\n```\nuv tool run fulcra-api user-info | jq -r '.preferences.timezone'\n```\n\n## Creating Custom Data Types (Annotations)\n\nFulcra supports creating custom schemas based on specific root \"base types.\" You can create new schemas easily via the CLI.\n\n```bash\nuv tool run fulcra-api data-type create <BASE_DATA_TYPE> \"<NAME>\" --description \"<DESCRIPTION>\"\n```\n\n### Base Data Types\nRun `uv tool run fulcra-api catalog --base-types-only` to see the exact IDs of the base types you can build upon.\nThe most common base types for custom tracking are:\n*   `MomentAnnotation`: For tracking occurrences of an event without a specific measurement (e.g., \"Took Medication\").\n*   `NumericAnnotation`: For tracking a specific quantity or number (e.g., \"Cups of Coffee\").\n*   `BooleanAnnotation`: For tracking simple Yes/No or True/False states (e.g., \"Did I go to the gym?\").\n*   `ScaleAnnotation`: For 1-5 scales (e.g., mood, pain, intensity).\n\n### Creation Examples\n```bash\n# Create a simple moment annotation\nuv tool run fulcra-api data-type create MomentAnnotation \"Daily Walk\" --description \"Went for a walk today\"\n\n# Create a boolean annotation\nuv tool run fulcra-api data-type create BooleanAnnotation \"Ate Breakfast\" --description \"Did I eat breakfast?\"\n\n# Create a numeric annotation\nuv tool run fulcra-api data-type create NumericAnnotation \"Water Consumed\" --description \"Ounces of water drank\"\n\n# Create a scale annotation\nuv tool run fulcra-api data-type create ScaleAnnotation \"Daily Mood\" --description \"1-5 scale of mood\"\n```\n\nThe `create` command will output the JSON definition of the new data type. Make sure to capture the returned `\"id\"` value (e.g., `com.fulcradynamics.annotation.12345`), as you will need it to record data against this schema.\n\n## Fulcra File Store & Open Knowledge Format (OKF)\n\nThe Fulcra File Store is an environment-agnostic remote filesystem accessed via the `fulcra-api file` commands. When storing text and markdown data in the file store (like memory or shared team files), agents must adhere to the **Open Knowledge Format (OKF)** standard (v0.1) to ensure the file store remains understandable to users and other agents, and to provide auditability. You can read the full OKF specification here: [https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md](https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md).\n\n### Core OKF Principles\n*   **Markdown + YAML Frontmatter:** All knowledge concepts should be written as `.md` files containing a YAML frontmatter block at the top, bordered by `---`. The frontmatter must contain at least a `type: <Type name>` field, and may optionally include `title:`, `description:`, `tags:`, etc.\n*   **`index.md` (Directory Listing):** Each directory should contain an `index.md` file (with no frontmatter). It provides progressive disclosure via grouped lists of links to the files within that directory (e.g., `* [Title](relative-url.md) - description`).\n*   **`log.md` (Update History):** Each directory should contain a `log.md` file to record a chronological history of changes. It contains date-grouped headings (e.g., `## YYYY-MM-DD`) with bulleted entries describing the updates (e.g., `* **Update**: Added new context file.`).\n\n**IMPORTANT OKF EFFICIENCY DIRECTIVE:** While OKF compliance is mandatory, it must not become cumbersome.\n- **DO NOT** attempt to index every individual file, especially not transient or highly repetitive files like individual messages inside an `inbox/` subdirectory. \n- For directories that contain many small or transient items, simply list the directory itself in the `index.md` with a high-level description of its purpose.\n- Keep the `index.md` and `log.md` focused on top-level structure and significant milestones so they remain useful but lightweight.\n\n### Artifacts Directory\nTo maintain a clean OKF directory structure, any binary files, media, images, compiled code, or non-markdown files must be stored inside a dedicated `artifact/` subdirectory within the relevant memory or team namespace.\n\n## Further Reading & References\n\nAs an agent, you should rely on the `fulcra-api` CLI as the primary and most robust way to interact with Fulcra. However, if the CLI cannot be installed/used in your environment, or if a user requests something outside the CLI's capabilities, you may use alternative methods like raw `curl` requests or the Python SDK.\n\nTo maintain your context as Fulcra evolves, or to assist users with deeper technical questions, you can consult the following external resources:\n- **Fulcra Website:** [https://www.fulcradynamics.com/](https://www.fulcradynamics.com/)\n- **REST API Documentation:** [https://fulcradynamics.github.io/developer-docs/api-reference/](https://fulcradynamics.github.io/developer-docs/api-reference/)\n- **Python SDK & CLI Source:** [https://github.com/fulcradynamics/fulcra-api-python/](https://github.com/fulcradynamics/fulcra-api-python/)\n- **Fulcra Agent Skills Repository:** [https://github.com/fulcradynamics/agent-skills](https://github.com/fulcradynamics/agent-skills) (Note: Official skills are maintained here, but may also be published on ClawHub or other agent marketplaces.)\n\nFile v0.1.3:references/fulcra-onboarding-auth.md\n\n---\nname: fulcra-onboarding-auth\ndescription: \"Handles initial authentication for the Fulcra CLI.\"\n---\n\n# Fulcra Onboarding: Authentication\n\nThis reference handles Step 2 of the onboarding process, securely establishing the user's connection to Fulcra.\n\n## Workflow\n\n1. **Authentication Check & Login (Requires Consent):**\n   - Briefly explain that you need to connect to their Fulcra account via the command line.\n   - **Ask for their explicit permission** to check their Fulcra authentication state and initiate a login flow.\n   - **How to verify:** After obtaining consent, run `uv tool run fulcra-api user-info`. If it returns valid JSON, the user is authenticated and you can proceed immediately to the next step.\n   - If not authenticated, explain that you will now generate a secure login link, and then run `uv tool run fulcra-api auth login` using the `exec` tool. \n   - **CRITICAL EXECUTION NOTE:** You must ALWAYS execute this command using a background process tool, as it will hang and poll for completion for up to two minutes. The command will output an authorization URL and a device code. You **MUST** extract the login URL and device code from the stdout, present them directly to the user in your chat message as a clickable markdown link where the URL itself is the text (e.g., `[https://...](https://...)`) along with the code, and tell them to complete the flow in their browser. Remind them not to share the link or code. Do *not* assume the browser will open automatically for them, and do *not* combine the authentication instructions with further brainstorming. Wait for them to confirm completion, or poll the process output.\n\n2. **Completion:**\n   - Once the user successfully authenticates (or if they were already authenticated), declare the core onboarding complete!\n   - Hand control back to the main `fulcra-onboarding` flow to present the Next Steps menu.\n\nFile v0.1.3:references/fulcra-onboarding-prerequisites.md\n\n---\nname: fulcra-onboarding-prerequisites\ndescription: \"Verifies and sets up the required environment for Fulcra, including ensuring the 'uv' package manager is installed.\"\n---\n\n# Fulcra Prerequisites Check\n\nThis skill ensures the host environment is ready to interact with the Fulcra API.\n\n## Workflow\n\n1. **Verify `uv` Installation:**\n   - Run `uv --version` to check if Astral's `uv` tool is installed.\n   - It is required for all `fulcra-api` CLI interactions.\n2. **Install `uv` if Missing (Requires Explicit Consent):**\n   - If `uv` is not found, you **must explicitly ask the user for permission** to install it on their machine. Briefly explain that `uv` is a fast Python package manager needed to interact with the Fulcra API.\n   - **CRITICAL SECURITY NOTE:** Do not guess the installation commands. If the user agrees to install `uv`, use your web fetching capabilities to read the official installation instructions at `https://docs.astral.sh/uv/getting-started/installation/` and execute the appropriate installation method for their operating system.\n   - Ensure `uv` is available in the current shell environment (e.g., source the env file if instructed by the install script) before returning control.\n\n## Handoff\n\nOnce `uv` is confirmed to be installed and working, return control to the main `fulcra-onboarding` flow.\n\nFile v0.1.3:skill-card.md\n\n## Description: <br>\nGuides a new user or agent through the initial setup, configuration, and capabilities of the Fulcra environment. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[fulcra](https://clawhub.ai/user/fulcra) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nAgents and users use this skill to connect a local agent environment to Fulcra, verify required CLI tooling, complete account authentication, and choose follow-up workflows such as tracking, memory backup, team coordination, mobile sync, desktop exploration, or preferences. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill can authenticate a local CLI to Fulcra and store credentials locally. <br>\nMitigation: Review and approve Fulcra login commands before execution, protect local credentials, and remove or revoke credentials when they are no longer needed. <br>\nRisk: The skill can enable account changes or access to sensitive personal context such as health, location, calendar, memory, or preference data. <br>\nMitigation: Require explicit confirmation before creating schemas, writing remote files, backing up memory, or reading sensitive data, and limit each operation to the user's stated request. <br>\nRisk: The onboarding flow may install or run local tooling such as uv and the fulcra-api CLI. <br>\nMitigation: Review installation instructions and command lines before execution, and use official installation sources for required tooling. <br>\n\n\n## Reference(s): <br>\n- [Fulcra Onboarding on ClawHub](https://clawhub.ai/fulcra/fulcra-onboarding) <br>\n- [Fulcra CLI](references/fulcra-cli.md) <br>\n- [Fulcra Onboarding Prerequisites](references/fulcra-onboarding-prerequisites.md) <br>\n- [Fulcra Onboarding Authentication](references/fulcra-onboarding-auth.md) <br>\n- [Fulcra Website](https://www.fulcradynamics.com/) <br>\n- [Fulcra REST API Documentation](https://fulcradynamics.github.io/developer-docs/api-reference/) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, Markdown, Shell commands, Configuration instructions, Guidance] <br>\n**Output Format:** [Markdown with inline shell commands and links] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Requires explicit user consent before installing uv, checking authentication, or initiating Fulcra login.] <br>\n\n## Skill Version(s): <br>\n0.1.3 (source: server release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v0.1.2: 6 files, 9188 bytes\n\nFiles: references/fulcra-cli.md (7139b), references/fulcra-onboarding-auth.md (1889b), references/fulcra-onboarding-prerequisites.md (1334b), skill-card.md (2769b), SKILL.md (4970b), _meta.json (136b)\n\nFile v0.1.2:SKILL.md\n\n---\nname: fulcra-onboarding\ndescription: \"Guides a new user or agent through the initial setup, configuration, and capabilities of the Fulcra environment.\"\nhomepage: \"https://github.com/fulcradynamics/agent-skills\"\nlicense: \"MIT\"\nuser-invocable: true\nmetadata: { \"openclaw\": { \"emoji\": \"🌱\" } }\n---\n\n# Fulcra Onboarding\n\nPrimary onboarding flow for new users connecting to the Fulcra environment. Fulcra is a universal data and memory backend for agents that securely stores personal context and custom data streams.\n\n## General Guidelines\n\n- **Tone & Vibe (The \"Wow\" Factor):** Fulcra unlocks massive potential because it acts as a universal memory and data backend for agents. Your tone should reflect this excitement and vast possibility. Be engaging, conversational, and fun.\n- **Use Emojis:** Liberally (but tastefully) use emojis throughout the onboarding process, especially when presenting lists, options, or celebrating a successful step.\n- **Maintain Momentum:** Keep the user moving forward. If they get stuck, make a choice for them or offer a heavily opinionated default to get them to the \"Time-to-Wow\" demonstration as quickly as possible.\n\n## Workflow: Hub and Spoke Model\n\nThe onboarding process follows a strict two-phase \"Hub and Spoke\" model. First, you get the user connected. Then, you present a menu of options and let the user choose what to do next.\n\n### Phase 1: Core Setup (The Hub)\n\n1. **Introduction to Fulcra:**\n   - Read the `references/fulcra-cli.md` file to understand the `fulcra-api` CLI context and capabilities.\n   - Start the conversation by giving the user a brief, exciting overview of what Fulcra is (a universal data and memory platform that collects and records any data from any source).\n   - Tell the user that the first step is to get them connected to Fulcra by setting up the Fulcra CLI. **Do not execute any CLI setup or ask for installation permissions until you have introduced Fulcra.**\n\n2. **Pre-flight Check & Context:**\n   - Read and execute the instructions in `references/fulcra-onboarding-prerequisites.md` to verify and install `uv` if necessary, asking the user for confirmation before installation. This must pass before proceeding.\n\n3. **Authentication:**\n   - Read and execute the instructions in `references/fulcra-onboarding-auth.md`. This step securely authenticates the user via the Fulcra CLI. \n   - Once authenticated, declare that the core onboarding is complete! Celebrate this milestone.\n\n### Phase 2: Next Steps (The Spokes)\n\nImmediately after declaring the core onboarding complete, present the following menu of next steps to the user. Do not force them down any path automatically.\n\n**Present this exact scannable menu to the user:**\n\n*   📊 **Agent Visibility & Custom Tracking:** Discover how to track custom data, agent visibility metrics, and visualize them using a custom dashboard.\n*   🧠 **Agent Memory Backup:** Snapshot my current memory and context directly to your Fulcra datastore.\n*   🤝 **Agent Coordination:** Set up shared team namespaces so your different agents can coordinate tasks.\n*   📱 **Get the App:** Download the iOS app for on-the-go logging and background sync.\n*   💻 **Context Web:** Explore your data on the desktop portal.\n*   ⚙️ **Cross-Platform Preferences:** Set up universal preferences across all your agents.\n\n**When the user makes a choice, follow the corresponding path below:**\n\n#### Path 1: Agent Visibility & Custom Tracking\n1. Explain that you can set up data schemas to track their custom data, as well as an \"Agent Visibility Package\" to record agent activities, and visualize it all on a custom HTML dashboard.\n2. If they consent and are interested, transition them to the `fulcra-tracking` skill.\n\n#### Path 2: Agent Memory Backup\n1. Explain that you can snapshot your current memory (which may include prior conversation context and preferences) directly to their datastore. \n2. If they consent, transition them to the `fulcra-memory` skill to perform the backup.\n\n#### Path 3: Agent Coordination\n1. Explain that Fulcra isn't just for dashboards—it acts as a universal backend that allows multiple agents to coordinate their work using shared Team namespaces.\n2. If they consent and are interested, transition them to the `fulcra-agent-teams` skill so they can get set up.\n\n#### Path 4: Get the App\n1. Direct them to the [Fulcra Context iOS app](https://apps.apple.com/app/id1633037434).\n2. Mention it unlocks automatic background sync (Health, location, calendar). **PRIVACY WARNING:** Explicitly inform the user these are highly sensitive data types requiring explicit iOS permissions, and they have full control to decline.\n\n#### Path 5: Context Web\n1. Direct them to [Context Web](https://context.fulcradynamics.com/) to explore their datastore on desktop.\n\n#### Path 6: Cross-Platform Preferences\n1. Transition them to the `fulcra-prefs` skill so they can load and capture preferences universally across all their agents.\n\nFile v0.1.2:_meta.json\n\n{\n  \"ownerId\": \"kn72pt2cb5f9nskgc9k2ddecxs87547j\",\n  \"slug\": \"fulcra-onboarding\",\n  \"version\": \"0.1.2\",\n  \"publishedAt\": 1781566826238\n}\n\nFile v0.1.2:references/fulcra-cli.md\n\n# Fulcra CLI\n\nFulcra Context is a universal data and memory platform that collects and records any data a user wants to ingest from any source. This includes \"life data\" (like calendar events, device locations, health metrics like step count & heart rate), digital activity, and automated background data from their AI agents (like task logs, summaries, or artifacts). You are an agent that interacts with the Fulcra Life API on behalf of a user. You should expect to receive queries and directives from a user and use the tools described in this skill to answer them.\n\n## Installation\n\nThe `fulcra-api` CLI command is the easiest way to interact with the Life API and can be installed and run via `uv tool run`:\n\n```\nuv tool run fulcra-api\n```\n\n\n## Authentication\n\nUse the `auth login` subcommand to authenticate to Fulcra on behalf of a user.\n\n```\nuv tool run fulcra-api auth login\n```\n\nThis will return a URL that you should direct the user to load in their browser, and a unique code that they should ensure matches the code displayed in their browser. **You must present the URL and code directly to the user; do not assume their browser will automatically open.**\n\nThe command will poll for a valid token and complete once the user finishes the authorization flow with a two minute timeout. Because it polls, you must run it as a background process or allow it to yield.\n\nCredentials will be persisted on the filesystem to `~/.config/fulcra/credentials.json` and the tool will refresh access tokens as neccessary.\n\n\n## Usage\n\nRely on the `--help` flag for in depth documentation on the command and individual subcommands.\n\n```\nuv tool run fulcra-api --help\n```\n\nAll command output, except for `auth`, is in JSON format and can be piped into another tool like `jq` for parsing and filtering structured data.\n\nAll date/time fields are returned in ISO 8601 format, time zone aware, and in UTC. They should be converted to a user's local time zone. Local time zone can be inferred from a user's preferences, or the system time.\n\n\n## Examples\n\nAuthenticate to the API:\n```\nuv tool run fulcra-api auth login\n```\n\nGet list of Fulcra data type identifiers:\n```\nuv tool run fulcra-api catalog | jq -r '.id'\n```\n\nReturn last week of step count records:\n```\nuv tool run fulcra-api get-records StepCount \"1 week\"\n```\n\nReturn a calculated time series of heart rate data for the last week:\n```\nuv tool run fulcra-api metric-time-series HeartRate \"1 week\"\n```\n\nReturn a user's configured time zone from user preferences:\n```\nuv tool run fulcra-api user-info | jq -r '.preferences.timezone'\n```\n\n## Creating Custom Data Types (Annotations)\n\nFulcra supports creating custom schemas based on specific root \"base types.\" You can create new schemas easily via the CLI.\n\n```bash\nuv tool run fulcra-api data-type create <BASE_DATA_TYPE> \"<NAME>\" --description \"<DESCRIPTION>\"\n```\n\n### Base Data Types\nRun `uv tool run fulcra-api catalog --base-types-only` to see the exact IDs of the base types you can build upon.\nThe most common base types for custom tracking are:\n*   `MomentAnnotation`: For tracking occurrences of an event without a specific measurement (e.g., \"Took Medication\").\n*   `NumericAnnotation`: For tracking a specific quantity or number (e.g., \"Cups of Coffee\").\n*   `BooleanAnnotation`: For tracking simple Yes/No or True/False states (e.g., \"Did I go to the gym?\").\n*   `ScaleAnnotation`: For 1-5 scales (e.g., mood, pain, intensity).\n\n### Creation Examples\n```bash\n# Create a simple moment annotation\nuv tool run fulcra-api data-type create MomentAnnotation \"Daily Walk\" --description \"Went for a walk today\"\n\n# Create a boolean annotation\nuv tool run fulcra-api data-type create BooleanAnnotation \"Ate Breakfast\" --description \"Did I eat breakfast?\"\n\n# Create a numeric annotation\nuv tool run fulcra-api data-type create NumericAnnotation \"Water Consumed\" --description \"Ounces of water drank\"\n\n# Create a scale annotation\nuv tool run fulcra-api data-type create ScaleAnnotation \"Daily Mood\" --description \"1-5 scale of mood\"\n```\n\nThe `create` command will output the JSON definition of the new data type. Make sure to capture the returned `\"id\"` value (e.g., `com.fulcradynamics.annotation.12345`), as you will need it to record data against this schema.\n\n## Fulcra File Store & Open Knowledge Format (OKF)\n\nThe Fulcra File Store is an environment-agnostic remote filesystem accessed via the `fulcra-api file` commands. When storing text and markdown data in the file store (like memory or shared team files), agents must adhere to the **Open Knowledge Format (OKF)** standard (v0.1) to ensure the file store remains understandable to users and other agents, and to provide auditability. You can read the full OKF specification here: [https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md](https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md).\n\n### Core OKF Principles\n*   **Markdown + YAML Frontmatter:** All knowledge concepts should be written as `.md` files containing a YAML frontmatter block at the top, bordered by `---`. The frontmatter must contain at least a `type: <Type name>` field, and may optionally include `title:`, `description:`, `tags:`, etc.\n*   **`index.md` (Directory Listing):** Each directory should contain an `index.md` file (with no frontmatter). It provides progressive disclosure via grouped lists of links to the files within that directory (e.g., `* [Title](relative-url.md) - description`).\n*   **`log.md` (Update History):** Each directory should contain a `log.md` file to record a chronological history of changes. It contains date-grouped headings (e.g., `## YYYY-MM-DD`) with bulleted entries describing the updates (e.g., `* **Update**: Added new context file.`).\n\n### Artifacts Directory\nTo maintain a clean OKF directory structure, any binary files, media, images, compiled code, or non-markdown files must be stored inside a dedicated `artifact/` subdirectory within the relevant memory or team namespace.\n\n## Further Reading & References\n\nAs an agent, you should rely on the `fulcra-api` CLI as the primary and most robust way to interact with Fulcra. However, if the CLI cannot be installed/used in your environment, or if a user requests something outside the CLI's capabilities, you may use alternative methods like raw `curl` requests or the Python SDK.\n\nTo maintain your context as Fulcra evolves, or to assist users with deeper technical questions, you can consult the following external resources:\n- **Fulcra Website:** [https://www.fulcradynamics.com/](https://www.fulcradynamics.com/)\n- **REST API Documentation:** [https://fulcradynamics.github.io/developer-docs/api-reference/](https://fulcradynamics.github.io/developer-docs/api-reference/)\n- **Python SDK & CLI Source:** [https://github.com/fulcradynamics/fulcra-api-python/](https://github.com/fulcradynamics/fulcra-api-python/)\n- **Fulcra Agent Skills Repository:** [https://github.com/fulcradynamics/agent-skills](https://github.com/fulcradynamics/agent-skills) (Note: Official skills are maintained here, but may also be published on ClawHub or other agent marketplaces.)\n\nFile v0.1.2:references/fulcra-onboarding-auth.md\n\n---\nname: fulcra-onboarding-auth\ndescription: \"Handles initial authentication for the Fulcra CLI.\"\n---\n\n# Fulcra Onboarding: Authentication\n\nThis reference handles Step 2 of the onboarding process, securely establishing the user's connection to Fulcra.\n\n## Workflow\n\n1. **Authentication Check & Login (Requires Consent):**\n   - Briefly explain that you need to connect to their Fulcra account via the command line.\n   - **Ask for their explicit permission** to check their Fulcra authentication state and initiate a login flow.\n   - **How to verify:** After obtaining consent, run `uv tool run fulcra-api user-info`. If it returns valid JSON, the user is authenticated and you can proceed immediately to the next step.\n   - If not authenticated, explain that you will now generate a secure login link, and then run `uv tool run fulcra-api auth login` using the `exec` tool. \n   - **CRITICAL EXECUTION NOTE:** You must ALWAYS execute this command using a background process tool, as it will hang and poll for completion for up to two minutes. The command will output an authorization URL and a device code. You **MUST** extract the login URL and device code from the stdout, present them directly to the user in your chat message as a clickable markdown link where the URL itself is the text (e.g., `[https://...](https://...)`) along with the code, and tell them to complete the flow in their browser. Remind them not to share the link or code. Do *not* assume the browser will open automatically for them, and do *not* combine the authentication instructions with further brainstorming. Wait for them to confirm completion, or poll the process output.\n\n2. **Completion:**\n   - Once the user successfully authenticates (or if they were already authenticated), declare the core onboarding complete!\n   - Hand control back to the main `fulcra-onboarding` flow to present the Next Steps menu.\n\nFile v0.1.2:references/fulcra-onboarding-prerequisites.md\n\n---\nname: fulcra-onboarding-prerequisites\ndescription: \"Verifies and sets up the required environment for Fulcra, including ensuring the 'uv' package manager is installed.\"\n---\n\n# Fulcra Prerequisites Check\n\nThis skill ensures the host environment is ready to interact with the Fulcra API.\n\n## Workflow\n\n1. **Verify `uv` Installation:**\n   - Run `uv --version` to check if Astral's `uv` tool is installed.\n   - It is required for all `fulcra-api` CLI interactions.\n2. **Install `uv` if Missing (Requires Explicit Consent):**\n   - If `uv` is not found, you **must explicitly ask the user for permission** to install it on their machine. Briefly explain that `uv` is a fast Python package manager needed to interact with the Fulcra API.\n   - **CRITICAL SECURITY NOTE:** Do not guess the installation commands. If the user agrees to install `uv`, use your web fetching capabilities to read the official installation instructions at `https://docs.astral.sh/uv/getting-started/installation/` and execute the appropriate installation method for their operating system.\n   - Ensure `uv` is available in the current shell environment (e.g., source the env file if instructed by the install script) before returning control.\n\n## Handoff\n\nOnce `uv` is confirmed to be installed and working, return control to the main `fulcra-onboarding` flow.\n\nFile v0.1.2:skill-card.md\n\n## Description: <br>\nGuides a new user or agent through the initial setup, configuration, and capabilities of the Fulcra environment. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[fulcra](https://clawhub.ai/user/fulcra) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nExternal users and agents use this skill to connect an agent environment to Fulcra, verify prerequisites, authenticate through the Fulcra CLI, and choose follow-on setup paths for tracking, memory, coordination, mobile sync, desktop access, or preferences. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill connects the agent environment to Fulcra, a service that may handle sensitive personal context and custom data streams. <br>\nMitigation: Install and authenticate only when the user intends to connect Fulcra, and approve memory backup, health, location, calendar, schema, or file-store actions only for data the user wants sent to Fulcra. <br>\nRisk: Fulcra authentication stores local credentials for CLI access. <br>\nMitigation: Authenticate only on trusted machines and remind the user not to share authorization links, device codes, or credential files. <br>\nRisk: Prerequisite setup may install or run command-line tools before Fulcra access is available. <br>\nMitigation: Ask for explicit consent before installation, review any uv installation prompt, and use official installation instructions when uv is missing. <br>\n\n\n## Reference(s): <br>\n- [Fulcra CLI](references/fulcra-cli.md) <br>\n- [Fulcra Onboarding: Authentication](references/fulcra-onboarding-auth.md) <br>\n- [Fulcra Prerequisites Check](references/fulcra-onboarding-prerequisites.md) <br>\n- [Fulcra Website](https://www.fulcradynamics.com/) <br>\n- [REST API Documentation](https://fulcradynamics.github.io/developer-docs/api-reference/) <br>\n- [Fulcra Context iOS App](https://apps.apple.com/app/id1633037434) <br>\n- [Context Web](https://context.fulcradynamics.com/) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [guidance, shell commands, configuration] <br>\n**Output Format:** [Markdown with inline shell commands] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May direct the agent to request user consent before installation, authentication, data sync, memory backup, schema creation, or file-store actions.] <br>\n\n## Skill Version(s): <br>\n0.1.2 (source: server release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v0.1.1: 6 files, 8310 bytes\n\nFiles: references/fulcra-cli.md (5394b), references/fulcra-onboarding-auth.md (1889b), references/fulcra-onboarding-prerequisites.md (1334b), skill-card.md (2431b), SKILL.md (4970b), _meta.json (136b)\n\nFile v0.1.1:SKILL.md\n\n---\nname: fulcra-onboarding\ndescription: \"Guides a new user or agent through the initial setup, configuration, and capabilities of the Fulcra environment.\"\nhomepage: \"https://github.com/fulcradynamics/agent-skills\"\nlicense: \"MIT\"\nuser-invocable: true\nmetadata: { \"openclaw\": { \"emoji\": \"🌱\" } }\n---\n\n# Fulcra Onboarding\n\nPrimary onboarding flow for new users connecting to the Fulcra environment. Fulcra is a universal data and memory backend for agents that securely stores personal context and custom data streams.\n\n## General Guidelines\n\n- **Tone & Vibe (The \"Wow\" Factor):** Fulcra unlocks massive potential because it acts as a universal memory and data backend for agents. Your tone should reflect this excitement and vast possibility. Be engaging, conversational, and fun.\n- **Use Emojis:** Liberally (but tastefully) use emojis throughout the onboarding process, especially when presenting lists, options, or celebrating a successful step.\n- **Maintain Momentum:** Keep the user moving forward. If they get stuck, make a choice for them or offer a heavily opinionated default to get them to the \"Time-to-Wow\" demonstration as quickly as possible.\n\n## Workflow: Hub and Spoke Model\n\nThe onboarding process follows a strict two-phase \"Hub and Spoke\" model. First, you get the user connected. Then, you present a menu of options and let the user choose what to do next.\n\n### Phase 1: Core Setup (The Hub)\n\n1. **Introduction to Fulcra:**\n   - Read the `references/fulcra-cli.md` file to understand the `fulcra-api` CLI context and capabilities.\n   - Start the conversation by giving the user a brief, exciting overview of what Fulcra is (a universal data and memory platform that collects and records any data from any source).\n   - Tell the user that the first step is to get them connected to Fulcra by setting up the Fulcra CLI. **Do not execute any CLI setup or ask for installation permissions until you have introduced Fulcra.**\n\n2. **Pre-flight Check & Context:**\n   - Read and execute the instructions in `references/fulcra-onboarding-prerequisites.md` to verify and install `uv` if necessary, asking the user for confirmation before installation. This must pass before proceeding.\n\n3. **Authentication:**\n   - Read and execute the instructions in `references/fulcra-onboarding-auth.md`. This step securely authenticates the user via the Fulcra CLI. \n   - Once authenticated, declare that the core onboarding is complete! Celebrate this milestone.\n\n### Phase 2: Next Steps (The Spokes)\n\nImmediately after declaring the core onboarding complete, present the following menu of next steps to the user. Do not force them down any path automatically.\n\n**Present this exact scannable menu to the user:**\n\n*   📊 **Agent Visibility & Custom Tracking:** Discover how to track custom data, agent visibility metrics, and visualize them using a custom dashboard.\n*   🧠 **Agent Memory Backup:** Snapshot my current memory and context directly to your Fulcra datastore.\n*   🤝 **Agent Coordination:** Set up shared team namespaces so your different agents can coordinate tasks.\n*   📱 **Get the App:** Download the iOS app for on-the-go logging and background sync.\n*   💻 **Context Web:** Explore your data on the desktop portal.\n*   ⚙️ **Cross-Platform Preferences:** Set up universal preferences across all your agents.\n\n**When the user makes a choice, follow the corresponding path below:**\n\n#### Path 1: Agent Visibility & Custom Tracking\n1. Explain that you can set up data schemas to track their custom data, as well as an \"Agent Visibility Package\" to record agent activities, and visualize it all on a custom HTML dashboard.\n2. If they consent and are interested, transition them to the `fulcra-tracking` skill.\n\n#### Path 2: Agent Memory Backup\n1. Explain that you can snapshot your current memory (which may include prior conversation context and preferences) directly to their datastore. \n2. If they consent, transition them to the `fulcra-memory` skill to perform the backup.\n\n#### Path 3: Agent Coordination\n1. Explain that Fulcra isn't just for dashboards—it acts as a universal backend that allows multiple agents to coordinate their work using shared Team namespaces.\n2. If they consent and are interested, transition them to the `fulcra-agent-teams` skill so they can get set up.\n\n#### Path 4: Get the App\n1. Direct them to the [Fulcra Context iOS app](https://apps.apple.com/app/id1633037434).\n2. Mention it unlocks automatic background sync (Health, location, calendar). **PRIVACY WARNING:** Explicitly inform the user these are highly sensitive data types requiring explicit iOS permissions, and they have full control to decline.\n\n#### Path 5: Context Web\n1. Direct them to [Context Web](https://context.fulcradynamics.com/) to explore their datastore on desktop.\n\n#### Path 6: Cross-Platform Preferences\n1. Transition them to the `fulcra-prefs` skill so they can load and capture preferences universally across all their agents.\n\nFile v0.1.1:_meta.json\n\n{\n  \"ownerId\": \"kn72pt2cb5f9nskgc9k2ddecxs87547j\",\n  \"slug\": \"fulcra-onboarding\",\n  \"version\": \"0.1.1\",\n  \"publishedAt\": 1781561211254\n}\n\nFile v0.1.1:references/fulcra-cli.md\n\n# Fulcra CLI\n\nFulcra Context is a universal data and memory platform that collects and records any data a user wants to ingest from any source. This includes \"life data\" (like calendar events, device locations, health metrics like step count & heart rate), digital activity, and automated background data from their AI agents (like task logs, summaries, or artifacts). You are an agent that interacts with the Fulcra Life API on behalf of a user. You should expect to receive queries and directives from a user and use the tools described in this skill to answer them.\n\n## Installation\n\nThe `fulcra-api` CLI command is the easiest way to interact with the Life API and can be installed and run via `uv tool run`:\n\n```\nuv tool run fulcra-api\n```\n\n\n## Authentication\n\nUse the `auth login` subcommand to authenticate to Fulcra on behalf of a user.\n\n```\nuv tool run fulcra-api auth login\n```\n\nThis will return a URL that you should direct the user to load in their browser, and a unique code that they should ensure matches the code displayed in their browser. **You must present the URL and code directly to the user; do not assume their browser will automatically open.**\n\nThe command will poll for a valid token and complete once the user finishes the authorization flow with a two minute timeout. Because it polls, you must run it as a background process or allow it to yield.\n\nCredentials will be persisted on the filesystem to `~/.config/fulcra/credentials.json` and the tool will refresh access tokens as neccessary.\n\n\n## Usage\n\nRely on the `--help` flag for in depth documentation on the command and individual subcommands.\n\n```\nuv tool run fulcra-api --help\n```\n\nAll command output, except for `auth`, is in JSON format and can be piped into another tool like `jq` for parsing and filtering structured data.\n\nAll date/time fields are returned in ISO 8601 format, time zone aware, and in UTC. They should be converted to a user's local time zone. Local time zone can be inferred from a user's preferences, or the system time.\n\n\n## Examples\n\nAuthenticate to the API:\n```\nuv tool run fulcra-api auth login\n```\n\nGet list of Fulcra data type identifiers:\n```\nuv tool run fulcra-api catalog | jq -r '.id'\n```\n\nReturn last week of step count records:\n```\nuv tool run fulcra-api get-records StepCount \"1 week\"\n```\n\nReturn a calculated time series of heart rate data for the last week:\n```\nuv tool run fulcra-api metric-time-series HeartRate \"1 week\"\n```\n\nReturn a user's configured time zone from user preferences:\n```\nuv tool run fulcra-api user-info | jq -r '.preferences.timezone'\n```\n\n## Creating Custom Data Types (Annotations)\n\nFulcra supports creating custom schemas based on specific root \"base types.\" You can create new schemas easily via the CLI.\n\n```bash\nuv tool run fulcra-api data-type create <BASE_DATA_TYPE> \"<NAME>\" --description \"<DESCRIPTION>\"\n```\n\n### Base Data Types\nRun `uv tool run fulcra-api catalog --base-types-only` to see the exact IDs of the base types you can build upon.\nThe most common base types for custom tracking are:\n*   `MomentAnnotation`: For tracking occurrences of an event without a specific measurement (e.g., \"Took Medication\").\n*   `NumericAnnotation`: For tracking a specific quantity or number (e.g., \"Cups of Coffee\").\n*   `BooleanAnnotation`: For tracking simple Yes/No or True/False states (e.g., \"Did I go to the gym?\").\n*   `ScaleAnnotation`: For 1-5 scales (e.g., mood, pain, intensity).\n\n### Creation Examples\n```bash\n# Create a simple moment annotation\nuv tool run fulcra-api data-type create MomentAnnotation \"Daily Walk\" --description \"Went for a walk today\"\n\n# Create a boolean annotation\nuv tool run fulcra-api data-type create BooleanAnnotation \"Ate Breakfast\" --description \"Did I eat breakfast?\"\n\n# Create a numeric annotation\nuv tool run fulcra-api data-type create NumericAnnotation \"Water Consumed\" --description \"Ounces of water drank\"\n\n# Create a scale annotation\nuv tool run fulcra-api data-type create ScaleAnnotation \"Daily Mood\" --description \"1-5 scale of mood\"\n```\n\nThe `create` command will output the JSON definition of the new data type. Make sure to capture the returned `\"id\"` value (e.g., `com.fulcradynamics.annotation.12345`), as you will need it to record data against this schema.\n\n## Further Reading & References\n\nAs an agent, you should rely on the `fulcra-api` CLI as the primary and most robust way to interact with Fulcra. However, if the CLI cannot be installed/used in your environment, or if a user requests something outside the CLI's capabilities, you may use alternative methods like raw `curl` requests or the Python SDK.\n\nTo maintain your context as Fulcra evolves, or to assist users with deeper technical questions, you can consult the following external resources:\n- **Fulcra Website:** [https://www.fulcradynamics.com/](https://www.fulcradynamics.com/)\n- **REST API Documentation:** [https://fulcradynamics.github.io/developer-docs/api-reference/](https://fulcradynamics.github.io/developer-docs/api-reference/)\n- **Python SDK & CLI Source:** [https://github.com/fulcradynamics/fulcra-api-python/](https://github.com/fulcradynamics/fulcra-api-python/)\n- **Fulcra Agent Skills Repository:** [https://github.com/fulcradynamics/agent-skills](https://github.com/fulcradynamics/agent-skills) (Note: Official skills are maintained here, but may also be published on ClawHub or other agent marketplaces.)\n\nFile v0.1.1:references/fulcra-onboarding-auth.md\n\n---\nname: fulcra-onboarding-auth\ndescription: \"Handles initial authentication for the Fulcra CLI.\"\n---\n\n# Fulcra Onboarding: Authentication\n\nThis reference handles Step 2 of the onboarding process, securely establishing the user's connection to Fulcra.\n\n## Workflow\n\n1. **Authentication Check & Login (Requires Consent):**\n   - Briefly explain that you need to connect to their Fulcra account via the command line.\n   - **Ask for their explicit permission** to check their Fulcra authentication state and initiate a login flow.\n   - **How to verify:** After obtaining consent, run `uv tool run fulcra-api user-info`. If it returns valid JSON, the user is authenticated and you can proceed immediately to the next step.\n   - If not authenticated, explain that you will now generate a secure login link, and then run `uv tool run fulcra-api auth login` using the `exec` tool. \n   - **CRITICAL EXECUTION NOTE:** You must ALWAYS execute this command using a background process tool, as it will hang and poll for completion for up to two minutes. The command will output an authorization URL and a device code. You **MUST** extract the login URL and device code from the stdout, present them directly to the user in your chat message as a clickable markdown link where the URL itself is the text (e.g., `[https://...](https://...)`) along with the code, and tell them to complete the flow in their browser. Remind them not to share the link or code. Do *not* assume the browser will open automatically for them, and do *not* combine the authentication instructions with further brainstorming. Wait for them to confirm completion, or poll the process output.\n\n2. **Completion:**\n   - Once the user successfully authenticates (or if they were already authenticated), declare the core onboarding complete!\n   - Hand control back to the main `fulcra-onboarding` flow to present the Next Steps menu.\n\nFile v0.1.1:references/fulcra-onboarding-prerequisites.md\n\n---\nname: fulcra-onboarding-prerequisites\ndescription: \"Verifies and sets up the required environment for Fulcra, including ensuring the 'uv' package manager is installed.\"\n---\n\n# Fulcra Prerequisites Check\n\nThis skill ensures the host environment is ready to interact with the Fulcra API.\n\n## Workflow\n\n1. **Verify `uv` Installat\n\nArchive v0.1.0: 10 files, 18460 bytes\n\nFiles: references/fulcra-cli.md (5201b), references/fulcra-onboarding-auth.md (1794b), references/fulcra-onboarding-demonstration.md (5958b), references/fulcra-onboarding-discovery.md (4257b), references/fulcra-onboarding-prerequisites.md (1901b), references/fulcra-onboarding-record-annotations.md (4003b), references/fulcra-onboarding-usecases.md (4830b), skill-card.md (3620b), SKILL.md (5508b), _meta.json (136b)\n\nArchive v0.0.9: 12 files, 21058 bytes\n\nFiles: references/fulcra-onboarding-backup.md (4593b), references/fulcra-onboarding-coordination.md (1710b), references/fulcra-onboarding-create-annotations.md (4688b), references/fulcra-onboarding-demonstration.md (5656b), references/fulcra-onboarding-discovery.md (3765b), references/fulcra-onboarding-handoff.md (2685b), references/fulcra-onboarding-prerequisites.md (1901b), references/fulcra-onboarding-record-annotations.md (4003b), references/fulcra-onboarding-usecases.md (4830b), skill-card.md (3478b), SKILL.md (4671b), _meta.json (136b)","readmeExcerpt":"Skill: Fulcra Onboarding (deprecated, use fulcra-get-started) Owner: fulcra Summary: Deprecated — renamed to fulcra-get-started. Use the fulcra-get-started skill instead. Tags: latest:0.3.0 Version history: v0.3.0 | 2026-08-12T20:42:58.062Z | auto - This version deprecates the fulcra-onboarding skill and renames it to fulcra-get-started. - The SKILL.md file is now a pointer directing users to use fulcra-get-started f","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"uv tool run fulcra-api"},{"language":"text","snippet":"uv tool run fulcra-api auth login --get-auth-url"},{"language":"text","snippet":"uv tool run fulcra-api auth login --device-code <DEVICE_CODE> --poll-timeout=5"},{"language":"text","snippet":"uv tool run fulcra-api --help"},{"language":"text","snippet":"uv tool run fulcra-api auth login --get-auth-url\n# ... present url/code to user, then ...\nuv tool run fulcra-api auth login --device-code <DEVICE_CODE> --poll-timeout=5"},{"language":"text","snippet":"uv tool run fulcra-api catalog | jq -r '.id'"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: fulcra-onboarding\ndescription: \"Deprecated — renamed to fulcra-get-started. Use the fulcra-get-started skill instead.\"\nhomepage: \"https://github.com/fulcradynamics/agent-skills\"\nlicense: \"MIT\"\nuser-invocable: true\nmetadata: { \"openclaw\": { \"emoji\": \"🌱\" } }\n---\n\n# Fulcra Onboarding — moved to `fulcra-get-started`\n\n> **This skill has been renamed.** `fulcra-onboarding` is deprecated and is kept only\n> as a pointer. All content now lives in the **`fulcra-get-started`** skill.\n\n## What to do\n\nUse the `fulcra-get-started` skill instead:\n\n- **In this repo:** `skills/fulcra-get-started/`\n- **GitHub:** https://github.com/fulcradynamics/agent-skills/tree/main/skills/fulcra-get-started\n- **Install:** `fulcradynamics/agent-skills/fulcra-get-started`\n\nIf you arrived here, read and follow `fulcra-get-started` — it walks you through\nconnecting to Fulcra for the first time (installing the CLI, logging in, and\nchoosing what to set up next)."},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn72pt2cb5f9nskgc9k2ddecxs87547j\",\n  \"slug\": \"fulcra-onboarding\",\n  \"version\": \"0.3.0\",\n  \"publishedAt\": 1786567378062\n}"},{"path":"skill-card.md","content":"## Description:\n\nDeprecated; renamed to fulcra-get-started. Use the fulcra-get-started skill instead.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[fulcra](https://clawhub.ai/user/fulcra)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this deprecated skill as a migration pointer to the fulcra-get-started skill for Fulcra onboarding and setup.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The deprecated skill points agents to mutable replacement instructions that can include installation, login, token, or account-access steps.\n\nMitigation: Verify the fulcra-get-started package or repository version and review CLI installation, login, token, and account-access steps before following them.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/fulcra/skills/fulcra-onboarding)\n- [Fulcra publisher profile](https://clawhub.ai/user/fulcra)\n- [Fulcra replacement skill](https://github.com/fulcradynamics/agent-skills/tree/main/skills/fulcra-get-started)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, guidance, configuration]\n\n**Output Format:** [Markdown guidance with inline code identifiers]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Deprecated pointer to fulcra-get-started; no direct execution artifacts.]\n\n## Skill Version(s):\n\n0.3.0 (source: server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Deprecated — renamed to fulcra-get-started. Use the fulcra-get-started skill instead. Skill: Fulcra Onboarding (deprecated, use fulcra-get-started) Owner: fulcra Summary: Deprecated — renamed to fulcra-get-started. Use the fulcra-get-started skill instead. Tags: latest:0.3.0 Version history: v0.3.0 | 2026-08-12T20:42:58.062Z | auto - This version deprecates the fulcra-onboarding skill and renames it to fulcra-get-started. - The SKILL.md file is now a pointer directing users to use fulcra-get-started f","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1278,"uniquenessScore":48,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T19:42:00.277Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-09T19:42:00.277Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-10T04:57:39.014Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}