{"id":"2e6a707e-31da-47fa-81ed-3d95116e7c4d","entityType":"agent","slug":"clawhub-fulcra-fulcra-agent-teams","name":"Fulcra Agent Teams (deprecated, use fulcra-workspaces)","canonicalUrl":"https://www.xpersona.co/agent/clawhub-fulcra-fulcra-agent-teams","canonicalPath":"/agent/clawhub-fulcra-fulcra-agent-teams","generatedAt":"2026-10-10T15:53:07.352Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-10T13:09:01.525Z","emptyReason":null},"description":"Deprecated — renamed to fulcra-workspaces. Use the fulcra-workspaces skill instead. Skill: Fulcra Agent Teams (deprecated, use fulcra-workspaces) Owner: fulcra Summary: Deprecated — renamed to fulcra-workspaces. Use the fulcra-workspaces skill instead. Tags: latest:0.1.0 Version history: v0.1.0 | 2026-08-12T20:44:51.147Z | auto The fulcra-agent-teams skill has been deprecated and renamed to fulcra-workspaces. - Marked the skill as deprecated; all prior documentation and functionality have been remov","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.4K downloads reported by the source. Last updated 10/10/2026.","installCommand":"clawhub skill install s173t2w929a11bv262sspwxv6h86t2yy:fulcra-agent-teams","sourceUrl":"https://clawhub.ai/fulcra/fulcra-agent-teams","homepage":"https://clawhub.ai/fulcra/skills/fulcra-agent-teams","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/fulcra/fulcra-agent-teams","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/fulcra/skills/fulcra-agent-teams","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":63,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Deprecated — renamed to fulcra-workspaces. Use the fulcra-workspaces skill instead. Skill: Fulcra Agent Teams (deprecated, use fulcra-workspaces) Owner: fulcra "},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-10T13:09:01.525Z","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":"2026-10-10T13:09:01.525Z","emptyReason":null},"stars":null,"forks":null,"downloads":1420,"packageName":null,"latestVersion":"0.1.0","tractionLabel":"1.4K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T13:09:01.525Z","emptyReason":null},"lastUpdatedAt":"2026-10-10T13:09:01.525Z","lastCrawledAt":"2026-10-10T13:09:01.525Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-11T13:09:01.525Z","lastVerifiedAt":null,"highlights":[{"version":"0.1.0","createdAt":"2026-08-12T20:44:51.147Z","changelog":"The fulcra-agent-teams skill has been deprecated and renamed to fulcra-workspaces. - Marked the skill as deprecated; all prior documentation and functionality have been removed. - SKILL.md now only provides a pointer to the new fulcra-workspaces skill. - Removed obsolete documentation and CLI reference files. - Users are directed to use fulcra-workspaces for all future team and workspace coordination needs.","fileCount":3,"zipByteSize":1838},{"version":"0.0.8","createdAt":"2026-07-30T17:01:37.339Z","changelog":"- Removed the redundant file skill-card.md. - No functional or user-facing changes in core skill logic. - Documentation and structural cleanup in SKILL.md only.","fileCount":4,"zipByteSize":10545},{"version":"0.0.7","createdAt":"2026-07-21T17:44:03.830Z","changelog":"- Updated documentation to clarify that team workspaces can be used by single agents, not just groups, creating persistent workspaces for agent output. - Improved descriptions of workspace purpose, emphasizing centralized, durable, user-owned data storage for agent products and work. - No functional or behavioral changes to code; this update primarily revises and streamlines the SKILL.md documentation. - Removed the redundant \"skill-card.md\" file.","fileCount":4,"zipByteSize":10332},{"version":"0.0.6","createdAt":"2026-07-02T23:29:19.189Z","changelog":"- Documentation revised to clarify that setting up automatic team inbox checking is now optional rather than required; users may choose manual or automatic workflows. - Language around background habits/cron for team activity was softened to highlight user choice and make automation opt-in. - Removed references in SKILL.md that implied agents must always seek user permission for automations; now presented as an optional, user-driven decision. - The file skill-card.md was removed for this release.","fileCount":4,"zipByteSize":10234},{"version":"0.0.5","createdAt":"2026-07-01T22:06:57.304Z","changelog":"- Introduced explicit team creation and joining procedures, including checks for existing teams and user-specified agent roles. - Added new required team files and directories: `role.md` (for team and member roles), `session/`, `task/`, and `knowledge/` for richer team collaboration and context tracking. - Updated inbox workflow to support both agent-convention and user-generated filenames; clarified requirements for archiving with timestamps to ensure chronological sorting. - Explained how to use the `data-updates` Fulcra API command for discovering recent changes without full directory listings. - Expanded documentation on maintaining session and task records within the team namespace for improved context sharing and traceability. - Removed `skill-card.md` file.","fileCount":4,"zipByteSize":10176},{"version":"0.0.4","createdAt":"2026-06-16T18:10:03.422Z","changelog":"- Added explicit directive discouraging the indexing or logging of transient inbox/archive messages in `index.md` or `log.md`, focusing OKF compliance on major team milestones only. - Updated guidance to clarify that team directory indexes should list inbox/archive directories at a high level, not enumerate every message/file. - Removed the file `skill-card.md`.","fileCount":4,"zipByteSize":6037},{"version":"0.0.3","createdAt":"2026-06-15T23:40:51.284Z","changelog":"- Updated team directory structure to require Open Knowledge Format (OKF) compliance. - Expanded documentation to specify OKF-compliant files, including required `index.md`, `log.md`, and OKF YAML frontmatter in `progress.md` and `completed.md`. - Clarified artifact directory usage for non-markdown files per OKF standards. - Provided direct links to the Fulcra CLI documentation and the full OKF specification. - Removed the legacy `skill-card.md` file.","fileCount":4,"zipByteSize":5812},{"version":"0.0.2","createdAt":"2026-06-12T20:36:19.862Z","changelog":"- Added support for optional automated inbox checking during agent heartbeats. - Requires explicit user consent before enabling background inbox checks. - Documents how to schedule automated inbox checks and proper logging of discovered messages. - Removed redundant file: skill-card.md.","fileCount":4,"zipByteSize":4961}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s173t2w929a11bv262sspwxv6h86t2yy:fulcra-agent-teams","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-agent-teams/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fulcra-fulcra-agent-teams/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fulcra-fulcra-agent-teams/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-fulcra-fulcra-agent-teams/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-fulcra-fulcra-agent-teams/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-fulcra-fulcra-agent-teams/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T15:53:07.348Z"}},"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-agent-teams/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fulcra-fulcra-agent-teams/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fulcra-fulcra-agent-teams/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-fulcra-fulcra-agent-teams/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":"2026-10-10T13:09:01.525Z","emptyReason":null},"readme":"Skill: Fulcra Agent Teams (deprecated, use fulcra-workspaces)\n\nOwner: fulcra\n\nSummary: Deprecated — renamed to fulcra-workspaces. Use the fulcra-workspaces skill instead.\n\nTags: latest:0.1.0\n\nVersion history:\n\nv0.1.0 | 2026-08-12T20:44:51.147Z | auto\n\nThe fulcra-agent-teams skill has been deprecated and renamed to fulcra-workspaces.\n\n- Marked the skill as deprecated; all prior documentation and functionality have been removed.\n- SKILL.md now only provides a pointer to the new fulcra-workspaces skill.\n- Removed obsolete documentation and CLI reference files.\n- Users are directed to use fulcra-workspaces for all future team and workspace coordination needs.\n\nv0.0.8 | 2026-07-30T17:01:37.339Z | auto\n\n- Removed the redundant file skill-card.md.\n- No functional or user-facing changes in core skill logic.\n- Documentation and structural cleanup in SKILL.md only.\n\nv0.0.7 | 2026-07-21T17:44:03.830Z | auto\n\n- Updated documentation to clarify that team workspaces can be used by single agents, not just groups, creating persistent workspaces for agent output.\n- Improved descriptions of workspace purpose, emphasizing centralized, durable, user-owned data storage for agent products and work.\n- No functional or behavioral changes to code; this update primarily revises and streamlines the SKILL.md documentation.\n- Removed the redundant \"skill-card.md\" file.\n\nv0.0.6 | 2026-07-02T23:29:19.189Z | auto\n\n- Documentation revised to clarify that setting up automatic team inbox checking is now optional rather than required; users may choose manual or automatic workflows.\n- Language around background habits/cron for team activity was softened to highlight user choice and make automation opt-in.\n- Removed references in SKILL.md that implied agents must always seek user permission for automations; now presented as an optional, user-driven decision.\n- The file skill-card.md was removed for this release.\n\nv0.0.5 | 2026-07-01T22:06:57.304Z | auto\n\n- Introduced explicit team creation and joining procedures, including checks for existing teams and user-specified agent roles.\n- Added new required team files and directories: `role.md` (for team and member roles), `session/`, `task/`, and `knowledge/` for richer team collaboration and context tracking.\n- Updated inbox workflow to support both agent-convention and user-generated filenames; clarified requirements for archiving with timestamps to ensure chronological sorting.\n- Explained how to use the `data-updates` Fulcra API command for discovering recent changes without full directory listings.\n- Expanded documentation on maintaining session and task records within the team namespace for improved context sharing and traceability.\n- Removed `skill-card.md` file.\n\nv0.0.4 | 2026-06-16T18:10:03.422Z | auto\n\n- Added explicit directive discouraging the indexing or logging of transient inbox/archive messages in `index.md` or `log.md`, focusing OKF compliance on major team milestones only.\n- Updated guidance to clarify that team directory indexes should list inbox/archive directories at a high level, not enumerate every message/file.\n- Removed the file `skill-card.md`.\n\nv0.0.3 | 2026-06-15T23:40:51.284Z | auto\n\n- Updated team directory structure to require Open Knowledge Format (OKF) compliance.\n- Expanded documentation to specify OKF-compliant files, including required `index.md`, `log.md`, and OKF YAML frontmatter in `progress.md` and `completed.md`.\n- Clarified artifact directory usage for non-markdown files per OKF standards.\n- Provided direct links to the Fulcra CLI documentation and the full OKF specification.\n- Removed the legacy `skill-card.md` file.\n\nv0.0.2 | 2026-06-12T20:36:19.862Z | auto\n\n- Added support for optional automated inbox checking during agent heartbeats.\n- Requires explicit user consent before enabling background inbox checks.\n- Documents how to schedule automated inbox checks and proper logging of discovered messages.\n- Removed redundant file: skill-card.md.\n\nv0.0.1 | 2026-06-08T23:40:39.734Z | auto\n\n- Initial release of fulcra-agent-teams skill.\n- Enables agents to collaborate using shared memory, team inboxes, and user artifacts via Fulcra's versioned file storage.\n- Defines clear directory structures and naming conventions for team coordination, inbox messaging, and artifact storage.\n- Includes important security guidelines to protect user data and ensure proper authorization for data transfers.\n- Provides workflow instructions for agents to manage files and messages using the Fulcra CLI.\n\nArchive index:\n\nArchive v0.1.0: 3 files, 1838 bytes\n\nFiles: skill-card.md (1790b), SKILL.md (982b), _meta.json (137b)\n\nFile v0.1.0:SKILL.md\n\n---\nname: fulcra-agent-teams\ndescription: \"Deprecated — renamed to fulcra-workspaces. Use the fulcra-workspaces skill instead.\"\nhomepage: \"https://github.com/fulcradynamics/agent-skills\"\nlicense: \"MIT\"\nuser-invocable: true\nmetadata: { \"openclaw\": { \"emoji\": \"🤝\" } }\n---\n\n# Fulcra Agent Teams — moved to `fulcra-workspaces`\n\n> **This skill has been renamed.** `fulcra-agent-teams` is deprecated and is kept only\n> as a pointer. All content now lives in the **`fulcra-workspaces`** skill.\n\n## What to do\n\nUse the `fulcra-workspaces` skill instead:\n\n- **In this repo:** `skills/fulcra-workspaces/`\n- **GitHub:** https://github.com/fulcradynamics/agent-skills/tree/main/skills/fulcra-workspaces\n- **Install:** `fulcradynamics/agent-skills/fulcra-workspaces`\n\nIf you arrived here, read and follow `fulcra-workspaces` — it lets agents\nestablish persistent, shared workspaces in Fulcra's versioned file storage for\ncoordinating work through team inboxes and user-owned artifacts.\n\nFile v0.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn72pt2cb5f9nskgc9k2ddecxs87547j\",\n  \"slug\": \"fulcra-agent-teams\",\n  \"version\": \"0.1.0\",\n  \"publishedAt\": 1786567491147\n}\n\nFile v0.1.0:skill-card.md\n\n## Description:\n\nDeprecated - renamed to fulcra-workspaces. Use the fulcra-workspaces 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\nDevelopers and agents use this deprecated skill as a pointer from fulcra-agent-teams to the replacement fulcra-workspaces skill. It helps users avoid relying on removed team coordination documentation and locate the renamed workspace skill.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Users may expect fulcra-agent-teams to provide active team coordination behavior even though this release is only a deprecated pointer.\n\nMitigation: Review and install fulcra-workspaces separately when Fulcra shared workspace features are needed.\n\n## Reference(s):\n\n- [Fulcra Agent Teams on ClawHub](https://clawhub.ai/fulcra/skills/fulcra-agent-teams)\n- [Fulcra Agent Skills Repository](https://github.com/fulcradynamics/agent-skills)\n- [fulcra-workspaces skill](https://github.com/fulcradynamics/agent-skills/tree/main/skills/fulcra-workspaces)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Markdown, Configuration]\n\n**Output Format:** [Markdown guidance with install and replacement-skill references]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Deprecated placeholder; no executable code or hidden behavior reported by security evidence.]\n\n## Skill Version(s):\n\n0.1.0 (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 v0.0.8: 4 files, 10545 bytes\n\nFiles: references/fulcra-agent-teams-cli.md (7550b), skill-card.md (2878b), SKILL.md (15177b), _meta.json (137b)\n\nFile v0.0.8:SKILL.md\n\n---\nname: fulcra-agent-teams\ndescription: \"Enable agents to collaborate using shared memory, team inboxes, and user artifacts via Fulcra's versioned file storage.\"\nhomepage: \"https://github.com/fulcradynamics/agent-skills\"\nlicense: \"MIT\"\nuser-invocable: true\nmetadata: { \"openclaw\": { \"emoji\": \"🤝\" } }\n---\n\n# Fulcra Agent Teams\n\nThe **primary role** of this skill is to allow agents to establish persistent workspaces in Fulcra's versioned file storage. A team workspace can be used by one or many agents, creating a centralized, durable place owned by the user where agent work, progress, and generated products can be securely stored, coordinated, and viewed.\n\n## 1. Uploading User Artifacts\n\nAgents can store generated assets, binaries, or compiled dashboards created for the user. Per the OKF standard, any non-markdown files must be stored in a dedicated `artifact/` directory.\n- **Namespace:** `agent/<agent-name>/artifact/` (e.g., `agent/wazir/artifact/onboarding-dashboard.html`)\n- **Note:** Always ask for explicit user approval before uploading anything to the artifact directory.\n\n## 2. Team Creation, Joining, & Coordination (OKF Compliant)\n\nAgents can collaborate and share memory using a shared `team/<team-name>/` prefix in the Fulcra datastore. This directory structure must conform to the Open Knowledge Format (OKF).\n\n### Creating a Team\nBefore creating a new team, you MUST always check if a team with that name already exists by listing the `team/` directory or checking for a `team/<team-name>/role.md` file. Do not accidentally overwrite or recreate an existing team structure. If the team already exists, simply join it.\n\n### Joining a Team\nWhen joining a team, do not assume your role. You MUST explicitly ask the user to confirm or clarify what your specific role, duties, and identity will be on this team. Once the user clarifies your role, document it in `team/<team-name>/member/<agent-name>/role.md`.\n\nAfter joining a team, you can optionally establish a habit for checking team activity:\n- Explain to the user that teamwork and team communication can be kept going autonomously by setting up a habit to regularly check your team inbox (`team/<team-name>/member/<agent-name>/inbox/`) and team activity.\n- Ask the user if they would like to set up this optional habit (e.g., via a background heartbeat entry in `HEARTBEAT.md` or an isolated cron job).\n- Emphasize that this is definitely optional; alternatively, they can just manually remind you to do team work each time.\n- If the user consents, set up the habit immediately so you don't miss incoming messages.\n\n**SECURITY & AUTHORIZATION WARNING:** Never transfer data, context, or files between agents without explicit authorization and strict respect for data ownership boundaries. Cross-agent data transfer can leak sensitive user context to a principal who lacks authorization. Ensure you explicitly warn the user if a team coordination action involves transferring private workspace data.\n\nWithin a team's directory, the following OKF structure is used:\n- **`team/<team-name>/index.md`**: Directory listing of the team's concepts and members.\n- **`team/<team-name>/log.md`**: Chronological update history for the team namespace.\n- **`team/<team-name>/role.md`**: The team's high-level purpose, overall mission, and operational identity. Agents should populate this when a new team is created. Must include OKF YAML frontmatter.\n- **`team/<team-name>/progress.md`**: Tracks what team members have recently done and what they plan to do next. Must include OKF YAML frontmatter.\n- **`team/<team-name>/completed.md`**: A growing record of each high-level objective completed by the team. Must include OKF YAML frontmatter.\n- **`team/<team-name>/artifact/`**: Shared non-markdown output files, deliverables, or binaries created by the team.\n- **`team/<team-name>/session/`**: Team-scoped session summaries recording discrete spates of work or collaboration.\n- **`team/<team-name>/task/`**: Team-scoped tracking for long-running, multi-session tasks.\n- **`team/<team-name>/knowledge/`**: A flexible, open-ended OKF knowledge base where team members can store, organize, and retrieve any domain knowledge, rules, or reference material useful for the team's shared objectives.\n- **`team/<team-name>/member/<agent-name>/role.md`**: The specific role, duties, and identity of the member within the team (e.g., manager delegating tasks vs. worker receiving tasks). Created when an agent joins a team.\n- **`team/<team-name>/member/<agent-name>/progress.md`**: A progress report for the specific team member. This is vital for maintaining context across isolated cron runs or background threads. It tracks what this specific agent is currently doing for the team, how to handle incoming tasks, and their immediate next steps. Must include OKF YAML frontmatter.\n- **`team/<team-name>/member/<agent-name>/inbox/`**: A drop-zone where other agents or users can place tasks, messages, or context for a specific agent.\n- **`team/<team-name>/member/<agent-name>/archive/`**: Where an agent moves its inbox messages once they have been read and processed.\n\n**IMPORTANT OKF EFFICIENCY DIRECTIVE:** While OKF compliance is required for team spaces, it must not become a burden.\n- **DO NOT** attempt to index or log every individual transient file or message within `member/<agent-name>/inbox/` or `member/<agent-name>/archive/`.\n- In the team's `index.md`, simply list the member directories or the `inbox/` directory as a whole with a high-level description (e.g., \"Contains unread coordination messages for the team\").\n- Keep the `index.md` and `log.md` focused strictly on major team milestones, high-level objectives, or structural additions (like a new member joining or a major artifact being published).\n\n### Checking for Team File Changes\nTo stay aware of recent team activity across many files and subdirectories without exhaustively listing them all, agents can use the Fulcra API's `data-updates` command (e.g., `uv tool run fulcra-api data-updates \"1 day\"`). This will return a summary of all uploaded files that changed recently, allowing agents to quickly identify which specific team files (if any) they should read to catch up on work they would not otherwise necessarily check.\n\n### The Inbox Lifecycle\n\nWhen collaborating, agents write markdown messages to one another's inboxes. To ensure messages sort chronologically and identify the sender, agents should ideally name messages using the convention: `YYYYMMDD-HHMMSS_<sender-name>_<short-topic>.md` (e.g., `20260608-232500_treecle_onboarding-status.md`).\n\nHowever, to accommodate users easily dropping manual tasks or context into an inbox, files placed here DO NOT strictly require this naming convention (e.g., a user might just drop `review-this.md`).\n\n**Thread Continuity:** When replying to a message or posting an update about a task, you MUST reuse the exact same `<short-topic>` component from the original message (or the base filename if it was manually dropped). This allows agents and users to track conversations and tasks across multiple inbox exchanges.\n\nWhen the target agent processes its inbox, it must first upload the message to its `archive/` directory, and then delete the original file from its `inbox/`. Because Fulcra's file system is versioned, it automatically keeps a perfect audit trail of when the file was created in the inbox and when it was completed (deleted).\n\nIf the original file name in the inbox does not already start with a timestamp, the processing agent MUST prepend a timestamp (`YYYYMMDD-HHMMSS_`) to the filename when saving it to the `archive/` directory. This ensures the archive remains chronologically sortable even for files manually dropped by users.\n\n### 3. Team Session and Task Tracking\n\nJust as agents maintain personal memory using the `fulcradynamics/agent-skills/fulcra-memory` skill, teams must track their collaborative work inside the shared team namespace.\n\n**Session Summaries:**\nWhen an agent completes a discrete block of work related to the team (e.g., resolving a team inbox message), the agent writes a session summary to the `team/<team-name>/session/` directory.\n- **Filename Convention:** Prefix the file with a timestamp (`YYYYMMDD-HHMMSS`) followed by an underscore, the agent's name, and a short subject (e.g., `team/research/session/20260623-180530_treecle_setup-dashboard.md`).\n- These files serve as targeted, easily-retrievable context. They should capture decisions made, important links, user preferences discovered, and the final state of the session.\n- Ensure the `session/` directory is listed in the top-level `index.md` with a high-level description. You do not need to index every individual session file in `index.md`.\n\n**Long-Running Tasks:**\nFor larger, ongoing objectives spanning multiple messages or sessions, track state in the `team/<team-name>/task/` directory.\n- **Filename Convention:** Name the file directly after the task (e.g., `team/research/task/setup-dashboard.md`). DO NOT prefix it with a timestamp.\n- These files track the overall purpose, current state, and result of the task. They should be updated periodically as work progresses.\n- **Task Updates:** When updating a task file, agents MUST append an entry documenting what was done, explicitly including the name of the agent doing the work, the date/time it was done, and relative links to any task-related files (such as newly generated artifacts or session summaries).\n- Task files MUST be included in the `team/<team-name>/task/index.md` file, which should list all active and completed tasks in the directory.\n\n**Team Knowledge Base:**\nThe `team/<team-name>/knowledge/` subdirectory allows teams to collaboratively build a shared repository of information. Because different teams and missions have unique requirements, this structure is deliberately open-ended.\n- Use OKF structuring (like `index.md` files) to organize topics, domains, or standard operating procedures.\n- **Fulcra Data Types:** If Fulcra data types (annotations, event logs, etc.) are being used to track the team's project, workspace, or deliverables, explicitly document those data types and their structure in the team's knowledge base so all agents understand how to log and read them.\n- Any team member can contribute to or retrieve from the knowledge base, ensuring all agents have access to the same foundational context without limiting the types of knowledge that can be stored.\n- Like other major subdirectories, `knowledge/` should be listed in the top-level team `index.md`.\n\n## 4. Completing Team Work (Updating State)\n\nWhenever an agent finishes processing a team task, inbox message, or background action (whether triggered by a chat, heartbeat, or cron job), they MUST synchronize their state with the rest of the team on Fulcra.\n\nBefore concluding the task or replying `HEARTBEAT_OK`, in addition to following other fulcra-agent-teams processes you must explicitly update:\n1. **Your Member Progress File:** Add an entry to `team/<team-name>/member/<agent-name>/progress.md` logging exactly what you just did and what your next steps are.\n2. **The Team Progress File:** If your work advanced a high-level team goal, append a brief summary to `team/<team-name>/progress.md`.\n3. **Task Files:** If you worked on a specific tracked task, append your update to the relevant `team/<team-name>/task/<task-name>.md` file.\n\nThis strict update requirement ensures that other agents (or your future self in an isolated cron job) always wake up to a perfectly accurate state.\n\n## 5. Automated Operations (Heartbeats & Cron)\n\nAgents can optionally check their inbox or perform team tasks automatically using their periodic background heartbeat (`HEARTBEAT.md`) or isolated cron jobs.\n\n**Background Heartbeats:**\n- **Require Consent:** You must explicitly ask the user for permission before enabling automated background inbox checks.\n- If the user approves, add a task to your local workspace's `HEARTBEAT.md` file to periodically check your inbox at `team/<team-name>/member/<agent-name>/inbox/`.\n- Ensure you log any new tasks or messages discovered during the heartbeat into your local daily memory logs, and process the message using the Inbox Lifecycle (archiving and deleting from the inbox).\n\n**Isolated Cron Jobs:**\n- **Require Consent:** You must explicitly ask the user for permission before creating any cron jobs for team tasks.\n- When setting up an isolated cron job for a team task (such as periodically checking your inbox), the `payload.message` (or `payload.text`) MUST explicitly instruct the agent to read the necessary context. \n- **Rule:** The cron payload must say something like: \"You are waking up to check your inbox at `team/<team-name>/member/<agent-name>/inbox/` and process new tasks. Before starting, you MUST read `team/<team-name>/progress.md`, `team/<team-name>/role.md`, your specific `team/<team-name>/member/<agent-name>/role.md`, and your specific `team/<team-name>/member/<agent-name>/progress.md` to establish context.\"\n- Ensure any new tasks or messages discovered during the cron run are processed using the Inbox Lifecycle (archiving and deleting from the inbox).\n- This prevents agents from attempting to work in isolated sessions without knowing current team states or priorities.\n\n## 6. Agent Local Memory Integration (MEMORY.md)\n\nTo ensure agents never lose track of their team responsibilities across main sessions and chats, an agent joining a team MUST update its own local long-term memory (`~/.openclaw/workspace/MEMORY.md`).\n- **Require Consent:** You must explicitly ask the user for permission before modifying your `MEMORY.md` file.\n- Once approved, add a clear directive to your `MEMORY.md` stating: \"Before starting any teamwork or processing team inbox messages (whether in chat, heartbeat, or cron), ALWAYS check the latest status in `team/<team-name>/progress.md`, the overall `team/<team-name>/role.md`, relevant `task/` files, your specific `team/<team-name>/member/<agent-name>/role.md`, and your specific `team/<team-name>/member/<agent-name>/progress.md`.\"\n- This guarantees the agent will organically recall to pull the latest Fulcra state before acting on team requests.\n\n## Workflow\n\nTo perform team operations, agents must interact with the Fulcra CLI. \n\nFor general information about the Fulcra File Store and the required Open Knowledge Format (OKF) standard, please refer to the main Fulcra CLI documentation found in the `fulcradynamics/agent-skills/fulcra-onboarding` skill, or read the full OKF specification directly:\n- [https://raw.githubusercontent.com/fulcradynamics/agent-skills/main/skills/fulcra-onboarding/references/fulcra-cli.md](https://raw.githubusercontent.com/fulcradynamics/agent-skills/main/skills/fulcra-onboarding/references/fulcra-cli.md)\n- [https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md](https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md)\n\nSee the reference documentation for the exact commands needed to manage artifacts and inbox messaging:\n- Read `references/fulcra-agent-teams-cli.md` for exact file management and CLI execution steps.\n\nFile v0.0.8:_meta.json\n\n{\n  \"ownerId\": \"kn72pt2cb5f9nskgc9k2ddecxs87547j\",\n  \"slug\": \"fulcra-agent-teams\",\n  \"version\": \"0.0.8\",\n  \"publishedAt\": 1785430897339\n}\n\nFile v0.0.8:references/fulcra-agent-teams-cli.md\n\n---\nname: fulcra-agent-teams-cli\ndescription: \"CLI command references for executing artifact uploads and team inbox operations with Fulcra.\"\n---\n\n# Fulcra Agent Teams CLI Reference\n\nThis reference dictates the exact shell commands required to execute the `fulcra-agent-teams` skill's operations. Ensure all CLI operations run in the agent's workspace.\n\n## Authentication Note\nIf you need to authenticate to Fulcra before running these commands, you must use the non-blocking two-step login process to prevent the CLI from hanging:\n1. `uv tool run fulcra-api auth login --get-auth-url` (present URL and code to user)\n2. `uv tool run fulcra-api auth login --device-code <DEVICE_CODE> --poll-timeout=5` (after user finishes flow)\n\n## 1. Checking Recent Team File Changes\n\nTo quickly check for recent updates across a team's namespaces without listing individual directories:\n\n```bash\n# Get a summary of files changed in the last 1 day\nuv tool run fulcra-api data-updates \"1 day\"\n\n# Example output:\n# {\n#   \"data_types\": {},\n#   \"file_changes\": [\n#     {\n#       \"full_name\": \"/team/first-olympiad/progress.md\",\n#       \"uploaded_at\": \"2026-07-01T21:23:28.690719Z\",\n#       \"state\": \"uploaded\",\n#       \"...\": \"...\"\n#     },\n#     {\n#       \"full_name\": \"/team/first-olympiad/task/setup-dashboard.md\",\n#       \"uploaded_at\": \"2026-07-01T21:23:28.690719Z\",\n#       \"state\": \"uploaded\",\n#       \"...\": \"...\"\n#     }\n#   ]\n# }\n```\n\n*Note: The `file_changes` key is a list of file metadata objects. You can extract the `full_name` from each to see the file paths. If the summary shows that specific team files were changed, you can then read those specific files to update your context.*\n\n## 2. Uploading User Artifacts\n\nWhen an agent generates a file (like an HTML dashboard, an image, or a report), and the user explicitly approves saving it to their Fulcra account, upload it to the `artifact/` subdirectory.\n\n```bash\n# Replace <agent_name> with the agent's name, and <artifact_name> with the file's name\nuv tool run fulcra-api file upload /path/to/local/file \"agent/<agent_name>/artifact/<artifact_name>\"\n```\n\n## 2. Team Coordination (Inbox & Archive)\n\nAgents can coordinate by writing to and reading from team namespaces.\n\n**Message Naming Convention:**\nMessages must follow the format `YYYYMMDD-HHMMSS_<sender-name>_<short-topic>.md`. Use underscores between the three main components so they can be reliably parsed.\n*Note: When replying to a message or providing a status update, always reuse the exact same `<short-topic>` as the original message to maintain thread continuity.*\n\n**Step A: Sending a message to a teammate's inbox**\n```bash\n# Upload a local markdown file to the target agent's inbox\nuv tool run fulcra-api file upload /tmp/message.md \"team/<team_name>/member/<target_agent_name>/inbox/20260608-232500_wazir_status-update.md\"\n```\n\n**Step B: Checking your inbox**\n```bash\n# List files in your agent's inbox\nuv tool run fulcra-api file list \"team/<team_name>/member/<your_agent_name>/inbox/\"\n```\n\n**Step C: Processing and Archiving a message**\nOnce you have downloaded and read a message from your inbox, move it to the archive. If the file was manually dropped and lacks a timestamp, **you must prepend one** (`YYYYMMDD-HHMMSS_`) when saving it to `archive/`.\n\n```bash\n# 1. Download to read (if you haven't already)\nuv tool run fulcra-api file download \"team/<team_name>/member/<your_agent_name>/inbox/20260608-232500_wazir_status-update.md\" /tmp/20260608-232500_wazir_status-update.md\n\n# 2. Upload it to your archive directory\nuv tool run fulcra-api file upload /tmp/20260608-232500_wazir_status-update.md \"team/<team_name>/member/<your_agent_name>/archive/20260608-232500_wazir_status-update.md\"\n\n# 3. Verify archival succeeded before deletion!\nuv tool run fulcra-api file stat \"team/<team_name>/member/<your_agent_name>/archive/20260608-232500_wazir_status-update.md\"\n\n# 4. Delete it from the inbox to clear it (only if step 3 succeeded)\nuv tool run fulcra-api file delete \"team/<team_name>/member/<your_agent_name>/inbox/20260608-232500_wazir_status-update.md\"\n```\n\n## 3. Team Activity Tracking (OKF Compliant)\n\nAgents can update shared files to track the team's high-level progress and completed objectives. Ensure all markdown files contain OKF YAML frontmatter, and that `log.md` and `index.md` are updated when appropriate.\n\n**Step A: Updating Team Progress**\nTo update the `progress.md` file (which stores what the team members have recently done and what they plan to do next):\n```bash\n# 1. Download the current progress file\nuv tool run fulcra-api file download \"team/<team_name>/progress.md\" /tmp/team_progress.md || touch /tmp/team_progress.md\n\n# 2. Edit /tmp/team_progress.md locally to reflect the latest plans and recent work. \n# Make sure it has OKF frontmatter:\n# ---\n# type: Progress Report\n# title: Team Progress\n# ---\n\n# 3. Upload the updated file back to Fulcra\nuv tool run fulcra-api file upload /tmp/team_progress.md \"team/<team_name>/progress.md\"\n\n# 4. Also append an update entry to log.md\nDATE=$(date -u +\"%Y-%m-%d\")\necho \"## $DATE\" > /tmp/log_update.md\necho \"* **Update**: <agent_name> updated team progress.\" >> /tmp/log_update.md\n# (In practice, download log.md, append the update under the correct date, and re-upload)\n```\n\n**Step B: Recording Completed Objectives**\nTo add a newly completed high-level objective to `completed.md` (which should generally only grow):\n```bash\n# 1. Download the current completed file\nuv tool run fulcra-api file download \"team/<team_name>/completed.md\" /tmp/team_completed.md || touch /tmp/team_completed.md\n\n# 2. Append the new objective (ensure OKF frontmatter exists at the top of the file)\necho \"- [$(date +%Y-%m-%d)] <Objective summary>\" >> /tmp/team_completed.md\n\n# 3. Upload the updated file back to Fulcra\nuv tool run fulcra-api file upload /tmp/team_completed.md \"team/<team_name>/completed.md\"\n```\n\n**Step C: Syncing Team and Member Roles & Progress**\nTo ensure the team and its members understand their purpose and current context, maintain `role.md` and member `progress.md` files (with proper OKF frontmatter).\n```bash\n# Update the overall team role\nuv tool run fulcra-api file upload /tmp/team-role.md \"team/<team_name>/role.md\"\n\n# Update your specific agent's role within the team\nuv tool run fulcra-api file upload /tmp/member-role.md \"team/<team_name>/member/<your_agent_name>/role.md\"\n\n# Update your specific agent's progress (critical for isolated background jobs)\nuv tool run fulcra-api file upload /tmp/member-progress.md \"team/<team_name>/member/<your_agent_name>/progress.md\"\n```\n\n## 4. Team Session and Task Tracking\n\nWhen completing a discrete block of work or tracking a long-running project within the team, upload summaries to the team namespace rather than your personal memory namespace.\n\n**Step A: Uploading a Session Summary**\nWhen a team session concludes, create a concise markdown summary (with `type: Session Summary` frontmatter) and upload it.\n```bash\n# Filename convention: YYYYMMDD-HHMMSS_<agent-name>_<subject>.md\nuv tool run fulcra-api file upload /tmp/session-summary.md \"team/<team_name>/session/20260623-180530_treecle_setup-dashboard.md\"\n```\n\n**Step B: Updating a Task Tracker**\nFor ongoing team objectives, update a task tracker (with `type: Task` frontmatter) and its index.\n```bash\n# Filename convention: <task-name>.md (No timestamp)\nuv tool run fulcra-api file upload /tmp/task-status.md \"team/<team_name>/task/setup-dashboard.md\"\nuv tool run fulcra-api file upload /tmp/task-index.md \"team/<team_name>/task/index.md\"\n```\n\nFile v0.0.8:skill-card.md\n\n## Description: <br>\nEnable agents to collaborate using shared memory, team inboxes, and user artifacts via Fulcra's versioned file storage. <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>\nDevelopers and agent operators use this skill to set up Fulcra-backed team workspaces, exchange inbox messages, preserve shared progress, and store approved user artifacts across one or more agents. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Shared team memory can expose private workspace context or files to another agent or principal. <br>\nMitigation: Require explicit authorization before transferring data between agents, define the team and allowed data scope up front, and avoid sharing raw private files unless the user clearly intends it. <br>\nRisk: Automated heartbeat or cron checks can continue processing team inboxes beyond the user's expected scope. <br>\nMitigation: Enable automation only with explicit consent, document the exact team, inbox, task scope, and duration, and include current team and member context in each automated run. <br>\nRisk: Inbox cleanup can remove the visible copy of a task before the agent has preserved it. <br>\nMitigation: Archive the inbox message first, verify the archived file exists, and delete the inbox copy only after that verification succeeds. <br>\nRisk: Artifact uploads can store sensitive generated files in Fulcra. <br>\nMitigation: Ask for explicit approval before uploading artifacts and place non-markdown outputs only in the documented artifact namespace. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/fulcra/skills/fulcra-agent-teams) <br>\n- [Fulcra Agent Teams CLI Reference](references/fulcra-agent-teams-cli.md) <br>\n- [Fulcra CLI documentation](https://raw.githubusercontent.com/fulcradynamics/agent-skills/main/skills/fulcra-onboarding/references/fulcra-cli.md) <br>\n- [Open Knowledge Format specification](https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [guidance, markdown, shell commands, configuration] <br>\n**Output Format:** [Markdown guidance with file path conventions and inline shell commands] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May create or update Fulcra file-store content only after user consent.] <br>\n\n## Skill Version(s): <br>\n0.0.8 (source: ClawHub 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 v0.0.7: 4 files, 10332 bytes\n\nFiles: references/fulcra-agent-teams-cli.md (7550b), skill-card.md (2688b), SKILL.md (14890b), _meta.json (137b)\n\nFile v0.0.7:SKILL.md\n\n---\nname: fulcra-agent-teams\ndescription: \"Enable agents to collaborate using shared memory, team inboxes, and user artifacts via Fulcra's versioned file storage.\"\nhomepage: \"https://github.com/fulcradynamics/agent-skills\"\nlicense: \"MIT\"\nuser-invocable: true\nmetadata: { \"openclaw\": { \"emoji\": \"🤝\" } }\n---\n\n# Fulcra Agent Teams\n\nThe **primary role** of this skill is to allow agents to establish persistent workspaces in Fulcra's versioned file storage. A team workspace can be used by one or many agents, creating a centralized, durable place owned by the user where agent work, progress, and generated products can be securely stored, coordinated, and viewed.\n\n## 1. Uploading User Artifacts\n\nAgents can store generated assets, binaries, or compiled dashboards created for the user. Per the OKF standard, any non-markdown files must be stored in a dedicated `artifact/` directory.\n- **Namespace:** `agent/<agent-name>/artifact/` (e.g., `agent/wazir/artifact/onboarding-dashboard.html`)\n- **Note:** Always ask for explicit user approval before uploading anything to the artifact directory.\n\n## 2. Team Creation, Joining, & Coordination (OKF Compliant)\n\nAgents can collaborate and share memory using a shared `team/<team-name>/` prefix in the Fulcra datastore. This directory structure must conform to the Open Knowledge Format (OKF).\n\n### Creating a Team\nBefore creating a new team, you MUST always check if a team with that name already exists by listing the `team/` directory or checking for a `team/<team-name>/role.md` file. Do not accidentally overwrite or recreate an existing team structure. If the team already exists, simply join it.\n\n### Joining a Team\nWhen joining a team, do not assume your role. You MUST explicitly ask the user to confirm or clarify what your specific role, duties, and identity will be on this team. Once the user clarifies your role, document it in `team/<team-name>/member/<agent-name>/role.md`.\n\nAfter joining a team, you can optionally establish a habit for checking team activity:\n- Explain to the user that teamwork and team communication can be kept going autonomously by setting up a habit to regularly check your team inbox (`team/<team-name>/member/<agent-name>/inbox/`) and team activity.\n- Ask the user if they would like to set up this optional habit (e.g., via a background heartbeat entry in `HEARTBEAT.md` or an isolated cron job).\n- Emphasize that this is definitely optional; alternatively, they can just manually remind you to do team work each time.\n- If the user consents, set up the habit immediately so you don't miss incoming messages.\n\n**SECURITY & AUTHORIZATION WARNING:** Never transfer data, context, or files between agents without explicit authorization and strict respect for data ownership boundaries. Cross-agent data transfer can leak sensitive user context to a principal who lacks authorization. Ensure you explicitly warn the user if a team coordination action involves transferring private workspace data.\n\nWithin a team's directory, the following OKF structure is used:\n- **`team/<team-name>/index.md`**: Directory listing of the team's concepts and members.\n- **`team/<team-name>/log.md`**: Chronological update history for the team namespace.\n- **`team/<team-name>/role.md`**: The team's high-level purpose, overall mission, and operational identity. Agents should populate this when a new team is created. Must include OKF YAML frontmatter.\n- **`team/<team-name>/progress.md`**: Tracks what team members have recently done and what they plan to do next. Must include OKF YAML frontmatter.\n- **`team/<team-name>/completed.md`**: A growing record of each high-level objective completed by the team. Must include OKF YAML frontmatter.\n- **`team/<team-name>/artifact/`**: Shared non-markdown output files, deliverables, or binaries created by the team.\n- **`team/<team-name>/session/`**: Team-scoped session summaries recording discrete spates of work or collaboration.\n- **`team/<team-name>/task/`**: Team-scoped tracking for long-running, multi-session tasks.\n- **`team/<team-name>/knowledge/`**: A flexible, open-ended OKF knowledge base where team members can store, organize, and retrieve any domain knowledge, rules, or reference material useful for the team's shared objectives.\n- **`team/<team-name>/member/<agent-name>/role.md`**: The specific role, duties, and identity of the member within the team (e.g., manager delegating tasks vs. worker receiving tasks). Created when an agent joins a team.\n- **`team/<team-name>/member/<agent-name>/progress.md`**: A progress report for the specific team member. This is vital for maintaining context across isolated cron runs or background threads. It tracks what this specific agent is currently doing for the team, how to handle incoming tasks, and their immediate next steps. Must include OKF YAML frontmatter.\n- **`team/<team-name>/member/<agent-name>/inbox/`**: A drop-zone where other agents or users can place tasks, messages, or context for a specific agent.\n- **`team/<team-name>/member/<agent-name>/archive/`**: Where an agent moves its inbox messages once they have been read and processed.\n\n**IMPORTANT OKF EFFICIENCY DIRECTIVE:** While OKF compliance is required for team spaces, it must not become a burden.\n- **DO NOT** attempt to index or log every individual transient file or message within `member/<agent-name>/inbox/` or `member/<agent-name>/archive/`.\n- In the team's `index.md`, simply list the member directories or the `inbox/` directory as a whole with a high-level description (e.g., \"Contains unread coordination messages for the team\").\n- Keep the `index.md` and `log.md` focused strictly on major team milestones, high-level objectives, or structural additions (like a new member joining or a major artifact being published).\n\n### Checking for Team File Changes\nTo stay aware of recent team activity across many files and subdirectories without exhaustively listing them all, agents can use the Fulcra API's `data-updates` command (e.g., `uv tool run fulcra-api data-updates \"1 day\"`). This will return a summary of all uploaded files that changed recently, allowing agents to quickly identify which specific team files (if any) they should read to catch up on work they would not otherwise necessarily check.\n\n### The Inbox Lifecycle\n\nWhen collaborating, agents write markdown messages to one another's inboxes. To ensure messages sort chronologically and identify the sender, agents should ideally name messages using the convention: `YYYYMMDD-HHMMSS_<sender-name>_<short-topic>.md` (e.g., `20260608-232500_treecle_onboarding-status.md`).\n\nHowever, to accommodate users easily dropping manual tasks or context into an inbox, files placed here DO NOT strictly require this naming convention (e.g., a user might just drop `review-this.md`).\n\n**Thread Continuity:** When replying to a message or posting an update about a task, you MUST reuse the exact same `<short-topic>` component from the original message (or the base filename if it was manually dropped). This allows agents and users to track conversations and tasks across multiple inbox exchanges.\n\nWhen the target agent processes its inbox, it must first upload the message to its `archive/` directory, and then delete the original file from its `inbox/`. Because Fulcra's file system is versioned, it automatically keeps a perfect audit trail of when the file was created in the inbox and when it was completed (deleted).\n\nIf the original file name in the inbox does not already start with a timestamp, the processing agent MUST prepend a timestamp (`YYYYMMDD-HHMMSS_`) to the filename when saving it to the `archive/` directory. This ensures the archive remains chronologically sortable even for files manually dropped by users.\n\n### 3. Team Session and Task Tracking\n\nJust as agents maintain personal memory using the `fulcradynamics/agent-skills/fulcra-memory` skill, teams must track their collaborative work inside the shared team namespace.\n\n**Session Summaries:**\nWhen an agent completes a discrete block of work related to the team (e.g., resolving a team inbox message), the agent writes a session summary to the `team/<team-name>/session/` directory.\n- **Filename Convention:** Prefix the file with a timestamp (`YYYYMMDD-HHMMSS`) followed by an underscore, the agent's name, and a short subject (e.g., `team/research/session/20260623-180530_treecle_setup-dashboard.md`).\n- These files serve as targeted, easily-retrievable context. They should capture decisions made, important links, user preferences discovered, and the final state of the session.\n- Ensure the `session/` directory is listed in the top-level `index.md` with a high-level description. You do not need to index every individual session file in `index.md`.\n\n**Long-Running Tasks:**\nFor larger, ongoing objectives spanning multiple messages or sessions, track state in the `team/<team-name>/task/` directory.\n- **Filename Convention:** Name the file directly after the task (e.g., `team/research/task/setup-dashboard.md`). DO NOT prefix it with a timestamp.\n- These files track the overall purpose, current state, and result of the task. They should be updated periodically as work progresses.\n- **Task Updates:** When updating a task file, agents MUST append an entry documenting what was done, explicitly including the name of the agent doing the work, the date/time it was done, and relative links to any task-related files (such as newly generated artifacts or session summaries).\n- Task files MUST be included in the `team/<team-name>/task/index.md` file, which should list all active and completed tasks in the directory.\n\n**Team Knowledge Base:**\nThe `team/<team-name>/knowledge/` subdirectory allows teams to collaboratively build a shared repository of information. Because different teams and missions have unique requirements, this structure is deliberately open-ended.\n- Use OKF structuring (like `index.md` files) to organize topics, domains, or standard operating procedures.\n- Any team member can contribute to or retrieve from the knowledge base, ensuring all agents have access to the same foundational context without limiting the types of knowledge that can be stored.\n- Like other major subdirectories, `knowledge/` should be listed in the top-level team `index.md`.\n\n## 4. Completing Team Work (Updating State)\n\nWhenever an agent finishes processing a team task, inbox message, or background action (whether triggered by a chat, heartbeat, or cron job), they MUST synchronize their state with the rest of the team on Fulcra.\n\nBefore concluding the task or replying `HEARTBEAT_OK`, in addition to following other fulcra-agent-teams processes you must explicitly update:\n1. **Your Member Progress File:** Add an entry to `team/<team-name>/member/<agent-name>/progress.md` logging exactly what you just did and what your next steps are.\n2. **The Team Progress File:** If your work advanced a high-level team goal, append a brief summary to `team/<team-name>/progress.md`.\n3. **Task Files:** If you worked on a specific tracked task, append your update to the relevant `team/<team-name>/task/<task-name>.md` file.\n\nThis strict update requirement ensures that other agents (or your future self in an isolated cron job) always wake up to a perfectly accurate state.\n\n## 5. Automated Operations (Heartbeats & Cron)\n\nAgents can optionally check their inbox or perform team tasks automatically using their periodic background heartbeat (`HEARTBEAT.md`) or isolated cron jobs.\n\n**Background Heartbeats:**\n- **Require Consent:** You must explicitly ask the user for permission before enabling automated background inbox checks.\n- If the user approves, add a task to your local workspace's `HEARTBEAT.md` file to periodically check your inbox at `team/<team-name>/member/<agent-name>/inbox/`.\n- Ensure you log any new tasks or messages discovered during the heartbeat into your local daily memory logs, and process the message using the Inbox Lifecycle (archiving and deleting from the inbox).\n\n**Isolated Cron Jobs:**\n- **Require Consent:** You must explicitly ask the user for permission before creating any cron jobs for team tasks.\n- When setting up an isolated cron job for a team task (such as periodically checking your inbox), the `payload.message` (or `payload.text`) MUST explicitly instruct the agent to read the necessary context. \n- **Rule:** The cron payload must say something like: \"You are waking up to check your inbox at `team/<team-name>/member/<agent-name>/inbox/` and process new tasks. Before starting, you MUST read `team/<team-name>/progress.md`, `team/<team-name>/role.md`, your specific `team/<team-name>/member/<agent-name>/role.md`, and your specific `team/<team-name>/member/<agent-name>/progress.md` to establish context.\"\n- Ensure any new tasks or messages discovered during the cron run are processed using the Inbox Lifecycle (archiving and deleting from the inbox).\n- This prevents agents from attempting to work in isolated sessions without knowing current team states or priorities.\n\n## 6. Agent Local Memory Integration (MEMORY.md)\n\nTo ensure agents never lose track of their team responsibilities across main sessions and chats, an agent joining a team MUST update its own local long-term memory (`~/.openclaw/workspace/MEMORY.md`).\n- **Require Consent:** You must explicitly ask the user for permission before modifying your `MEMORY.md` file.\n- Once approved, add a clear directive to your `MEMORY.md` stating: \"Before starting any teamwork or processing team inbox messages (whether in chat, heartbeat, or cron), ALWAYS check the latest status in `team/<team-name>/progress.md`, the overall `team/<team-name>/role.md`, relevant `task/` files, your specific `team/<team-name>/member/<agent-name>/role.md`, and your specific `team/<team-name>/member/<agent-name>/progress.md`.\"\n- This guarantees the agent will organically recall to pull the latest Fulcra state before acting on team requests.\n\n## Workflow\n\nTo perform team operations, agents must interact with the Fulcra CLI. \n\nFor general information about the Fulcra File Store and the required Open Knowledge Format (OKF) standard, please refer to the main Fulcra CLI documentation found in the `fulcradynamics/agent-skills/fulcra-onboarding` skill, or read the full OKF specification directly:\n- [https://raw.githubusercontent.com/fulcradynamics/agent-skills/main/skills/fulcra-onboarding/references/fulcra-cli.md](https://raw.githubusercontent.com/fulcradynamics/agent-skills/main/skills/fulcra-onboarding/references/fulcra-cli.md)\n- [https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md](https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md)\n\nSee the reference documentation for the exact commands needed to manage artifacts and inbox messaging:\n- Read `references/fulcra-agent-teams-cli.md` for exact file management and CLI execution steps.\n\nFile v0.0.7:_meta.json\n\n{\n  \"ownerId\": \"kn72pt2cb5f9nskgc9k2ddecxs87547j\",\n  \"slug\": \"fulcra-agent-teams\",\n  \"version\": \"0.0.7\",\n  \"publishedAt\": 1784655843830\n}\n\nFile v0.0.7:references/fulcra-agent-teams-cli.md\n\n---\nname: fulcra-agent-teams-cli\ndescription: \"CLI command references for executing artifact uploads and team inbox operations with Fulcra.\"\n---\n\n# Fulcra Agent Teams CLI Reference\n\nThis reference dictates the exact shell commands required to execute the `fulcra-agent-teams` skill's operations. Ensure all CLI operations run in the agent's workspace.\n\n## Authentication Note\nIf you need to authenticate to Fulcra before running these commands, you must use the non-blocking two-step login process to prevent the CLI from hanging:\n1. `uv tool run fulcra-api auth login --get-auth-url` (present URL and code to user)\n2. `uv tool run fulcra-api auth login --device-code <DEVICE_CODE> --poll-timeout=5` (after user finishes flow)\n\n## 1. Checking Recent Team File Changes\n\nTo quickly check for recent updates across a team's namespaces without listing individual directories:\n\n```bash\n# Get a summary of files changed in the last 1 day\nuv tool run fulcra-api data-updates \"1 day\"\n\n# Example output:\n# {\n#   \"data_types\": {},\n#   \"file_changes\": [\n#     {\n#       \"full_name\": \"/team/first-olympiad/progress.md\",\n#       \"uploaded_at\": \"2026-07-01T21:23:28.690719Z\",\n#       \"state\": \"uploaded\",\n#       \"...\": \"...\"\n#     },\n#     {\n#       \"full_name\": \"/team/first-olympiad/task/setup-dashboard.md\",\n#       \"uploaded_at\": \"2026-07-01T21:23:28.690719Z\",\n#       \"state\": \"uploaded\",\n#       \"...\": \"...\"\n#     }\n#   ]\n# }\n```\n\n*Note: The `file_changes` key is a list of file metadata objects. You can extract the `full_name` from each to see the file paths. If the summary shows that specific team files were changed, you can then read those specific files to update your context.*\n\n## 2. Uploading User Artifacts\n\nWhen an agent generates a file (like an HTML dashboard, an image, or a report), and the user explicitly approves saving it to their Fulcra account, upload it to the `artifact/` subdirectory.\n\n```bash\n# Replace <agent_name> with the agent's name, and <artifact_name> with the file's name\nuv tool run fulcra-api file upload /path/to/local/file \"agent/<agent_name>/artifact/<artifact_name>\"\n```\n\n## 2. Team Coordination (Inbox & Archive)\n\nAgents can coordinate by writing to and reading from team namespaces.\n\n**Message Naming Convention:**\nMessages must follow the format `YYYYMMDD-HHMMSS_<sender-name>_<short-topic>.md`. Use underscores between the three main components so they can be reliably parsed.\n*Note: When replying to a message or providing a status update, always reuse the exact same `<short-topic>` as the original message to maintain thread continuity.*\n\n**Step A: Sending a message to a teammate's inbox**\n```bash\n# Upload a local markdown file to the target agent's inbox\nuv tool run fulcra-api file upload /tmp/message.md \"team/<team_name>/member/<target_agent_name>/inbox/20260608-232500_wazir_status-update.md\"\n```\n\n**Step B: Checking your inbox**\n```bash\n# List files in your agent's inbox\nuv tool run fulcra-api file list \"team/<team_name>/member/<your_agent_name>/inbox/\"\n```\n\n**Step C: Processing and Archiving a message**\nOnce you have downloaded and read a message from your inbox, move it to the archive. If the file was manually dropped and lacks a timestamp, **you must prepend one** (`YYYYMMDD-HHMMSS_`) when saving it to `archive/`.\n\n```bash\n# 1. Download to read (if you haven't already)\nuv tool run fulcra-api file download \"team/<team_name>/member/<your_agent_name>/inbox/20260608-232500_wazir_status-update.md\" /tmp/20260608-232500_wazir_status-update.md\n\n# 2. Upload it to your archive directory\nuv tool run fulcra-api file upload /tmp/20260608-232500_wazir_status-update.md \"team/<team_name>/member/<your_agent_name>/archive/20260608-232500_wazir_status-update.md\"\n\n# 3. Verify archival succeeded before deletion!\nuv tool run fulcra-api file stat \"team/<team_name>/member/<your_agent_name>/archive/20260608-232500_wazir_status-update.md\"\n\n# 4. Delete it from the inbox to clear it (only if step 3 succeeded)\nuv tool run fulcra-api file delete \"team/<team_name>/member/<your_agent_name>/inbox/20260608-232500_wazir_status-update.md\"\n```\n\n## 3. Team Activity Tracking (OKF Compliant)\n\nAgents can update shared files to track the team's high-level progress and completed objectives. Ensure all markdown files contain OKF YAML frontmatter, and that `log.md` and `index.md` are updated when appropriate.\n\n**Step A: Updating Team Progress**\nTo update the `progress.md` file (which stores what the team members have recently done and what they plan to do next):\n```bash\n# 1. Download the current progress file\nuv tool run fulcra-api file download \"team/<team_name>/progress.md\" /tmp/team_progress.md || touch /tmp/team_progress.md\n\n# 2. Edit /tmp/team_progress.md locally to reflect the latest plans and recent work. \n# Make sure it has OKF frontmatter:\n# ---\n# type: Progress Report\n# title: Team Progress\n# ---\n\n# 3. Upload the updated file back to Fulcra\nuv tool run fulcra-api file upload /tmp/team_progress.md \"team/<team_name>/progress.md\"\n\n# 4. Also append an update entry to log.md\nDATE=$(date -u +\"%Y-%m-%d\")\necho \"## $DATE\" > /tmp/log_update.md\necho \"* **Update**: <agent_name> updated team progress.\" >> /tmp/log_update.md\n# (In practice, download log.md, append the update under the correct date, and re-upload)\n```\n\n**Step B: Recording Completed Objectives**\nTo add a newly completed high-level objective to `completed.md` (which should generally only grow):\n```bash\n# 1. Download the current completed file\nuv tool run fulcra-api file download \"team/<team_name>/completed.md\" /tmp/team_completed.md || touch /tmp/team_completed.md\n\n# 2. Append the new objective (ensure OKF frontmatter exists at the top of the file)\necho \"- [$(date +%Y-%m-%d)] <Objective summary>\" >> /tmp/team_completed.md\n\n# 3. Upload the updated file back to Fulcra\nuv tool run fulcra-api file upload /tmp/team_completed.md \"team/<team_name>/completed.md\"\n```\n\n**Step C: Syncing Team and Member Roles & Progress**\nTo ensure the team and its members understand their purpose and current context, maintain `role.md` and member `progress.md` files (with proper OKF frontmatter).\n```bash\n# Update the overall team role\nuv tool run fulcra-api file upload /tmp/team-role.md \"team/<team_name>/role.md\"\n\n# Update your specific agent's role within the team\nuv tool run fulcra-api file upload /tmp/member-role.md \"team/<team_name>/member/<your_agent_name>/role.md\"\n\n# Update your specific agent's progress (critical for isolated background jobs)\nuv tool run fulcra-api file upload /tmp/member-progress.md \"team/<team_name>/member/<your_agent_name>/progress.md\"\n```\n\n## 4. Team Session and Task Tracking\n\nWhen completing a discrete block of work or tracking a long-running project within the team, upload summaries to the team namespace rather than your personal memory namespace.\n\n**Step A: Uploading a Session Summary**\nWhen a team session concludes, create a concise markdown summary (with `type: Session Summary` frontmatter) and upload it.\n```bash\n# Filename convention: YYYYMMDD-HHMMSS_<agent-name>_<subject>.md\nuv tool run fulcra-api file upload /tmp/session-summary.md \"team/<team_name>/session/20260623-180530_treecle_setup-dashboard.md\"\n```\n\n**Step B: Updating a Task Tracker**\nFor ongoing team objectives, update a task tracker (with `type: Task` frontmatter) and its index.\n```bash\n# Filename convention: <task-name>.md (No timestamp)\nuv tool run fulcra-api file upload /tmp/task-status.md \"team/<team_name>/task/setup-dashboard.md\"\nuv tool run fulcra-api file upload /tmp/task-index.md \"team/<team_name>/task/index.md\"\n```\n\nFile v0.0.7:skill-card.md\n\n## Description: <br>\nEnable agents to collaborate using shared memory, team inboxes, and user artifacts via Fulcra's versioned file storage. <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>\nDevelopers and agent operators use this skill to create persistent Fulcra team workspaces, coordinate work through shared inboxes, and store user-approved artifacts in versioned file storage. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Persistent shared state can retain team context, inbox messages, and generated artifacts across sessions. <br>\nMitigation: Install only when durable Fulcra workspaces are desired, and review workspace contents and ownership boundaries before enabling team coordination. <br>\nRisk: Optional HEARTBEAT.md entries, cron jobs, and MEMORY.md edits can cause future automated processing of team inbox data. <br>\nMitigation: Require explicit user consent before enabling automation or local memory updates, and review the exact background task or memory directive before approval. <br>\nRisk: Uploading private artifacts or transferring context between agents can expose user data to unintended team members. <br>\nMitigation: Require explicit user approval for artifact uploads and cross-agent data transfer, and verify the target team, member, and path before running Fulcra CLI commands. <br>\n\n\n## Reference(s): <br>\n- [ClawHub Skill Page](https://clawhub.ai/fulcra/skills/fulcra-agent-teams) <br>\n- [Fulcra Agent Teams CLI Reference](references/fulcra-agent-teams-cli.md) <br>\n- [Fulcra CLI Documentation](https://raw.githubusercontent.com/fulcradynamics/agent-skills/main/skills/fulcra-onboarding/references/fulcra-cli.md) <br>\n- [Open Knowledge Format Specification](https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance] <br>\n**Output Format:** [Markdown guidance with inline shell commands and path conventions] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Includes consent gates for artifact uploads, automation, and local memory updates.] <br>\n\n## Skill Version(s): <br>\n0.0.7 (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 v0.0.6: 4 files, 10234 bytes\n\nFiles: references/fulcra-agent-teams-cli.md (7550b), skill-card.md (2569b), SKILL.md (14734b), _meta.json (137b)\n\nFile v0.0.6:SKILL.md\n\n---\nname: fulcra-agent-teams\ndescription: \"Enable agents to collaborate using shared memory, team inboxes, and user artifacts via Fulcra's versioned file storage.\"\nhomepage: \"https://github.com/fulcradynamics/agent-skills\"\nlicense: \"MIT\"\nuser-invocable: true\nmetadata: { \"openclaw\": { \"emoji\": \"🤝\" } }\n---\n\n# Fulcra Agent Teams\n\nThe **primary role** of this skill is to allow agents to store generated artifacts and coordinate with other agents using shared team spaces in Fulcra's versioned file storage.\n\n## 1. Uploading User Artifacts\n\nAgents can store generated assets, binaries, or compiled dashboards created for the user. Per the OKF standard, any non-markdown files must be stored in a dedicated `artifact/` directory.\n- **Namespace:** `agent/<agent-name>/artifact/` (e.g., `agent/wazir/artifact/onboarding-dashboard.html`)\n- **Note:** Always ask for explicit user approval before uploading anything to the artifact directory.\n\n## 2. Team Creation, Joining, & Coordination (OKF Compliant)\n\nAgents can collaborate and share memory using a shared `team/<team-name>/` prefix in the Fulcra datastore. This directory structure must conform to the Open Knowledge Format (OKF).\n\n### Creating a Team\nBefore creating a new team, you MUST always check if a team with that name already exists by listing the `team/` directory or checking for a `team/<team-name>/role.md` file. Do not accidentally overwrite or recreate an existing team structure. If the team already exists, simply join it.\n\n### Joining a Team\nWhen joining a team, do not assume your role. You MUST explicitly ask the user to confirm or clarify what your specific role, duties, and identity will be on this team. Once the user clarifies your role, document it in `team/<team-name>/member/<agent-name>/role.md`.\n\nAfter joining a team, you can optionally establish a habit for checking team activity:\n- Explain to the user that teamwork and team communication can be kept going autonomously by setting up a habit to regularly check your team inbox (`team/<team-name>/member/<agent-name>/inbox/`) and team activity.\n- Ask the user if they would like to set up this optional habit (e.g., via a background heartbeat entry in `HEARTBEAT.md` or an isolated cron job).\n- Emphasize that this is definitely optional; alternatively, they can just manually remind you to do team work each time.\n- If the user consents, set up the habit immediately so you don't miss incoming messages.\n\n**SECURITY & AUTHORIZATION WARNING:** Never transfer data, context, or files between agents without explicit authorization and strict respect for data ownership boundaries. Cross-agent data transfer can leak sensitive user context to a principal who lacks authorization. Ensure you explicitly warn the user if a team coordination action involves transferring private workspace data.\n\nWithin a team's directory, the following OKF structure is used:\n- **`team/<team-name>/index.md`**: Directory listing of the team's concepts and members.\n- **`team/<team-name>/log.md`**: Chronological update history for the team namespace.\n- **`team/<team-name>/role.md`**: The team's high-level purpose, overall mission, and operational identity. Agents should populate this when a new team is created. Must include OKF YAML frontmatter.\n- **`team/<team-name>/progress.md`**: Tracks what team members have recently done and what they plan to do next. Must include OKF YAML frontmatter.\n- **`team/<team-name>/completed.md`**: A growing record of each high-level objective completed by the team. Must include OKF YAML frontmatter.\n- **`team/<team-name>/artifact/`**: Shared non-markdown output files, deliverables, or binaries created by the team.\n- **`team/<team-name>/session/`**: Team-scoped session summaries recording discrete spates of work or collaboration.\n- **`team/<team-name>/task/`**: Team-scoped tracking for long-running, multi-session tasks.\n- **`team/<team-name>/knowledge/`**: A flexible, open-ended OKF knowledge base where team members can store, organize, and retrieve any domain knowledge, rules, or reference material useful for the team's shared objectives.\n- **`team/<team-name>/member/<agent-name>/role.md`**: The specific role, duties, and identity of the member within the team (e.g., manager delegating tasks vs. worker receiving tasks). Created when an agent joins a team.\n- **`team/<team-name>/member/<agent-name>/progress.md`**: A progress report for the specific team member. This is vital for maintaining context across isolated cron runs or background threads. It tracks what this specific agent is currently doing for the team, how to handle incoming tasks, and their immediate next steps. Must include OKF YAML frontmatter.\n- **`team/<team-name>/member/<agent-name>/inbox/`**: A drop-zone where other agents or users can place tasks, messages, or context for a specific agent.\n- **`team/<team-name>/member/<agent-name>/archive/`**: Where an agent moves its inbox messages once they have been read and processed.\n\n**IMPORTANT OKF EFFICIENCY DIRECTIVE:** While OKF compliance is required for team spaces, it must not become a burden.\n- **DO NOT** attempt to index or log every individual transient file or message within `member/<agent-name>/inbox/` or `member/<agent-name>/archive/`.\n- In the team's `index.md`, simply list the member directories or the `inbox/` directory as a whole with a high-level description (e.g., \"Contains unread coordination messages for the team\").\n- Keep the `index.md` and `log.md` focused strictly on major team milestones, high-level objectives, or structural additions (like a new member joining or a major artifact being published).\n\n### Checking for Team File Changes\nTo stay aware of recent team activity across many files and subdirectories without exhaustively listing them all, agents can use the Fulcra API's `data-updates` command (e.g., `uv tool run fulcra-api data-updates \"1 day\"`). This will return a summary of all uploaded files that changed recently, allowing agents to quickly identify which specific team files (if any) they should read to catch up on work they would not otherwise necessarily check.\n\n### The Inbox Lifecycle\n\nWhen collaborating, agents write markdown messages to one another's inboxes. To ensure messages sort chronologically and identify the sender, agents should ideally name messages using the convention: `YYYYMMDD-HHMMSS_<sender-name>_<short-topic>.md` (e.g., `20260608-232500_treecle_onboarding-status.md`).\n\nHowever, to accommodate users easily dropping manual tasks or context into an inbox, files placed here DO NOT strictly require this naming convention (e.g., a user might just drop `review-this.md`).\n\n**Thread Continuity:** When replying to a message or posting an update about a task, you MUST reuse the exact same `<short-topic>` component from the original message (or the base filename if it was manually dropped). This allows agents and users to track conversations and tasks across multiple inbox exchanges.\n\nWhen the target agent processes its inbox, it must first upload the message to its `archive/` directory, and then delete the original file from its `inbox/`. Because Fulcra's file system is versioned, it automatically keeps a perfect audit trail of when the file was created in the inbox and when it was completed (deleted).\n\nIf the original file name in the inbox does not already start with a timestamp, the processing agent MUST prepend a timestamp (`YYYYMMDD-HHMMSS_`) to the filename when saving it to the `archive/` directory. This ensures the archive remains chronologically sortable even for files manually dropped by users.\n\n### 3. Team Session and Task Tracking\n\nJust as agents maintain personal memory using the `fulcradynamics/agent-skills/fulcra-memory` skill, teams must track their collaborative work inside the shared team namespace.\n\n**Session Summaries:**\nWhen an agent completes a discrete block of work related to the team (e.g., resolving a team inbox message), the agent writes a session summary to the `team/<team-name>/session/` directory.\n- **Filename Convention:** Prefix the file with a timestamp (`YYYYMMDD-HHMMSS`) followed by an underscore, the agent's name, and a short subject (e.g., `team/research/session/20260623-180530_treecle_setup-dashboard.md`).\n- These files serve as targeted, easily-retrievable context. They should capture decisions made, important links, user preferences discovered, and the final state of the session.\n- Ensure the `session/` directory is listed in the top-level `index.md` with a high-level description. You do not need to index every individual session file in `index.md`.\n\n**Long-Running Tasks:**\nFor larger, ongoing objectives spanning multiple messages or sessions, track state in the `team/<team-name>/task/` directory.\n- **Filename Convention:** Name the file directly after the task (e.g., `team/research/task/setup-dashboard.md`). DO NOT prefix it with a timestamp.\n- These files track the overall purpose, current state, and result of the task. They should be updated periodically as work progresses.\n- **Task Updates:** When updating a task file, agents MUST append an entry documenting what was done, explicitly including the name of the agent doing the work, the date/time it was done, and relative links to any task-related files (such as newly generated artifacts or session summaries).\n- Task files MUST be included in the `team/<team-name>/task/index.md` file, which should list all active and completed tasks in the directory.\n\n**Team Knowledge Base:**\nThe `team/<team-name>/knowledge/` subdirectory allows teams to collaboratively build a shared repository of information. Because different teams and missions have unique requirements, this structure is deliberately open-ended.\n- Use OKF structuring (like `index.md` files) to organize topics, domains, or standard operating procedures.\n- Any team member can contribute to or retrieve from the knowledge base, ensuring all agents have access to the same foundational context without limiting the types of knowledge that can be stored.\n- Like other major subdirectories, `knowledge/` should be listed in the top-level team `index.md`.\n\n## 4. Completing Team Work (Updating State)\n\nWhenever an agent finishes processing a team task, inbox message, or background action (whether triggered by a chat, heartbeat, or cron job), they MUST synchronize their state with the rest of the team on Fulcra.\n\nBefore concluding the task or replying `HEARTBEAT_OK`, in addition to following other fulcra-agent-teams processes you must explicitly update:\n1. **Your Member Progress File:** Add an entry to `team/<team-name>/member/<agent-name>/progress.md` logging exactly what you just did and what your next steps are.\n2. **The Team Progress File:** If your work advanced a high-level team goal, append a brief summary to `team/<team-name>/progress.md`.\n3. **Task Files:** If you worked on a specific tracked task, append your update to the relevant `team/<team-name>/task/<task-name>.md` file.\n\nThis strict update requirement ensures that other agents (or your future self in an isolated cron job) always wake up to a perfectly accurate state.\n\n## 5. Automated Operations (Heartbeats & Cron)\n\nAgents can optionally check their inbox or perform team tasks automatically using their periodic background heartbeat (`HEARTBEAT.md`) or isolated cron jobs.\n\n**Background Heartbeats:**\n- **Require Consent:** You must explicitly ask the user for permission before enabling automated background inbox checks.\n- If the user approves, add a task to your local workspace's `HEARTBEAT.md` file to periodically check your inbox at `team/<team-name>/member/<agent-name>/inbox/`.\n- Ensure you log any new tasks or messages discovered during the heartbeat into your local daily memory logs, and process the message using the Inbox Lifecycle (archiving and deleting from the inbox).\n\n**Isolated Cron Jobs:**\n- **Require Consent:** You must explicitly ask the user for permission before creating any cron jobs for team tasks.\n- When setting up an isolated cron job for a team task (such as periodically checking your inbox), the `payload.message` (or `payload.text`) MUST explicitly instruct the agent to read the necessary context. \n- **Rule:** The cron payload must say something like: \"You are waking up to check your inbox at `team/<team-name>/member/<agent-name>/inbox/` and process new tasks. Before starting, you MUST read `team/<team-name>/progress.md`, `team/<team-name>/role.md`, your specific `team/<team-name>/member/<agent-name>/role.md`, and your specific `team/<team-name>/member/<agent-name>/progress.md` to establish context.\"\n- Ensure any new tasks or messages discovered during the cron run are processed using the Inbox Lifecycle (archiving and deleting from the inbox).\n- This prevents agents from attempting to work in isolated sessions without knowing current team states or priorities.\n\n## 6. Agent Local Memory Integration (MEMORY.md)\n\nTo ensure agents never lose track of their team responsibilities across main sessions and chats, an agent joining a team MUST update its own local long-term memory (`~/.openclaw/workspace/MEMORY.md`).\n- **Require Consent:** You must explicitly ask the user for permission before modifying your `MEMORY.md` file.\n- Once approved, add a clear directive to your `MEMORY.md` stating: \"Before starting any teamwork or processing team inbox messages (whether in chat, heartbeat, or cron), ALWAYS check the latest status in `team/<team-name>/progress.md`, the overall `team/<team-name>/role.md`, relevant `task/` files, your specific `team/<team-name>/member/<agent-name>/role.md`, and your specific `team/<team-name>/member/<agent-name>/progress.md`.\"\n- This guarantees the agent will organically recall to pull the latest Fulcra state before acting on team requests.\n\n## Workflow\n\nTo perform team operations, agents must interact with the Fulcra CLI. \n\nFor general information about the Fulcra File Store and the required Open Knowledge Format (OKF) standard, please refer to the main Fulcra CLI documentation found in the `fulcradynamics/agent-skills/fulcra-onboarding` skill, or read the full OKF specification directly:\n- [https://raw.githubusercontent.com/fulcradynamics/agent-skills/main/skills/fulcra-onboarding/references/fulcra-cli.md](https://raw.githubusercontent.com/fulcradynamics/agent-skills/main/skills/fulcra-onboarding/references/fulcra-cli.md)\n- [https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md](https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md)\n\nSee the reference documentation for the exact commands needed to manage artifacts and inbox messaging:\n- Read `references/fulcra-agent-teams-cli.md` for exact file management and CLI execution steps.\n\nFile v0.0.6:_meta.json\n\n{\n  \"ownerId\": \"kn72pt2cb5f9nskgc9k2ddecxs87547j\",\n  \"slug\": \"fulcra-agent-teams\",\n  \"version\": \"0.0.6\",\n  \"publishedAt\": 1783034959189\n}\n\nFile v0.0.6:references/fulcra-agent-teams-cli.md\n\n---\nname: fulcra-agent-teams-cli\ndescription: \"CLI command references for executing artifact uploads and team inbox operations with Fulcra.\"\n---\n\n# Fulcra Agent Teams CLI Reference\n\nThis reference dictates the exact shell commands required to execute the `fulcra-agent-teams` skill's operations. Ensure all CLI operations run in the agent's workspace.\n\n## Authentication Note\nIf you need to authenticate to Fulcra before running these commands, you must use the non-blocking two-step login process to prevent the CLI from hanging:\n1. `uv tool run fulcra-api auth login --get-auth-url` (present URL and code to user)\n2. `uv tool run fulcra-api auth login --device-code <DEVICE_CODE> --poll-timeout=5` (after user finishes flow)\n\n## 1. Checking Recent Team File Changes\n\nTo quickly check for recent updates across a team's namespaces without listing individual directories:\n\n```bash\n# Get a summary of files changed in the last 1 day\nuv tool run fulcra-api data-updates \"1 day\"\n\n# Example output:\n# {\n#   \"data_types\": {},\n#   \"file_changes\": [\n#     {\n#       \"full_name\": \"/team/first-olympiad/progress.md\",\n#       \"uploaded_at\": \"2026-07-01T21:23:28.690719Z\",\n#       \"state\": \"uploaded\",\n#       \"...\": \"...\"\n#     },\n#     {\n#       \"full_name\": \"/team/first-olympiad/task/setup-dashboard.md\",\n#       \"uploaded_at\": \"2026-07-01T21:23:28.690719Z\",\n#       \"state\": \"uploaded\",\n#       \"...\": \"...\"\n#     }\n#   ]\n# }\n```\n\n*Note: The `file_changes` key is a list of file metadata objects. You can extract the `full_name` from each to see the file paths. If the summary shows that specific team files were changed, you can then read those specific files to update your context.*\n\n## 2. Uploading User Artifacts\n\nWhen an agent generates a file (like an HTML dashboard, an image, or a report), and the user explicitly approves saving it to their Fulcra account, upload it to the `artifact/` subdirectory.\n\n```bash\n# Replace <agent_name> with the agent's name, and <artifact_name> with the file's name\nuv tool run fulcra-api file upload /path/to/local/file \"agent/<agent_name>/artifact/<artifact_name>\"\n```\n\n## 2. Team Coordination (Inbox & Archive)\n\nAgents can coordinate by writing to and reading from team namespaces.\n\n**Message Naming Convention:**\nMessages must follow the format `YYYYMMDD-HHMMSS_<sender-name>_<short-topic>.md`. Use underscores between the three main components so they can be reliably parsed.\n*Note: When replying to a message or providing a status update, always reuse the exact same `<short-topic>` as the original message to maintain thread continuity.*\n\n**Step A: Sending a message to a teammate's inbox**\n```bash\n# Upload a local markdown file to the target agent's inbox\nuv tool run fulcra-api file upload /tmp/message.md \"team/<team_name>/member/<target_agent_name>/inbox/20260608-232500_wazir_status-update.md\"\n```\n\n**Step B: Checking your inbox**\n```bash\n# List files in your agent's inbox\nuv tool run fulcra-api file list \"team/<team_name>/member/<your_agent_name>/inbox/\"\n```\n\n**Step C: Processing and Archiving a message**\nOnce you have downloaded and read a message from your inbox, move it to the archive. If the file was manually dropped and lacks a timestamp, **you must prepend one** (`YYYYMMDD-HHMMSS_`) when saving it to `archive/`.\n\n```bash\n# 1. Download to read (if you haven't already)\nuv tool run fulcra-api file download \"team/<team_name>/member/<your_agent_name>/inbox/20260608-232500_wazir_status-update.md\" /tmp/20260608-232500_wazir_status-update.md\n\n# 2. Upload it to your archive directory\nuv tool run fulcra-api file upload /tmp/20260608-232500_wazir_status-update.md \"team/<team_name>/member/<your_agent_name>/archive/20260608-232500_wazir_status-update.md\"\n\n# 3. Verify archival succeeded before deletion!\nuv tool run fulcra-api file stat \"team/<team_name>/member/<your_agent_name>/archive/20260608-232500_wazir_status-update.md\"\n\n# 4. Delete it from the inbox to clear it (only if step 3 succeeded)\nuv tool run fulcra-api file delete \"team/<team_name>/member/<your_agent_name>/inbox/20260608-232500_wazir_status-update.md\"\n```\n\n## 3. Team Activity Tracking (OKF Compliant)\n\nAgents can update shared files to track the team's high-level progress and completed objectives. Ensure all markdown files contain OKF YAML frontmatter, and that `log.md` and `index.md` are updated when appropriate.\n\n**Step A: Updating Team Progress**\nTo update the `progress.md` file (which stores what the team members have recently done and what they plan to do next):\n```bash\n# 1. Download the current progress file\nuv tool run fulcra-api file download \"team/<team_name>/progress.md\" /tmp/team_progress.md || touch /tmp/team_progress.md\n\n# 2. Edit /tmp/team_progress.md locally to reflect the latest plans and recent work. \n# Make sure it has OKF frontmatter:\n# ---\n# type: Progress Report\n# title: Team Progress\n# ---\n\n# 3. Upload the updated file back to Fulcra\nuv tool run fulcra-api file upload /tmp/team_progress.md \"team/<team_name>/progress.md\"\n\n# 4. Also append an update entry to log.md\nDATE=$(date -u +\"%Y-%m-%d\")\necho \"## $DATE\" > /tmp/log_update.md\necho \"* **Update**: <agent_name> updated team progress.\" >> /tmp/log_update.md\n# (In practice, download log.md, append the update under the correct date, and re-upload)\n```\n\n**Step B: Recording Completed Objectives**\nTo add a newly completed high-level objective to `completed.md` (which should generally only grow):\n```bash\n# 1. Download the current completed file\nuv tool run fulcra-api file download \"team/<team_name>/completed.md\" /tmp/team_completed.md || touch /tmp/team_completed.md\n\n# 2. Append the new objective (ensure OKF frontmatter exists at the top of the file)\necho \"- [$(date +%Y-%m-%d)] <Objective summary>\" >> /tmp/team_completed.md\n\n# 3. Upload the updated file back to Fulcra\nuv tool run fulcra-api file upload /tmp/team_completed.md \"team/<team_name>/completed.md\"\n```\n\n**Step C: Syncing Team and Member Roles & Progress**\nTo ensure the team and its members understand their purpose and current context, maintain `role.md` and member `progress.md` files (with proper OKF frontmatter).\n```bash\n# Update the overall team role\nuv tool run fulcra-api file upload /tmp/team-role.md \"team/<team_name>/role.md\"\n\n# Update your specific agent's role within the team\nuv tool run fulcra-api file upload /tmp/member-role.md \"team/<team_name>/member/<your_agent_name>/role.md\"\n\n# Update your specific agent's progress (critical for isolated background jobs)\nuv tool run fulcra-api file upload /tmp/member-progress.md \"team/<team_name>/member/<your_agent_name>/progress.md\"\n```\n\n## 4. Team Session and Task Tracking\n\nWhen completing a discrete block of work or tracking a long-running project within the team, upload summaries to the team namespace rather than your personal memory namespace.\n\n**Step A: Uploading a Session Summary**\nWhen a team session concludes, create a concise markdown summary (with `type: Session Summary` frontmatter) and upload it.\n```bash\n# Filename convention: YYYYMMDD-HHMMSS_<agent-name>_<subject>.md\nuv tool run fulcra-api file upload /tmp/session-summary.md \"team/<team_name>/session/20260623-180530_treecle_setup-dashboard.md\"\n```\n\n**Step B: Updating a Task Tracker**\nFor ongoing team objectives, update a task tracker (with `type: Task` frontmatter) and its index.\n```bash\n# Filename convention: <task-name>.md (No timestamp)\nuv tool run fulcra-api file upload /tmp/task-status.md \"team/<team_name>/task/setup-dashboard.md\"\nuv tool run fulcra-api file upload /tmp/task-index.md \"team/<team_name>/task/index.md\"\n```\n\nFile v0.0.6:skill-card.md\n\n## Description: <br>\nEnable agents to collaborate using shared memory, team inboxes, and user artifacts via Fulcra's versioned file storage. <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 developers use this skill to coordinate agent teams through Fulcra shared storage, including artifact uploads, team inbox messaging, and shared progress and task records. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Shared team storage can persist or expose user context, generated files, or workspace content to other agents. <br>\nMitigation: Share content only after explicit authorization and only with agents that are authorized to receive it. <br>\nRisk: Optional heartbeats or cron jobs can repeatedly read, write, archive, or delete team files beyond the user's intent. <br>\nMitigation: Before enabling automation, define the team name, agent name, frequency, duration, and allowed file actions. <br>\nRisk: Uploaded artifacts or team messages may contain secrets or private workspace data. <br>\nMitigation: Review content before upload and avoid storing secrets or private material unless every receiving agent is authorized. <br>\n\n\n## Reference(s): <br>\n- [Fulcra Agent Teams on ClawHub](https://clawhub.ai/fulcra/skills/fulcra-agent-teams) <br>\n- [Fulcra Agent Teams CLI Reference](references/fulcra-agent-teams-cli.md) <br>\n- [Fulcra CLI Documentation](https://raw.githubusercontent.com/fulcradynamics/agent-skills/main/skills/fulcra-onboarding/references/fulcra-cli.md) <br>\n- [Open Knowledge Format Specification](https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Markdown, Files, Shell commands, Configuration, Guidance] <br>\n**Output Format:** [Markdown guidance with inline shell commands and Fulcra file paths] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May create or update Fulcra-backed team, member, inbox, archive, task, session, knowledge, and artifact files when authorized.] <br>\n\n## Skill Version(s): <br>\n0.0.6 (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 v0.0.5: 4 files, 10176 bytes\n\nFiles: references/fulcra-agent-teams-cli.md (7550b), skill-card.md (2481b), SKILL.md (14574b), _meta.json (137b)\n\nFile v0.0.5:SKILL.md\n\n---\nname: fulcra-agent-teams\ndescription: \"Enable agents to collaborate using shared memory, team inboxes, and user artifacts via Fulcra's versioned file storage.\"\nhomepage: \"https://github.com/fulcradynamics/agent-skills\"\nlicense: \"MIT\"\nuser-invocable: true\nmetadata: { \"openclaw\": { \"emoji\": \"🤝\" } }\n---\n\n# Fulcra Agent Teams\n\nThe **primary role** of this skill is to allow agents to store generated artifacts and coordinate with other agents using shared team spaces in Fulcra's versioned file storage.\n\n## 1. Uploading User Artifacts\n\nAgents can store generated assets, binaries, or compiled dashboards created for the user. Per the OKF standard, any non-markdown files must be stored in a dedicated `artifact/` directory.\n- **Namespace:** `agent/<agent-name>/artifact/` (e.g., `agent/wazir/artifact/onboarding-dashboard.html`)\n- **Note:** Always ask for explicit user approval before uploading anything to the artifact directory.\n\n## 2. Team Creation, Joining, & Coordination (OKF Compliant)\n\nAgents can collaborate and share memory using a shared `team/<team-name>/` prefix in the Fulcra datastore. This directory structure must conform to the Open Knowledge Format (OKF).\n\n### Creating a Team\nBefore creating a new team, you MUST always check if a team with that name already exists by listing the `team/` directory or checking for a `team/<team-name>/role.md` file. Do not accidentally overwrite or recreate an existing team structure. If the team already exists, simply join it.\n\n### Joining a Team\nWhen joining a team, do not assume your role. You MUST explicitly ask the user to confirm or clarify what your specific role, duties, and identity will be on this team. Once the user clarifies your role, document it in `team/<team-name>/member/<agent-name>/role.md`.\n\nAfter joining a team, you must establish a habit for checking team activity:\n- Tell the user that to participate effectively, you need to regularly check your team inbox (`team/<team-name>/member/<agent-name>/inbox/`) and team activity.\n- Ask the user for permission to set up a habit to do this (e.g., via a background heartbeat entry in `HEARTBEAT.md`, an isolated cron job, or a polling loop if applicable).\n- If the user consents, set up the habit immediately so you don't miss incoming messages.\n\n**SECURITY & AUTHORIZATION WARNING:** Never transfer data, context, or files between agents without explicit authorization and strict respect for data ownership boundaries. Cross-agent data transfer can leak sensitive user context to a principal who lacks authorization. Ensure you explicitly warn the user if a team coordination action involves transferring private workspace data.\n\nWithin a team's directory, the following OKF structure is used:\n- **`team/<team-name>/index.md`**: Directory listing of the team's concepts and members.\n- **`team/<team-name>/log.md`**: Chronological update history for the team namespace.\n- **`team/<team-name>/role.md`**: The team's high-level purpose, overall mission, and operational identity. Agents should populate this when a new team is created. Must include OKF YAML frontmatter.\n- **`team/<team-name>/progress.md`**: Tracks what team members have recently done and what they plan to do next. Must include OKF YAML frontmatter.\n- **`team/<team-name>/completed.md`**: A growing record of each high-level objective completed by the team. Must include OKF YAML frontmatter.\n- **`team/<team-name>/artifact/`**: Shared non-markdown output files, deliverables, or binaries created by the team.\n- **`team/<team-name>/session/`**: Team-scoped session summaries recording discrete spates of work or collaboration.\n- **`team/<team-name>/task/`**: Team-scoped tracking for long-running, multi-session tasks.\n- **`team/<team-name>/knowledge/`**: A flexible, open-ended OKF knowledge base where team members can store, organize, and retrieve any domain knowledge, rules, or reference material useful for the team's shared objectives.\n- **`team/<team-name>/member/<agent-name>/role.md`**: The specific role, duties, and identity of the member within the team (e.g., manager delegating tasks vs. worker receiving tasks). Created when an agent joins a team.\n- **`team/<team-name>/member/<agent-name>/progress.md`**: A progress report for the specific team member. This is vital for maintaining context across isolated cron runs or background threads. It tracks what this specific agent is currently doing for the team, how to handle incoming tasks, and their immediate next steps. Must include OKF YAML frontmatter.\n- **`team/<team-name>/member/<agent-name>/inbox/`**: A drop-zone where other agents or users can place tasks, messages, or context for a specific agent.\n- **`team/<team-name>/member/<agent-name>/archive/`**: Where an agent moves its inbox messages once they have been read and processed.\n\n**IMPORTANT OKF EFFICIENCY DIRECTIVE:** While OKF compliance is required for team spaces, it must not become a burden.\n- **DO NOT** attempt to index or log every individual transient file or message within `member/<agent-name>/inbox/` or `member/<agent-name>/archive/`.\n- In the team's `index.md`, simply list the member directories or the `inbox/` directory as a whole with a high-level description (e.g., \"Contains unread coordination messages for the team\").\n- Keep the `index.md` and `log.md` focused strictly on major team milestones, high-level objectives, or structural additions (like a new member joining or a major artifact being published).\n\n### Checking for Team File Changes\nTo stay aware of recent team activity across many files and subdirectories without exhaustively listing them all, agents can use the Fulcra API's `data-updates` command (e.g., `uv tool run fulcra-api data-updates \"1 day\"`). This will return a summary of all uploaded files that changed recently, allowing agents to quickly identify which specific team files (if any) they should read to catch up on work they would not otherwise necessarily check.\n\n### The Inbox Lifecycle\n\nWhen collaborating, agents write markdown messages to one another's inboxes. To ensure messages sort chronologically and identify the sender, agents should ideally name messages using the convention: `YYYYMMDD-HHMMSS_<sender-name>_<short-topic>.md` (e.g., `20260608-232500_treecle_onboarding-status.md`).\n\nHowever, to accommodate users easily dropping manual tasks or context into an inbox, files placed here DO NOT strictly require this naming convention (e.g., a user might just drop `review-this.md`).\n\n**Thread Continuity:** When replying to a message or posting an update about a task, you MUST reuse the exact same `<short-topic>` component from the original message (or the base filename if it was manually dropped). This allows agents and users to track conversations and tasks across multiple inbox exchanges.\n\nWhen the target agent processes its inbox, it must first upload the message to its `archive/` directory, and then delete the original file from its `inbox/`. Because Fulcra's file system is versioned, it automatically keeps a perfect audit trail of when the file was created in the inbox and when it was completed (deleted).\n\nIf the original file name in the inbox does not already start with a timestamp, the processing agent MUST prepend a timestamp (`YYYYMMDD-HHMMSS_`) to the filename when saving it to the `archive/` directory. This ensures the archive remains chronologically sortable even for files manually dropped by users.\n\n### 3. Team Session and Task Tracking\n\nJust as agents maintain personal memory using the `fulcradynamics/agent-skills/fulcra-memory` skill, teams must track their collaborative work inside the shared team namespace.\n\n**Session Summaries:**\nWhen an agent completes a discrete block of work related to the team (e.g., resolving a team inbox message), the agent writes a session summary to the `team/<team-name>/session/` directory.\n- **Filename Convention:** Prefix the file with a timestamp (`YYYYMMDD-HHMMSS`) followed by an underscore, the agent's name, and a short subject (e.g., `team/research/session/20260623-180530_treecle_setup-dashboard.md`).\n- These files serve as targeted, easily-retrievable context. They should capture decisions made, important links, user preferences discovered, and the final state of the session.\n- Ensure the `session/` directory is listed in the top-level `index.md` with a high-level description. You do not need to index every individual session file in `index.md`.\n\n**Long-Running Tasks:**\nFor larger, ongoing objectives spanning multiple messages or sessions, track state in the `team/<team-name>/task/` directory.\n- **Filename Convention:** Name the file directly after the task (e.g., `team/research/task/setup-dashboard.md`). DO NOT prefix it with a timestamp.\n- These files track the overall purpose, current state, and result of the task. They should be updated periodically as work progresses.\n- **Task Updates:** When updating a task file, agents MUST append an entry documenting what was done, explicitly including the name of the agent doing the work, the date/time it was done, and relative links to any task-related files (such as newly generated artifacts or session summaries).\n- Task files MUST be included in the `team/<team-name>/task/index.md` file, which should list all active and completed tasks in the directory.\n\n**Team Knowledge Base:**\nThe `team/<team-name>/knowledge/` subdirectory allows teams to collaboratively build a shared repository of information. Because different teams and missions have unique requirements, this structure is deliberately open-ended.\n- Use OKF structuring (like `index.md` files) to organize topics, domains, or standard operating procedures.\n- Any team member can contribute to or retrieve from the knowledge base, ensuring all agents have access to the same foundational context without limiting the types of knowledge that can be stored.\n- Like other major subdirectories, `knowledge/` should be listed in the top-level team `index.md`.\n\n## 4. Completing Team Work (Updating State)\n\nWhenever an agent finishes processing a team task, inbox message, or background action (whether triggered by a chat, heartbeat, or cron job), they MUST synchronize their state with the rest of the team on Fulcra.\n\nBefore concluding the task or replying `HEARTBEAT_OK`, in addition to following other fulcra-agent-teams processes you must explicitly update:\n1. **Your Member Progress File:** Add an entry to `team/<team-name>/member/<agent-name>/progress.md` logging exactly what you just did and what your next steps are.\n2. **The Team Progress File:** If your work advanced a high-level team goal, append a brief summary to `team/<team-name>/progress.md`.\n3. **Task Files:** If you worked on a specific tracked task, append your update to the relevant `team/<team-name>/task/<task-name>.md` file.\n\nThis strict update requirement ensures that other agents (or your future self in an isolated cron job) always wake up to a perfectly accurate state.\n\n## 5. Automated Operations (Heartbeats & Cron)\n\nAgents can optionally check their inbox or perform team tasks automatically using their periodic background heartbeat (`HEARTBEAT.md`) or isolated cron jobs.\n\n**Background Heartbeats:**\n- **Require Consent:** You must explicitly ask the user for permission before enabling automated background inbox checks.\n- If the user approves, add a task to your local workspace's `HEARTBEAT.md` file to periodically check your inbox at `team/<team-name>/member/<agent-name>/inbox/`.\n- Ensure you log any new tasks or messages discovered during the heartbeat into your local daily memory logs, and process the message using the Inbox Lifecycle (archiving and deleting from the inbox).\n\n**Isolated Cron Jobs:**\n- **Require Consent:** You must explicitly ask the user for permission before creating any cron jobs for team tasks.\n- When setting up an isolated cron job for a team task (such as periodically checking your inbox), the `payload.message` (or `payload.text`) MUST explicitly instruct the agent to read the necessary context. \n- **Rule:** The cron payload must say something like: \"You are waking up to check your inbox at `team/<team-name>/member/<agent-name>/inbox/` and process new tasks. Before starting, you MUST read `team/<team-name>/progress.md`, `team/<team-name>/role.md`, your specific `team/<team-name>/member/<agent-name>/role.md`, and your specific `team/<team-name>/member/<agent-name>/progress.md` to establish context.\"\n- Ensure any new tasks or messages discovered during the cron run are processed using the Inbox Lifecycle (archiving and deleting from the inbox).\n- This prevents agents from attempting to work in isolated sessions without knowing current team states or priorities.\n\n## 6. Agent Local Memory Integration (MEMORY.md)\n\nTo ensure agents never lose track of their team responsibilities across main sessions and chats, an agent joining a team MUST update its own local long-term memory (`~/.openclaw/workspace/MEMORY.md`).\n- **Require Consent:** You must explicitly ask the user for permission before modifying your `MEMORY.md` file.\n- Once approved, add a clear directive to your `MEMORY.md` stating: \"Before starting any teamwork or processing team inbox messages (whether in chat, heartbeat, or cron), ALWAYS check the latest status in `team/<team-name>/progress.md`, the overall `team/<team-name>/role.md`, relevant `task/` files, your specific `team/<team-name>/member/<agent-name>/role.md`, and your specific `team/<team-name>/member/<agent-name>/progress.md`.\"\n- This guarantees the agent will organically recall to pull the latest Fulcra state before acting on team requests.\n\n## Workflow\n\nTo perform team operations, agents must interact with the Fulcra CLI. \n\nFor general information about the Fulcra File Store and the required Open Knowledge Format (OKF) standard, please refer to the main Fulcra CLI documentation found in the `fulcradynamics/agent-skills/fulcra-onboarding` skill, or read the full OKF specification directly:\n- [https://raw.githubusercontent.com/fulcradynamics/agent-skills/main/skills/fulcra-onboarding/references/fulcra-cli.md](https://raw.githubusercontent.com/fulcradynamics/agent-skills/main/skills/fulcra-onboarding/references/fulcra-cli.md)\n- [https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md](https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md)\n\nSee the reference documentation for the exact commands needed to manage artifacts and inbox messaging:\n- Read `references/fulcra-agent-teams-cli.md` for exact file management and CLI execution steps.\n\nFile v0.0.5:_meta.json\n\n{\n  \"ownerId\": \"kn72pt2cb5f9nskgc9k2ddecxs87547j\",\n  \"slug\": \"fulcra-agent-teams\",\n  \"version\": \"0.0.5\",\n  \"publishedAt\": 1782943617304\n}\n\nFile v0.0.5:references/fulcra-agent-teams-cli.md\n\n---\nname: fulcra-agent-teams-cli\ndescription: \"CLI command references for executing artifact uploads and team inbox operations with Fulcra.\"\n---\n\n# Fulcra Agent Teams CLI Reference\n\nThis reference dictates the exact shell commands required to execute the `fulcra-agent-teams` skill's operations. Ensure all CLI operations run in the agent's workspace.\n\n## Authentication Note\nIf you need to authenticate to Fulcra before running these commands, you must use the non-blocking two-step login process to prevent the CLI from hanging:\n1. `uv tool run fulcra-api auth login --get-auth-url` (present URL and code to user)\n2. `uv tool run fulcra-api auth login --device-code <DEVICE_CODE> --poll-timeout=5` (after user finishes flow)\n\n## 1. Checking Recent Team File Changes\n\nTo quickly check for recent updates across a team's namespaces without listing individual directories:\n\n```bash\n# Get a summary of files changed in the last 1 day\nuv tool run fulcra-api data-updates \"1 day\"\n\n# Example output:\n# {\n#   \"data_types\": {},\n#   \"file_changes\": [\n#     {\n#       \"full_name\": \"/team/first-olympiad/progress.md\",\n#       \"uploaded_at\": \"2026-07-01T21:23:28.690719Z\",\n#       \"state\": \"uploaded\",\n#       \"...\": \"...\"\n#     },\n#     {\n#       \"full_name\": \"/team/first-olympiad/task/setup-dashboard.md\",\n#       \"uploaded_at\": \"2026-07-01T21:23:28.690719Z\",\n#       \"state\": \"uploaded\",\n#       \"...\": \"...\"\n#     }\n#   ]\n# }\n```\n\n*Note: The `file_changes` key is a list of file metadata objects. You can extract the `full_name` from each to see the file paths. If the summary shows that specific team files were changed, you can then read those specific files to update your context.*\n\n## 2. Uploading User Artifacts\n\nWhen an agent generates a file (like an HTML dashboard, an image, or a report), and the user explicitly approves saving it to their Fulcra account, upload it to the `artifact/` subdirectory.\n\n```bash\n# Replace <agent_name> with the agent's name, and <artifact_name> with the file's name\nuv tool run fulcra-api file upload /path/to/local/file \"agent/<agent_name>/artifact/<artifact_name>\"\n```\n\n## 2. Team Coordination (Inbox & Archive)\n\nAgents can coordinate by writing to and reading from team namespaces.\n\n**Message Naming Convention:**\nMessages must follow the format `YYYYMMDD-HHMMSS_<sender-name>_<short-topic>.md`. Use underscores between the three main components so they can be reliably parsed.\n*Note: When replying to a message or providing a status update, always reuse the exact same `<short-topic>` as the original message to maintain thread continuity.*\n\n**Step A: Sending a message to a teammate's inbox**\n```bash\n# Upload a local markdown file to the target agent's inbox\nuv tool run fulcra-api file upload /tmp/message.md \"team/<team_name>/member/<target_agent_name>/inbox/20260608-232500_wazir_status-update.md\"\n```\n\n**Step B: Checking your inbox**\n```bash\n# List files in your agent's inbox\nuv tool run fulcra-api file list \"team/<team_name>/member/<your_agent_name>/inbox/\"\n```\n\n**Step C: Processing and Archiving a message**\nOnce you have downloaded and read a message from your inbox, move it to the archive. If the file was manually dropped and lacks a timestamp, **you must prepend one** (`YYYYMMDD-HHMMSS_`) when saving it to `archive/`.\n\n```bash\n# 1. Download to read (if you haven't already)\nuv tool run fulcra-api file download \"team/<team_name>/member/<your_agent_name>/inbox/20260608-232500_wazir_status-update.md\" /tmp/20260608-232500_wazir_status-update.md\n\n# 2. Upload it to your archive directory\nuv tool run fulcra-api file upload /tmp/20260608-232500_wazir_status-update.md \"team/<team_name>/member/<your_agent_name>/archive/20260608-232500_wazir_status-update.md\"\n\n# 3. Verify archival succeeded before deletion!\nuv tool run fulcra-api file stat \"team/<team_name>/member/<your_agent_name>/archive/20260608-232500_wazir_status-update.md\"\n\n# 4. Delete it from the inbox to clear it (only if step 3 succeeded)\nuv tool run fulcra-api file delete \"team/<team_name>/member/<your_agent_name>/inbox/20260608-232500_wazir_status-update.md\"\n```\n\n## 3. Team Activity Tracking (OKF Compliant)\n\nAgents can update shared files to track the team's high-level progress and completed objectives. Ensure all markdown files contain OKF YAML frontmatter, and that `log.md` and `index.md` are updated when appropriate.\n\n**Step A: Updating Team Progress**\nTo update the `progress.md` file (which stores what the team members have recently done and what they plan to do next):\n```bash\n# 1. Download the current progress file\nuv tool run fulcra-api file download \"team/<team_name>/progress.md\" /tmp/team_progress.md || touch /tmp/team_progress.md\n\n# 2. Edit /tmp/team_progress.md locally to reflect the latest plans and recent work. \n# Make sure it has OKF frontmatter:\n# ---\n# type: Progress Report\n# title: Team Progress\n# ---\n\n# 3. Upload the updated file back to Fulcra\nuv tool run fulcra-api file upload /tmp/team_progress.md \"team/<team_name>/progress.md\"\n\n# 4. Also append an update entry to log.md\nDATE=$(date -u +\"%Y-%m-%d\")\necho \"## $DATE\" > /tmp/log_update.md\necho \"* **Update**: <agent_name> updated team progress.\" >> /tmp/log_update.md\n# (In practice, download log.md, append the update under the correct date, and re-upload)\n```\n\n**Step B: Recording Completed Objectives**\nTo add a newly completed high-level objective to `completed.md` (which should generally only grow):\n```bash\n# 1. Download the current completed file\nuv tool run fulcra-api file download \"team/<team_name>/completed.md\" /tmp/team_completed.md || touch /tmp/team_completed.md\n\n# 2. Append the new objective (ensure OKF frontmatter exists at the top of the file)\necho \"- [$(date +%Y-%m-%d)] <Objective summary>\" >> /tmp/team_completed.md\n\n# 3. Upload the updated file back to Fulcra\nuv tool run fulcra-api file upload /tmp/team_completed.md \"team/<team_name>/completed.md\"\n```\n\n**Step C: Syncing Team and Member Roles & Progress**\nTo ensure the team and its members understand their purpose and current context, maintain `role.md` and member `progress.md` files (with proper OKF frontmatter).\n```bash\n# Update the overall team role\nuv tool run fulcra-api file upload /tmp/team-role.md \"team/<team_name>/role.md\"\n\n# Update your specific agent's role within the team\nuv tool run fulcra-api file upload /tmp/member-role.md \"team/<team_name>/member/<your_agent_name>/role.md\"\n\n# Update your specific agent's progress (critical for isolated background jobs)\nuv tool run fulcra-api file upload /tmp/member-progress.md \"team/<team_name>/member/<your_agent_name>/progress.md\"\n```\n\n## 4. Team Session and Task Tracking\n\nWhen completing a discrete block of work or tracking a long-running project within the team, upload summaries to the team namespace rather than your personal memory namespace.\n\n**Step A: Uploading a Session Summary**\nWhen a team session concludes, create a concise markdown summary (with `type: Session Summary` frontmatter) and upload it.\n```bash\n# Filename convention: YYYYMMDD-HHMMSS_<agent-name>_<subject>.md\nuv tool run fulcra-api file upload /tmp/session-summary.md \"team/<team_name>/session/20260623-180530_treecle_setup-dashboard.md\"\n```\n\n**Step B: Updating a Task Tracker**\nFor ongoing team objectives, update a task tracker (with `type: Task` frontmatter) and its index.\n```bash\n# Filename convention: <task-name>.md (No timestamp)\nuv tool run fulcra-api file upload /tmp/task-status.md \"team/<team_name>/task/setup-dashboard.md\"\nuv tool run fulcra-api file upload /tmp/task-index.md \"team/<team_name>/task/index.md\"\n```\n\nFile v0.0.5:skill-card.md\n\n## Description: <br>\nEnable agents to collaborate using shared memory, team inboxes, and user artifacts via Fulcra's versioned file storage. <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>\nDevelopers and agent operators use this skill to let agents coordinate through Fulcra team spaces, exchange inbox messages, preserve team state, and save approved user artifacts. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Persistent heartbeat or cron-style checks may continue acting on shared team data after the immediate session. <br>\nMitigation: Require explicit user approval before enabling automation, and define allowed inboxes, actions, duration, logging location, and shutdown steps. <br>\nRisk: Team coordination can move private workspace context or files to another agent or shared team space. <br>\nMitigation: Transfer data only with explicit authorization and keep actions within the user's stated ownership and sharing boundaries. <br>\nRisk: Local memory updates can preserve team responsibilities or operating instructions beyond the current task. <br>\nMitigation: Ask before editing memory files and record only the minimum team context needed for authorized future work. <br>\n\n\n## Reference(s): <br>\n- [Fulcra Agent Teams CLI Reference](references/fulcra-agent-teams-cli.md) <br>\n- [Fulcra CLI Documentation](https://raw.githubusercontent.com/fulcradynamics/agent-skills/main/skills/fulcra-onboarding/references/fulcra-cli.md) <br>\n- [Open Knowledge Format Specification](https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [guidance, markdown, shell commands, configuration] <br>\n**Output Format:** [Markdown with inline bash code blocks] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Includes Fulcra namespace conventions, team inbox workflows, artifact upload guidance, and OKF tracking file patterns.] <br>\n\n## Skill Version(s): <br>\n0.0.5 (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 v0.0.4: 4 files, 6037 bytes\n\nFiles: references/fulcra-agent-teams-cli.md (4486b), skill-card.md (2585b), SKILL.md (5732b), _meta.json (137b)\n\nFile v0.0.4:SKILL.md\n\n---\nname: fulcra-agent-teams\ndescription: \"Enable agents to collaborate using shared memory, team inboxes, and user artifacts via Fulcra's versioned file storage.\"\nhomepage: \"https://github.com/fulcradynamics/agent-skills\"\nlicense: \"MIT\"\nuser-invocable: true\nmetadata: { \"openclaw\": { \"emoji\": \"🤝\" } }\n---\n\n# Fulcra Agent Teams\n\nThe **primary role** of this skill is to allow agents to store generated artifacts and coordinate with other agents using shared team spaces in Fulcra's versioned file storage.\n\n## 1. Uploading User Artifacts\n\nAgents can store generated assets, binaries, or compiled dashboards created for the user. Per the OKF standard, any non-markdown files must be stored in a dedicated `artifact/` directory.\n- **Namespace:** `agent/<agent-name>/artifact/` (e.g., `agent/wazir/artifact/onboarding-dashboard.html`)\n- **Note:** Always ask for explicit user approval before uploading anything to the artifact directory.\n\n## 2. Team Coordination & Shared Memory (OKF Compliant)\n\nAgents can collaborate and share memory using a shared `team/<team-name>/` prefix in the Fulcra datastore. This directory structure must conform to the Open Knowledge Format (OKF).\n\n**SECURITY & AUTHORIZATION WARNING:** Never transfer data, context, or files between agents without explicit authorization and strict respect for data ownership boundaries. Cross-agent data transfer can leak sensitive user context to a principal who lacks authorization. Ensure you explicitly warn the user if a team coordination action involves transferring private workspace data.\n\nWithin a team's directory, the following OKF structure is used:\n- **`team/<team-name>/index.md`**: Directory listing of the team's concepts and members.\n- **`team/<team-name>/log.md`**: Chronological update history for the team namespace.\n- **`team/<team-name>/progress.md`**: Tracks what team members have recently done and what they plan to do next. Must include OKF YAML frontmatter.\n- **`team/<team-name>/completed.md`**: A growing record of each high-level objective completed by the team. Must include OKF YAML frontmatter.\n- **`team/<team-name>/artifact/`**: Shared non-markdown output files, deliverables, or binaries created by the team.\n- **`team/<team-name>/member/<agent-name>/inbox/`**: A drop-zone where other agents or users can place tasks, messages, or context for a specific agent.\n- **`team/<team-name>/member/<agent-name>/archive/`**: Where an agent moves its inbox messages once they have been read and processed.\n\n**IMPORTANT OKF EFFICIENCY DIRECTIVE:** While OKF compliance is required for team spaces, it must not become a burden.\n- **DO NOT** attempt to index or log every individual transient file or message within `member/<agent-name>/inbox/` or `member/<agent-name>/archive/`.\n- In the team's `index.md`, simply list the member directories or the `inbox/` directory as a whole with a high-level description (e.g., \"Contains unread coordination messages for the team\").\n- Keep the `index.md` and `log.md` focused strictly on major team milestones, high-level objectives, or structural additions (like a new member joining or a major artifact being published).\n\n### The Inbox Lifecycle\n\nWhen collaborating, agents write markdown messages to one another's inboxes. To ensure messages sort chronologically and identify the sender, messages must be named using the convention: `YYYYMMDD-HHMMSS_<sender-name>_<short-topic>.md` (e.g., `20260608-232500_treecle_onboarding-status.md`).\n\n**Thread Continuity:** When replying to a message or posting an update about a task, you MUST reuse the exact same `<short-topic>` component from the original message. This allows agents and users to track conversations and tasks across multiple inbox exchanges.\n\nWhen the target agent processes its inbox, it must first upload the message to its `archive/` directory, and then delete the original file from its `inbox/`. Because Fulcra's file system is versioned, it automatically keeps a perfect audit trail of when the file was created in the inbox and when it was completed (deleted).\n\n## 3. Automated Inbox Checking (Heartbeat)\n\nAgents can optionally check their inbox automatically during their periodic background heartbeat (if the agent supports a `HEARTBEAT.md` or cron-driven background execution).\n- **Require Consent:** You must explicitly ask the user for permission before enabling automated background inbox checks.\n- If the user approves, add a task to your local workspace's `HEARTBEAT.md` file (or equivalent background schedule) to periodically check your inbox at `team/<team-name>/member/<agent-name>/inbox/`.\n- Ensure you log any new tasks or messages discovered during the heartbeat into your local daily memory logs, and process the message using the Inbox Lifecycle (archiving and deleting from the inbox).\n\n## Workflow\n\nTo perform team operations, agents must interact with the Fulcra CLI. \n\nFor general information about the Fulcra File Store and the required Open Knowledge Format (OKF) standard, please refer to the main Fulcra CLI documentation found in the `fulcra-onboarding` skill, or read the full OKF specification directly:\n- [https://raw.githubusercontent.com/fulcradynamics/agent-skills/main/skills/fulcra-onboarding/references/fulcra-cli.md](https://raw.githubusercontent.com/fulcradynamics/agent-skills/main/skills/fulcra-onboarding/references/fulcra-cli.md)\n- [https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md](https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md)\n\nSee the reference documentation for the exact commands needed to manage artifacts and inbox messaging:\n- Read `references/fulcra-agent-teams-cli.md` for exact file management and CLI execution steps.\n\nFile v0.0.4:_meta.json\n\n{\n  \"ownerId\": \"kn72pt2cb5f9nskgc9k2ddecxs87547j\",\n  \"slug\": \"fulcra-agent-teams\",\n  \"version\": \"0.0.4\",\n  \"publishedAt\": 1781633403422\n}\n\nFile v0.0.4:references/fulcra-agent-teams-cli.md\n\n---\nname: fulcra-agent-teams-cli\ndescription: \"CLI command references for executing artifact uploads and team inbox operations with Fulcra.\"\n---\n\n# Fulcra Agent Teams CLI Reference\n\nThis reference dictates the exact shell commands required to execute the `fulcra-agent-teams` skill's operations. Ensure all CLI operations run in the agent's workspace.\n\n## 1. Uploading User Artifacts\n\nWhen an agent generates a file (like an HTML dashboard, an image, or a report), and the user explicitly approves saving it to their Fulcra account, upload it to the `artifact/` subdirectory.\n\n```bash\n# Replace <agent_name> with the agent's name, and <artifact_name> with the file's name\nuv tool run fulcra-api file upload /path/to/local/file \"agent/<agent_name>/artifact/<artifact_name>\"\n```\n\n## 2. Team Coordination (Inbox & Archive)\n\nAgents can coordinate by writing to and reading from team namespaces.\n\n**Message Naming Convention:**\nMessages must follow the format `YYYYMMDD-HHMMSS_<sender-name>_<short-topic>.md`. Use underscores between the three main components so they can be reliably parsed.\n*Note: When replying to a message or providing a status update, always reuse the exact same `<short-topic>` as the original message to maintain thread continuity.*\n\n**Step A: Sending a message to a teammate's inbox**\n```bash\n# Upload a local markdown file to the target agent's inbox\nuv tool run fulcra-api file upload /tmp/message.md \"team/<team_name>/member/<target_agent_name>/inbox/20260608-232500_wazir_status-update.md\"\n```\n\n**Step B: Checking your inbox**\n```bash\n# List files in your agent's inbox\nuv tool run fulcra-api file list \"team/<team_name>/member/<your_agent_name>/inbox/\"\n```\n\n**Step C: Processing and Archiving a message**\nOnce you have downloaded and read a message from your inbox, move it to the archive.\n\n```bash\n# 1. Download to read (if you haven't already)\nuv tool run fulcra-api file download \"team/<team_name>/member/<your_agent_name>/inbox/20260608-232500_wazir_status-update.md\" /tmp/20260608-232500_wazir_status-update.md\n\n# 2. Upload it to your archive directory\nuv tool run fulcra-api file upload /tmp/20260608-232500_wazir_status-update.md \"team/<team_name>/member/<your_agent_name>/archive/20260608-232500_wazir_status-update.md\"\n\n# 3. Verify archival succeeded before deletion!\nuv tool run fulcra-api file stat \"team/<team_name>/member/<your_agent_name>/archive/20260608-232500_wazir_status-update.md\"\n\n# 4. Delete it from the inbox to clear it (only if step 3 succeeded)\nuv tool run fulcra-api file delete \"team/<team_name>/member/<your_agent_name>/inbox/20260608-232500_wazir_status-update.md\"\n```\n\n## 3. Team Activity Tracking (OKF Compliant)\n\nAgents can update shared files to track the team's high-level progress and completed objectives. Ensure all markdown files contain OKF YAML frontmatter, and that `log.md` and `index.md` are updated when appropriate.\n\n**Step A: Updating Team Progress**\nTo update the `progress.md` file (which stores what the team members have recently done and what they plan to do next):\n```bash\n# 1. Download the current progress file\nuv tool run fulcra-api file download \"team/<team_name>/progress.md\" /tmp/team_progress.md || touch /tmp/team_progress.md\n\n# 2. Edit /tmp/team_progress.md locally to reflect the latest plans and recent work. \n# Make sure it has OKF frontmatter:\n# ---\n# type: Progress Report\n# title: Team Progress\n# ---\n\n# 3. Upload the updated file back to Fulcra\nuv tool run fulcra-api file upload /tmp/team_progress.md \"team/<team_name>/progress.md\"\n\n# 4. Also append an update entry to log.md\nDATE=$(date -u +\"%Y-%m-%d\")\necho \"## $DATE\" > /tmp/log_update.md\necho \"* **Update**: <agent_name> updated team progress.\" >> /tmp/log_update.md\n# (In practice, download log.md, append the update under the correct date, and re-upload)\n```\n\n**Step B: Recording Completed Objectives**\nTo add a newly completed high-level objective to `completed.md` (which should generally only grow):\n```bash\n# 1. Download the current completed file\nuv tool run fulcra-api file download \"team/<team_name>/completed.md\" /tmp/team_completed.md || touch /tmp/team_completed.md\n\n# 2. Append the new objective (ensure OKF frontmatter exists at the top of the file)\necho \"- [$(date +%Y-%m-%d)] <Objective summary>\" >> /tmp/team_completed.md\n\n# 3. Upload the updated file back to Fulcra\nuv tool run fulcra-api file upload /tmp/team_completed.md \"team/<team_name>/completed.md\"\n\n# 4. Also update the team log.md with the completion event.\n```\n\nFile v0.0.4:skill-card.md\n\n## Description: <br>\nEnable agents to collaborate using shared memory, team inboxes, and user artifacts via Fulcra's versioned file storage. <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>\nDevelopers and agent operators use this skill to coordinate work across agents through Fulcra shared storage, including approved artifact uploads, team inbox messages, archive handling, and OKF-style team progress files. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Cross-agent coordination can expose private workspace data to recipients who are not authorized to receive it. <br>\nMitigation: Confirm the allowed Fulcra team paths and recipients before use, and require explicit authorization before transferring context or files between agents. <br>\nRisk: Uploaded artifacts or inbox messages may contain sensitive user data. <br>\nMitigation: Approve each artifact upload and avoid placing sensitive data in shared team inboxes unless every recipient is authorized. <br>\nRisk: Automated inbox checks create persistent periodic processing. <br>\nMitigation: Enable background inbox checks only after user consent and keep processing scoped to the approved team inbox path. <br>\n\n\n## Reference(s): <br>\n- [ClawHub release page](https://clawhub.ai/fulcra/fulcra-agent-teams) <br>\n- [Fulcra Agent Teams CLI Reference](references/fulcra-agent-teams-cli.md) <br>\n- [Fulcra CLI documentation](https://raw.githubusercontent.com/fulcradynamics/agent-skills/main/skills/fulcra-onboarding/references/fulcra-cli.md) <br>\n- [Open Knowledge Format specification](https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [guidance, shell commands, markdown, configuration] <br>\n**Output Format:** [Markdown guidance with inline shell commands and Fulcra path conventions] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Requires explicit user approval for artifact uploads and cross-agent data transfer; automated inbox checks require user consent.] <br>\n\n## Skill Version(s): <br>\n0.0.4 (source: ClawHub 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 v0.0.3: 4 files, 5812 bytes\n\nFiles: references/fulcra-agent-teams-cli.md (4486b), skill-card.md (2677b), SKILL.md (5079b), _meta.json (137b)\n\nFile v0.0.3:SKILL.md\n\n---\nname: fulcra-agent-teams\ndescription: \"Enable agents to collaborate using shared memory, team inboxes, and user artifacts via Fulcra's versioned file storage.\"\nhomepage: \"https://github.com/fulcradynamics/agent-skills\"\nlicense: \"MIT\"\nuser-invocable: true\nmetadata: { \"openclaw\": { \"emoji\": \"🤝\" } }\n---\n\n# Fulcra Agent Teams\n\nThe **primary role** of this skill is to allow agents to store generated artifacts and coordinate with other agents using shared team spaces in Fulcra's versioned file storage.\n\n## 1. Uploading User Artifacts\n\nAgents can store generated assets, binaries, or compiled dashboards created for the user. Per the OKF standard, any non-markdown files must be stored in a dedicated `artifact/` directory.\n- **Namespace:** `agent/<agent-name>/artifact/` (e.g., `agent/wazir/artifact/onboarding-dashboard.html`)\n- **Note:** Always ask for explicit user approval before uploading anything to the artifact directory.\n\n## 2. Team Coordination & Shared Memory (OKF Compliant)\n\nAgents can collaborate and share memory using a shared `team/<team-name>/` prefix in the Fulcra datastore. This directory structure must conform to the Open Knowledge Format (OKF).\n\n**SECURITY & AUTHORIZATION WARNING:** Never transfer data, context, or files between agents without explicit authorization and strict respect for data ownership boundaries. Cross-agent data transfer can leak sensitive user context to a principal who lacks authorization. Ensure you explicitly warn the user if a team coordination action involves transferring private workspace data.\n\nWithin a team's directory, the following OKF structure is used:\n- **`team/<team-name>/index.md`**: Directory listing of the team's concepts and members.\n- **`team/<team-name>/log.md`**: Chronological update history for the team namespace.\n- **`team/<team-name>/progress.md`**: Tracks what team members have recently done and what they plan to do next. Must include OKF YAML frontmatter.\n- **`team/<team-name>/completed.md`**: A growing record of each high-level objective completed by the team. Must include OKF YAML frontmatter.\n- **`team/<team-name>/artifact/`**: Shared non-markdown output files, deliverables, or binaries created by the team.\n- **`team/<team-name>/member/<agent-name>/inbox/`**: A drop-zone where other agents or users can place tasks, messages, or context for a specific agent.\n- **`team/<team-name>/member/<agent-name>/archive/`**: Where an agent moves its inbox messages once they have been read and processed.\n\n### The Inbox Lifecycle\n\nWhen collaborating, agents write markdown messages to one another's inboxes. To ensure messages sort chronologically and identify the sender, messages must be named using the convention: `YYYYMMDD-HHMMSS_<sender-name>_<short-topic>.md` (e.g., `20260608-232500_treecle_onboarding-status.md`).\n\n**Thread Continuity:** When replying to a message or posting an update about a task, you MUST reuse the exact same `<short-topic>` component from the original message. This allows agents and users to track conversations and tasks across multiple inbox exchanges.\n\nWhen the target agent processes its inbox, it must first upload the message to its `archive/` directory, and then delete the original file from its `inbox/`. Because Fulcra's file system is versioned, it automatically keeps a perfect audit trail of when the file was created in the inbox and when it was completed (deleted).\n\n## 3. Automated Inbox Checking (Heartbeat)\n\nAgents can optionally check their inbox automatically during their periodic background heartbeat (if the agent supports a `HEARTBEAT.md` or cron-driven background execution).\n- **Require Consent:** You must explicitly ask the user for permission before enabling automated background inbox checks.\n- If the user approves, add a task to your local workspace's `HEARTBEAT.md` file (or equivalent background schedule) to periodically check your inbox at `team/<team-name>/member/<agent-name>/inbox/`.\n- Ensure you log any new tasks or messages discovered during the heartbeat into your local daily memory logs, and process the message using the Inbox Lifecycle (archiving and deleting from the inbox).\n\n## Workflow\n\nTo perform team operations, agents must interact with the Fulcra CLI. \n\nFor general information about the Fulcra File Store and the required Open Knowledge Format (OKF) standard, please refer to the main Fulcra CLI documentation found in the `fulcra-onboarding` skill, or read the full OKF specification directly:\n- [https://raw.githubusercontent.com/fulcradynamics/agent-skills/main/skills/fulcra-onboarding/references/fulcra-cli.md](https://raw.githubusercontent.com/fulcradynamics/agent-skills/main/skills/fulcra-onboarding/references/fulcra-cli.md)\n- [https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md](https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md)\n\nSee the reference documentation for the exact commands needed to manage artifacts and inbox messaging:\n- Read `references/fulcra-agent-teams-cli.md` for exact file management and CLI execution steps.\n\nFile v0.0.3:_meta.json\n\n{\n  \"ownerId\": \"kn72pt2cb5f9nskgc9k2ddecxs87547j\",\n  \"slug\": \"fulcra-agent-teams\",\n  \"version\": \"0.0.3\",\n  \"publishedAt\": 1781566851284\n}\n\nFile v0.0.3:references/fulcra-agent-teams-cli.md\n\n---\nname: fulcra-agent-teams-cli\ndescription: \"CLI command references for executing artifact uploads and team inbox operations with Fulcra.\"\n---\n\n# Fulcra Agent Teams CLI Reference\n\nThis reference dictates the exact shell commands required to execute the `fulcra-agent-teams` skill's operations. Ensure all CLI operations run in the agent's workspace.\n\n## 1. Uploading User Artifacts\n\nWhen an agent generates a file (like an HTML dashboard, an image, or a report), and the user explicitly approves saving it to their Fulcra account, upload it to the `artifact/` subdirectory.\n\n```bash\n# Replace <agent_name> with the agent's name, and <artifact_name> with the file's name\nuv tool run fulcra-api file upload /path/to/local/file \"agent/<agent_name>/artifact/<artifact_name>\"\n```\n\n## 2. Team Coordination (Inbox & Archive)\n\nAgents can coordinate by writing to and reading from team namespaces.\n\n**Message Naming Convention:**\nMessages must follow the format `YYYYMMDD-HHMMSS_<sender-name>_<short-topic>.md`. Use underscores between the three main components so they can be reliably parsed.\n*Note: When replying to a message or providing a status update, always reuse the exact same `<short-topic>` as the original message to maintain thread continuity.*\n\n**Step A: Sending a message to a teammate's inbox**\n```bash\n# Upload a local markdown file to the target agent's inbox\nuv tool run fulcra-api file upload /tmp/message.md \"team/<team_name>/member/<target_agent_name>/inbox/20260608-232500_wazir_status-update.md\"\n```\n\n**Step B: Checking your inbox**\n```bash\n# List files in your agent's inbox\nuv tool run fulcra-api file list \"team/<team_name>/member/<your_agent_name>/inbox/\"\n```\n\n**Step C: Processing and Archiving a message**\nOnce you have downloaded and read a message from your inbox, move it to the archive.\n\n```bash\n# 1. Download to read (if you haven't already)\nuv tool run fulcra-api file download \"team/<team_name>/member/<your_agent_name>/inbox/20260608-232500_wazir_status-update.md\" /tmp/20260608-232500_wazir_status-update.md\n\n# 2. Upload it to your archive directory\nuv tool run fulcra-api file upload /tmp/20260608-232500_wazir_status-update.md \"team/<team_name>/member/<your_agent_name>/archive/20260608-232500_wazir_status-update.md\"\n\n# 3. Verify archival succeeded before deletion!\nuv tool run fulcra-api file stat \"team/<team_name>/member/<your_agent_name>/archive/20260608-232500_wazir_status-update.md\"\n\n# 4. Delete it from the inbox to clear it (only if step 3 succeeded)\nuv tool run fulcra-api file delete \"team/<team_name>/member/<your_agent_name>/inbox/20260608-232500_wazir_status-update.md\"\n```\n\n## 3. Team Activity Tracking (OKF Compliant)\n\nAgents can update shared files to track the team's high-level progress and completed objectives. Ensure all markdown files contain OKF YAML frontmatter, and that `log.md` and `index.md` are updated when appropriate.\n\n**Step A: Updating Team Progress**\nTo update the `progress.md` file (which stores what the team members have recently done and what they plan to do next):\n```bash\n# 1. Download the current progress file\nuv tool run fulcra-api file download \"team/<team_name>/progress.md\" /tmp/team_progress.md || touch /tmp/team_progress.md\n\n# 2. Edit /tmp/team_progress.md locally to reflect the latest plans and recent work. \n# Make sure it has OKF frontmatter:\n# ---\n# type: Progress Report\n# title: Team Progress\n# ---\n\n# 3. Upload the updated file back to Fulcra\nuv tool run fulcra-api file upload /tmp/team_progress.md \"team/<team_name>/progress.md\"\n\n# 4. Also append an update entry to log.md\nDATE=$(date -u +\"%Y-%m-%d\")\necho \"## $DATE\" > /tmp/log_update.md\necho \"* **Update**: <agent_name> updated team progress.\" >> /tmp/log_update.md\n# (In practice, download log.md, append the update under the correct date, and re-upload)\n```\n\n**Step B: Recording Completed Objectives**\nTo add a newly completed high-level objective to `completed.md` (which should generally only grow):\n```bash\n# 1. Download the current completed file\nuv tool run fulcra-api file download \"team/<team_name>/completed.md\" /tmp/team_completed.md || touch /tmp/team_completed.md\n\n# 2. Append the new objective (ensure OKF frontmatter exists at the top of the file)\necho \"- [$(date +%Y-%m-%d)] <Objective summary>\" >> /tmp/team_completed.md\n\n# 3. Upload the updated file back to Fulcra\nuv tool run fulcra-api file upload /tmp/team_completed.md \"team/<team_name>/completed.md\"\n\n# 4. Also update the team log.md with the completion event.\n```\n\nFile v0.0.3:skill-card.md\n\n## Description: <br>\nEnable agents to collaborate using shared memory, team inboxes, and user artifacts via Fulcra's versioned file storage. <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>\nDevelopers and agent operators use this skill to coordinate multi-agent work through Fulcra team namespaces, shared memory files, inbox messages, and approved artifact uploads. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: A review helper in the skill set may bypass sandbox and approval controls for nested agent review. <br>\nMitigation: Review the autoreview helper before installing or using this skill set; disable full-access mode with --no-yolo or AUTOREVIEW_YOLO=0 when those permissions are not required. <br>\nRisk: Fallback reviewers may send local diffs to other review CLIs. <br>\nMitigation: Disable fallback reviewers when local diffs should not be shared outside the intended review toolchain. <br>\nRisk: Cross-agent coordination can transfer private workspace data to a principal that lacks authorization. <br>\nMitigation: Require explicit authorization before transferring data, context, or files between agents, and warn the user when a team action involves private workspace data. <br>\nRisk: Artifact uploads and automated inbox checks can persist user data or background activity unexpectedly. <br>\nMitigation: Ask for explicit user approval before uploading artifacts or enabling automated inbox checks. <br>\n\n\n## Reference(s): <br>\n- [Fulcra Agent Teams CLI Reference](references/fulcra-agent-teams-cli.md) <br>\n- [Fulcra CLI documentation](https://raw.githubusercontent.com/fulcradynamics/agent-skills/main/skills/fulcra-onboarding/references/fulcra-cli.md) <br>\n- [Open Knowledge Format specification](https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Guidance, Markdown, Shell commands, Configuration] <br>\n**Output Format:** [Markdown with inline bash code blocks] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Requires explicit user approval before artifact uploads or automated inbox checks.] <br>\n\n## Skill Version(s): <br>\n0.0.3 (source: ClawHub 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 v0.0.2: 4 files, 4961 bytes\n\nFiles: references/fulcra-agent-teams-cli.md (3861b), skill-card.md (2097b), SKILL.md (3991b), _meta.json (137b)\n\nFile v0.0.2:SKILL.md\n\n---\nname: fulcra-agent-teams\ndescription: \"Enable agents to collaborate using shared memory, team inboxes, and user artifacts via Fulcra's versioned file storage.\"\nhomepage: \"https://github.com/fulcradynamics/agent-skills\"\nlicense: \"MIT\"\nuser-invocable: true\nmetadata: { \"openclaw\": { \"emoji\": \"🤝\" } }\n---\n\n# Fulcra Agent Teams\n\nThe **primary role** of this skill is to allow agents to store generated artifacts and coordinate with other agents using shared team spaces in Fulcra's versioned file storage.\n\n## 1. Uploading User Artifacts\n\nAgents can store generated assets or dashboards created for the user.\n- **Namespace:** `agent/<agent-name>/artifact/` (e.g., `agent/wazir/artifact/onboarding-dashboard.html`)\n- **Note:** Always ask for explicit user approval before uploading anything to the artifact directory.\n\n## 2. Team Coordination & Shared Memory\n\nAgents can collaborate and share memory using a shared `team/<team-name>/` prefix in the Fulcra datastore.\n\n**SECURITY & AUTHORIZATION WARNING:** Never transfer data, context, or files between agents without explicit authorization and strict respect for data ownership boundaries. Cross-agent data transfer can leak sensitive user context to a principal who lacks authorization. Ensure you explicitly warn the user if a team coordination action involves transferring private workspace data.\n\nWithin a team's directory, the following structure is used:\n- **`team/<team-name>/artifact/`**: Shared output files and deliverables created by the team.\n- **`team/<team-name>/progress.md`**: Tracks what team members have recently done and what they are planning to do next in terms of high-level tasks.\n- **`team/<team-name>/completed.md`**: A growing record of each high-level objective completed by the team.\n- **`team/<team-name>/member/<agent-name>/inbox/`**: A drop-zone where other agents or users can place tasks, messages, or context for a specific agent.\n- **`team/<team-name>/member/<agent-name>/archive/`**: Where an agent moves its inbox messages once they have been read and processed.\n\n### The Inbox Lifecycle\n\nWhen collaborating, agents write markdown messages to one another's inboxes. To ensure messages sort chronologically and identify the sender, messages must be named using the convention: `YYYYMMDD-HHMMSS_<sender-name>_<short-topic>.md` (e.g., `20260608-232500_treecle_onboarding-status.md`).\n\n**Thread Continuity:** When replying to a message or posting an update about a task, you MUST reuse the exact same `<short-topic>` component from the original message. This allows agents and users to track conversations and tasks across multiple inbox exchanges.\n\nWhen the target agent processes its inbox, it must first upload the message to its `archive/` directory, and then delete the original file from its `inbox/`. Because Fulcra's file system is versioned, it automatically keeps a perfect audit trail of when the file was created in the inbox and when it was completed (deleted).\n\n## 3. Automated Inbox Checking (Heartbeat)\n\nAgents can optionally check their inbox automatically during their periodic background heartbeat (if the agent supports a `HEARTBEAT.md` or cron-driven background execution).\n- **Require Consent:** You must explicitly ask the user for permission before enabling automated background inbox checks.\n- If the user approves, add a task to your local workspace's `HEARTBEAT.md` file (or equivalent background schedule) to periodically check your inbox at `team/<team-name>/member/<agent-name>/inbox/`.\n- Ensure you log any new tasks or messages discovered during the heartbeat into your local daily memory logs, and process the message using the Inbox Lifecycle (archiving and deleting from the inbox).\n\n## Workflow\n\nTo perform team operations, agents must interact with the Fulcra CLI. \n\nSee the reference documentation for the exact commands needed to manage artifacts and inbox messaging:\n- Read `references/fulcra-agent-teams-cli.md` for exact file management and CLI execution steps.\n\nFile v0.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn72pt2cb5f9nskgc9k2ddecxs87547j\",\n  \"slug\": \"fulcra-agent-teams\",\n  \"version\": \"0.0.2\",\n  \"publishedAt\": 1781296579862\n}\n\nFile v0.0.2:references/fulcra-agent-teams-cli.md\n\n---\nname: fulcra-agent-teams-cli\ndescription: \"CLI command references for executing artifact uploads and team inbox operations with Fulcra.\"\n---\n\n# Fulcra Agent Teams CLI Reference\n\nThis reference dictates the exact shell commands required to execute the `fulcra-agent-teams` skill's operations. Ensure all CLI operations run in the agent's workspace.\n\n## 1. Uploading User Artifacts\n\nWhen an agent generates a file (like an HTML dashboard, an image, or a report), and the user explicitly approves saving it to their Fulcra account, upload it to the `artifact/` subdirectory.\n\n```bash\n# Replace <agent_name> with the agent's name, and <artifact_name> with the file's name\nuv tool run fulcra-api file upload /path/to/local/file \"agent/<agent_name>/artifact/<artifact_name>\"\n```\n\n## 2. Team Coordination (Inbox & Archive)\n\nAgents can coordinate by writing to and reading from team namespaces.\n\n**Message Naming Convention:**\nMessages must follow the format `YYYYMMDD-HHMMSS_<sender-name>_<short-topic>.md`. Use underscores between the three main components so they can be reliably parsed.\n*Note: When replying to a message or providing a status update, always reuse the exact same `<short-topic>` as the original message to maintain thread continuity.*\n\n**Step A: Sending a message to a teammate's inbox**\n```bash\n# Upload a local markdown file to the target agent's inbox\nuv tool run fulcra-api file upload /tmp/message.md \"team/<team_name>/member/<target_agent_name>/inbox/20260608-232500_wazir_status-update.md\"\n```\n\n**Step B: Checking your inbox**\n```bash\n# List files in your agent's inbox\nuv tool run fulcra-api file list \"team/<team_name>/member/<your_agent_name>/inbox/\"\n```\n\n**Step C: Processing and Archiving a message**\nOnce you have downloaded and read a message from your inbox, move it to the archive.\n\n```bash\n# 1. Download to read (if you haven't already)\nuv tool run fulcra-api file download \"team/<team_name>/member/<your_agent_name>/inbox/20260608-232500_wazir_status-update.md\" /tmp/20260608-232500_wazir_status-update.md\n\n# 2. Upload it to your archive directory\nuv tool run fulcra-api file upload /tmp/20260608-232500_wazir_status-update.md \"team/<team_name>/member/<your_agent_name>/archive/20260608-232500_wazir_status-update.md\"\n\n# 3. Verify archival succeeded before deletion!\nuv tool run fulcra-api file stat \"team/<team_name>/member/<your_agent_name>/archive/20260608-232500_wazir_status-update.md\"\n\n# 4. Delete it from the inbox to clear it (only if step 3 succeeded)\nuv tool run fulcra-api file delete \"team/<team_name>/member/<your_agent_name>/inbox/20260608-232500_wazir_status-update.md\"\n```\n\n## 3. Team Activity Tracking\n\nAgents can update shared files to track the team's high-level progress and completed objectives.\n\n**Step A: Updating Team Progress**\nTo update the `progress.md` file (which stores what the team members have recently done and what they plan to do next):\n```bash\n# 1. Download the current progress file\nuv tool run fulcra-api file download \"team/<team_name>/progress.md\" /tmp/team_progress.md || touch /tmp/team_progress.md\n\n# 2. Edit /tmp/team_progress.md locally to reflect the latest plans and recent work.\n\n# 3. Upload the updated file back to Fulcra\nuv tool run fulcra-api file upload /tmp/team_progress.md \"team/<team_name>/progress.md\"\n```\n\n**Step B: Recording Completed Objectives**\nTo add a newly completed high-level objective to `completed.md` (which should generally only grow):\n```bash\n# 1. Download the current completed file\nuv tool run fulcra-api file download \"team/<team_name>/completed.md\" /tmp/team_completed.md || touch /tmp/team_completed.md\n\n# 2. Append the new objective\necho \"- [$(date +%Y-%m-%d)] <Objective summary>\" >> /tmp/team_completed.md\n\n# 3. Upload the updated file back to Fulcra\nuv tool run fulcra-api file upload /tmp/team_completed.md \"team/<team_name>/completed.md\"\n```\n\nFile v0.0.2:skill-card.md\n\n## Description: <br>\nEnable agents to collaborate using shared memory, team inboxes, and user artifacts via Fulcra's versioned file storage. <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 developers use this skill to store user-approved artifacts in Fulcra and coordinate work through team namespaces, inboxes, shared progress notes, and completed-objective logs. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Unapproved sharing of private workspace data through Fulcra artifact or team namespaces. <br>\nMitigation: Confirm what files or context will be shared, which team namespace is being used, and that the user has authorized the transfer before uploading or coordinating. <br>\nRisk: Automated inbox checks could run without clear user consent. <br>\nMitigation: Enable heartbeat-based inbox checking only after explicit user permission, then log discovered messages and process them through the documented archive-and-delete lifecycle. <br>\n\n\n## Reference(s): <br>\n- [Fulcra Agent Teams CLI Reference](references/fulcra-agent-teams-cli.md) <br>\n- [ClawHub Skill Page](https://clawhub.ai/fulcra/fulcra-agent-teams) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance] <br>\n**Output Format:** [Markdown guidance with inline shell commands and file path conventions] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Requires explicit user approval before artifact uploads, cross-agent data transfer, and optional heartbeat-based inbox checks.] <br>\n\n## Skill Version(s): <br>\n0.0.2 (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 v0.0.1: 4 files, 4723 bytes\n\nFiles: references/fulcra-agent-teams-cli.md (3861b), skill-card.md (2250b), SKILL.md (3248b), _meta.json (137b)\n\nFile v0.0.1:SKILL.md\n\n---\nname: fulcra-agent-teams\ndescription: \"Enable agents to collaborate using shared memory, team inboxes, and user artifacts via Fulcra's versioned file storage.\"\nhomepage: \"https://github.com/fulcradynamics/agent-skills\"\nlicense: \"MIT\"\nuser-invocable: true\nmetadata: { \"openclaw\": { \"emoji\": \"🤝\" } }\n---\n\n# Fulcra Agent Teams\n\nThe **primary role** of this skill is to allow agents to store generated artifacts and coordinate with other agents using shared team spaces in Fulcra's versioned file storage.\n\n## 1. Uploading User Artifacts\n\nAgents can store generated assets or dashboards created for the user.\n- **Namespace:** `agent/<agent-name>/artifact/` (e.g., `agent/wazir/artifact/onboarding-dashboard.html`)\n- **Note:** Always ask for explicit user approval before uploading anything to the artifact directory.\n\n## 2. Team Coordination & Shared Memory\n\nAgents can collaborate and share memory using a shared `team/<team-name>/` prefix in the Fulcra datastore.\n\n**SECURITY & AUTHORIZATI","readmeExcerpt":"Skill: Fulcra Agent Teams (deprecated, use fulcra-workspaces) Owner: fulcra Summary: Deprecated — renamed to fulcra-workspaces. Use the fulcra-workspaces skill instead. Tags: latest:0.1.0 Version history: v0.1.0 | 2026-08-12T20:44:51.147Z | auto The fulcra-agent-teams skill has been deprecated and renamed to fulcra-workspaces. - Marked the skill as deprecated; all prior documentation and functionality have been remov","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"# Get a summary of files changed in the last 1 day\nuv tool run fulcra-api data-updates \"1 day\"\n\n# Example output:\n# {\n#   \"data_types\": {},\n#   \"file_changes\": [\n#     {\n#       \"full_name\": \"/team/first-olympiad/progress.md\",\n#       \"uploaded_at\": \"2026-07-01T21:23:28.690719Z\",\n#       \"state\": \"uploaded\",\n#       \"...\": \"...\"\n#     },\n#     {\n#       \"full_name\": \"/team/first-olympiad/task/setup-dashboard.md\",\n#       \"uploaded_at\": \"2026-07-01T21:23:28.690719Z\",\n#       \"state\": \"uploaded\",\n#       \"...\": \"...\"\n#     }\n#   ]\n# }"},{"language":"bash","snippet":"# Replace <agent_name> with the agent's name, and <artifact_name> with the file's name\nuv tool run fulcra-api file upload /path/to/local/file \"agent/<agent_name>/artifact/<artifact_name>\""},{"language":"bash","snippet":"# Upload a local markdown file to the target agent's inbox\nuv tool run fulcra-api file upload /tmp/message.md \"team/<team_name>/member/<target_agent_name>/inbox/20260608-232500_wazir_status-update.md\""},{"language":"bash","snippet":"# List files in your agent's inbox\nuv tool run fulcra-api file list \"team/<team_name>/member/<your_agent_name>/inbox/\""},{"language":"bash","snippet":"# 1. Download to read (if you haven't already)\nuv tool run fulcra-api file download \"team/<team_name>/member/<your_agent_name>/inbox/20260608-232500_wazir_status-update.md\" /tmp/20260608-232500_wazir_status-update.md\n\n# 2. Upload it to your archive directory\nuv tool run fulcra-api file upload /tmp/20260608-232500_wazir_status-update.md \"team/<team_name>/member/<your_agent_name>/archive/20260608-232500_wazir_status-update.md\"\n\n# 3. Verify archival succeeded before deletion!\nuv tool run fulcra-api file stat \"team/<team_name>/member/<your_agent_name>/archive/20260608-232500_wazir_status-update.md\"\n\n# 4. Delete it from the inbox to clear it (only if step 3 succeeded)\nuv tool run fulcra-api file delete \"team/<team_name>/member/<your_agent_name>/inbox/20260608-232500_wazir_status-update.md\""},{"language":"bash","snippet":"# 1. Download the current progress file\nuv tool run fulcra-api file download \"team/<team_name>/progress.md\" /tmp/team_progress.md || touch /tmp/team_progress.md\n\n# 2. Edit /tmp/team_progress.md locally to reflect the latest plans and recent work. \n# Make sure it has OKF frontmatter:\n# ---\n# type: Progress Report\n# title: Team Progress\n# ---\n\n# 3. Upload the updated file back to Fulcra\nuv tool run fulcra-api file upload /tmp/team_progress.md \"team/<team_name>/progress.md\"\n\n# 4. Also append an update entry to log.md\nDATE=$(date -u +\"%Y-%m-%d\")\necho \"## $DATE\" > /tmp/log_update.md\necho \"* **Update**: <agent_name> updated team progress.\" >> /tmp/log_update.md\n# (In practice, download log.md, append the update under the correct date, and re-upload)"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: fulcra-agent-teams\ndescription: \"Deprecated — renamed to fulcra-workspaces. Use the fulcra-workspaces skill instead.\"\nhomepage: \"https://github.com/fulcradynamics/agent-skills\"\nlicense: \"MIT\"\nuser-invocable: true\nmetadata: { \"openclaw\": { \"emoji\": \"🤝\" } }\n---\n\n# Fulcra Agent Teams — moved to `fulcra-workspaces`\n\n> **This skill has been renamed.** `fulcra-agent-teams` is deprecated and is kept only\n> as a pointer. All content now lives in the **`fulcra-workspaces`** skill.\n\n## What to do\n\nUse the `fulcra-workspaces` skill instead:\n\n- **In this repo:** `skills/fulcra-workspaces/`\n- **GitHub:** https://github.com/fulcradynamics/agent-skills/tree/main/skills/fulcra-workspaces\n- **Install:** `fulcradynamics/agent-skills/fulcra-workspaces`\n\nIf you arrived here, read and follow `fulcra-workspaces` — it lets agents\nestablish persistent, shared workspaces in Fulcra's versioned file storage for\ncoordinating work through team inboxes and user-owned artifacts."},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn72pt2cb5f9nskgc9k2ddecxs87547j\",\n  \"slug\": \"fulcra-agent-teams\",\n  \"version\": \"0.1.0\",\n  \"publishedAt\": 1786567491147\n}"},{"path":"skill-card.md","content":"## Description:\n\nDeprecated - renamed to fulcra-workspaces. Use the fulcra-workspaces 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\nDevelopers and agents use this deprecated skill as a pointer from fulcra-agent-teams to the replacement fulcra-workspaces skill. It helps users avoid relying on removed team coordination documentation and locate the renamed workspace skill.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Users may expect fulcra-agent-teams to provide active team coordination behavior even though this release is only a deprecated pointer.\n\nMitigation: Review and install fulcra-workspaces separately when Fulcra shared workspace features are needed.\n\n## Reference(s):\n\n- [Fulcra Agent Teams on ClawHub](https://clawhub.ai/fulcra/skills/fulcra-agent-teams)\n- [Fulcra Agent Skills Repository](https://github.com/fulcradynamics/agent-skills)\n- [fulcra-workspaces skill](https://github.com/fulcradynamics/agent-skills/tree/main/skills/fulcra-workspaces)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Markdown, Configuration]\n\n**Output Format:** [Markdown guidance with install and replacement-skill references]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Deprecated placeholder; no executable code or hidden behavior reported by security evidence.]\n\n## Skill Version(s):\n\n0.1.0 (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-workspaces. Use the fulcra-workspaces skill instead. Skill: Fulcra Agent Teams (deprecated, use fulcra-workspaces) Owner: fulcra Summary: Deprecated — renamed to fulcra-workspaces. Use the fulcra-workspaces skill instead. Tags: latest:0.1.0 Version history: v0.1.0 | 2026-08-12T20:44:51.147Z | auto The fulcra-agent-teams skill has been deprecated and renamed to fulcra-workspaces. - Marked the skill as deprecated; all prior documentation and functionality have been remov","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1259,"uniquenessScore":46,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-10T13:09:01.525Z","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":"2026-10-10T13:09:01.525Z","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":"2026-10-10T15:53:07.352Z","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"}]}}}