{"id":"cf1c16eb-ae24-49fe-b554-78339afed3e6","entityType":"agent","slug":"clawhub-madebydia-deep-current","name":"Deep Current","canonicalUrl":"https://www.xpersona.co/agent/clawhub-madebydia-deep-current","canonicalPath":"/agent/clawhub-madebydia-deep-current","generatedAt":"2026-10-10T14:43:17.941Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-10T12:26:32.550Z","emptyReason":null},"description":"Persistent research thread manager with a CLI for tracking topics, notes, sources, and findings. Pair with a nightly cron job to build a personal research di... Skill: Deep Current Owner: madebydia Summary: Persistent research thread manager with a CLI for tracking topics, notes, sources, and findings. Pair with a nightly cron job to build a personal research di... Tags: latest:2.0.1 Version history: v2.0.1 | 2026-06-07T03:31:41.596Z | user Refresh publisher identity and metadata for madebydia v2.0.0 | 2026-03-24T17:18:08.340Z | user Add metadata, fix ClawHub listing v1.1.0","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 s176b3312npmthbt2chf2mccw183grfh:deep-current","sourceUrl":"https://clawhub.ai/madebydia/deep-current","homepage":"https://clawhub.ai/madebydia/skills/deep-current","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/madebydia/deep-current","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/madebydia/skills/deep-current","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":47,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Persistent research thread manager with a CLI for tracking topics, notes, sources, and findings. Pair with a nightly cron job to build a personal research di..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-10T12:26:32.550Z","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":"2026-10-10T12:26:32.550Z","emptyReason":null},"stars":null,"forks":null,"downloads":1433,"packageName":null,"latestVersion":"2.0.1","tractionLabel":"1.4K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T12:26:32.550Z","emptyReason":null},"lastUpdatedAt":"2026-10-10T12:26:32.550Z","lastCrawledAt":"2026-10-10T12:26:32.550Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-11T12:26:32.550Z","lastVerifiedAt":null,"highlights":[{"version":"2.0.1","createdAt":"2026-06-07T03:31:41.596Z","changelog":"Refresh publisher identity and metadata for madebydia","fileCount":6,"zipByteSize":9393},{"version":"2.0.0","createdAt":"2026-03-24T17:18:08.340Z","changelog":"Add metadata, fix ClawHub listing","fileCount":5,"zipByteSize":8612},{"version":"1.1.0","createdAt":"2026-02-25T03:24:32.056Z","changelog":"Added 'covered' command for cross-report dedup checking. Fixed DATA_FILE path resolution to find workspace currents.json. Updated cron prompt to check covered topics before researching.","fileCount":4,"zipByteSize":7454},{"version":"1.0.1","createdAt":"2026-02-22T17:47:16.077Z","changelog":"Clarify architecture: shipped code is a thread management CLI, web research is performed by the agent using its standard web_search/web_fetch tools.","fileCount":3,"zipByteSize":4971},{"version":"1.0.0","createdAt":"2026-02-22T17:12:23.165Z","changelog":"Initial release: nightly autonomous research engine with persistent threads, web search, and dense briefings.","fileCount":3,"zipByteSize":4625}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s176b3312npmthbt2chf2mccw183grfh:deep-current","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","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-madebydia-deep-current/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-madebydia-deep-current/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-madebydia-deep-current/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-madebydia-deep-current/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-madebydia-deep-current/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-madebydia-deep-current/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T14:43:17.940Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-madebydia-deep-current/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-madebydia-deep-current/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-madebydia-deep-current/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-madebydia-deep-current/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":"2026-10-10T12:26:32.550Z","emptyReason":null},"readme":"Skill: Deep Current\n\nOwner: madebydia\n\nSummary: Persistent research thread manager with a CLI for tracking topics, notes, sources, and findings. Pair with a nightly cron job to build a personal research di...\n\nTags: latest:2.0.1\n\nVersion history:\n\nv2.0.1 | 2026-06-07T03:31:41.596Z | user\n\nRefresh publisher identity and metadata for madebydia\n\nv2.0.0 | 2026-03-24T17:18:08.340Z | user\n\nAdd metadata, fix ClawHub listing\n\nv1.1.0 | 2026-02-25T03:24:32.056Z | user\n\nAdded 'covered' command for cross-report dedup checking. Fixed DATA_FILE path resolution to find workspace currents.json. Updated cron prompt to check covered topics before researching.\n\nv1.0.1 | 2026-02-22T17:47:16.077Z | user\n\nClarify architecture: shipped code is a thread management CLI, web research is performed by the agent using its standard web_search/web_fetch tools.\n\nv1.0.0 | 2026-02-22T17:12:23.165Z | user\n\nInitial release: nightly autonomous research engine with persistent threads, web search, and dense briefings.\n\nArchive index:\n\nArchive v2.0.1: 6 files, 9393 bytes\n\nFiles: LICENSE (1067b), README.md (3171b), scripts/deep-current.py (10318b), skill-card.md (1921b), SKILL.md (4808b), _meta.json (131b)\n\nFile v2.0.1:SKILL.md\n\n---\nname: deep-current\ndescription: Persistent research thread manager with a CLI for tracking topics, notes, sources, and findings. Pair with a nightly cron job to build a personal research digest over time. The shipped code is a local Python CLI for thread management — research is performed by the agent using its standard web_search and web_fetch tools.\nmetadata: {\"openclaw\":{\"requires\":{\"bins\":[\"python3\"]},\"writablePaths\":[\"deep-current/\",\"deep-current-reports/\"],\"homepage\":\"https://github.com/madebydia/deep-current\",\"author\":\"Diana Park (@madebydia)\"}}\n---\n\n# Deep Current\n\nA research thread manager for agents. Track topics you care about, accumulate notes and sources over time, and pair with a scheduled cron job to produce regular research digests.\n\n## Architecture\n\nThis skill ships **one component**: a Python CLI (`scripts/deep-current.py`) that manages research threads as local JSON data. It handles:\n- Creating, listing, and updating research threads\n- Storing notes, sources, and findings per thread\n- Thread lifecycle (active/paused/resolved) and decay\n\n**What this skill does NOT ship:** web search, link following, or report generation. Those capabilities come from the agent's built-in tools (`web_search`, `web_fetch`). The cron job prompt instructs the agent to use those tools to research threads, then write findings to a report file.\n\nIn short: the CLI manages *what* to research. The agent's existing tools do the *how*.\n\n## How It Works\n\n1. **Threads** — Long-running research topics stored in `deep-current/currents.json`\n2. **Nightly job** — A cron job tells the agent which threads to research (agent uses its own `web_search`/`web_fetch` tools)\n3. **Reports** — Each night's findings are written to `deep-current-reports/YYYY-MM-DD.md` (one file per run)\n4. **Thread CLI** — Manage threads between sessions (add, note, source, finding, status)\n\n## Setup\n\n### 1. Create data directory\n\n```bash\nmkdir -p deep-current\n```\n\n### 2. Initialize currents.json\n\n```json\n{\n  \"threads\": []\n}\n```\n\n### 3. Schedule the cron job\n\nCreate an isolated cron job that runs nightly. The agent will use its own `web_search` and `web_fetch` tools to research each thread, then use the CLI to record findings. Example prompt:\n\n```\nYou are running a Deep Current research session.\n\n1. Run `python3 scripts/deep-current.py list` to see all active threads.\n2. Run `python3 scripts/deep-current.py covered` to see topics and URLs already covered in recent reports. AVOID repeating these.\n3. Pick TWO threads based on current relevance — check recent context to decide.\n4. For each thread, use web_search and web_fetch to research the topic. Follow interesting links and cross-reference claims. Find NEW angles, developments, or sources not already covered.\n5. Update each thread with notes/sources/findings using the deep-current.py CLI.\n\n## Output Format\nCreate a new file in deep-current-reports/ named YYYY-MM-DD.md:\n\n# Deep Current — [tonight's date]\n## [catchy title for thread 1]\n[findings with inline source links]\n## [catchy title for thread 2]\n[findings with inline source links]\n\nKeep it dense and interesting. No fluff. Link to sources. Flag anything actionable.\n```\n\nRecommended: run at 1-3am, use a capable model, 30min timeout.\n\n## Thread CLI\n\nManage research threads with `scripts/deep-current.py`:\n\n| Command | Purpose |\n|---------|---------|\n| `list` | Show all threads with status |\n| `show <id>` | Full thread details |\n| `add <title>` | Create new thread |\n| `note <id> <text>` | Add dated research note |\n| `source <id> <url> [desc]` | Add source/reference |\n| `finding <id> <text>` | Record key finding |\n| `status <id> <active\\|paused\\|resolved>` | Change thread status |\n| `digest` | Summary of all active threads |\n| `decay` | Prune stale threads (>90 days inactive + no recent notes) |\n| `covered [days]` | Show topics & URLs from recent reports (default 14 days) to avoid duplication |\n\nThread IDs are auto-generated slugs from the title. Prefix matching works for short IDs.\n\n## Report Format\n\nEach run creates a standalone file in `deep-current-reports/YYYY-MM-DD.md`. Each report contains:\n- Date header\n- 2+ research threads with catchy titles\n- Dense findings with inline source links\n- Actionable flags for anything the user should act on\n\nOne file per run — easy to browse, search, or archive.\n\n## Research Quality Guidelines\n\nWhen running a research session (nightly or manual), the agent should:\n- Use `web_search` to find sources, `web_fetch` to read them\n- Cross-reference claims across multiple sources\n- Cite sources inline with markdown links\n- Flag actionable items explicitly\n- Write for a smart reader — dense, no filler\n- Use catchy thread titles (this is morning reading, make it engaging)\n- Distinguish speculation from sourced facts\n\nFile v2.0.1:README.md\n\n# Deep Current\n\nA research thread manager for AI agents. Track topics over time, accumulate notes and sources, and pair with scheduled jobs to produce regular research digests.\n\nYour agent picks the threads. Your agent does the searching. This tool keeps the state.\n\n## What It Does\n\n**Ships:** A zero-dependency Python CLI (`scripts/deep-current.py`) that manages research threads as local JSON.\n\n**Doesn't ship:** Web search, link following, or report generation. Those come from your agent's own tools.\n\nThe CLI handles *what* to research. Your agent handles *how*.\n\n## Quick Start\n\n```bash\n# Create a thread\npython3 scripts/deep-current.py add \"Carnivore Diet Research\"\n\n# Add notes, sources, findings as you go\npython3 scripts/deep-current.py note carnivore \"New study on protein satiety in women\"\npython3 scripts/deep-current.py source carnivore \"https://example.com/study\" \"2024 protein satiety meta-analysis\"\npython3 scripts/deep-current.py finding carnivore \"High-protein diets show 25% better satiety scores\"\n\n# See what you're tracking\npython3 scripts/deep-current.py list\npython3 scripts/deep-current.py show carnivore\npython3 scripts/deep-current.py digest\n```\n\n## CLI Reference\n\n| Command | Purpose |\n|---------|---------|\n| `list` | Show all threads with status |\n| `show <id>` | Full thread details |\n| `add <title>` | Create new thread |\n| `note <id> <text>` | Add dated research note |\n| `source <id> <url> [desc]` | Add source/reference |\n| `finding <id> <text>` | Record key finding |\n| `status <id> <active\\|paused\\|resolved>` | Change thread status |\n| `digest` | Summary of all active threads |\n| `decay` | Prune stale threads (>90 days inactive) |\n\nThread IDs are auto-generated slugs. Prefix matching works (`carn` matches `carnivore-diet-research`).\n\n## Agent Integration\n\n### OpenClaw\n\nInstall from [ClawHub](https://clawhub.ai/madebydia/deep-current):\n\n```bash\nopenclaw skills install deep-current\n```\n\nSchedule a nightly cron job that tells your agent to pick threads, research them with `web_search`/`web_fetch`, and write findings to `deep-current-reports/YYYY-MM-DD.md`. See [SKILL.md](SKILL.md) for the full cron prompt template.\n\n### Other Agent Frameworks\n\nThe CLI is framework-agnostic. Any agent that can:\n\n1. Run shell commands (to call the CLI)\n2. Search the web (to do the actual research)\n3. Write files (to output reports)\n\n...can use Deep Current. Point your agent at the CLI, give it a prompt like \"pick a thread, research it, write findings,\" and you're set.\n\n### Manual / Script Use\n\nIt's just Python with no dependencies. Use it as a personal research tracker without any agent at all:\n\n```bash\npython3 scripts/deep-current.py add \"Topic I'm curious about\"\npython3 scripts/deep-current.py note topic \"Found an interesting paper on...\"\npython3 scripts/deep-current.py digest\n```\n\n## Data\n\nEverything lives in `deep-current/currents.json` — a single JSON file. Back it up, version it, move it between machines. Reports go to `deep-current-reports/` as individual dated markdown files.\n\n## License\n\nMIT\n\n---\n\nBuilt by [@madebydia](https://x.com/madebydia) · Available on [ClawHub](https://clawhub.ai/madebydia/deep-current)\n\nFile v2.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn711gxkbyw34qye3faaqw24yn8163fm\",\n  \"slug\": \"deep-current\",\n  \"version\": \"2.0.1\",\n  \"publishedAt\": 1780803101596\n}\n\nFile v2.0.1:skill-card.md\n\n## Description:\n\nDeep Current helps agents maintain long-running research threads with a local Python CLI for topics, notes, sources, findings, and dated markdown reports.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[madebydia](https://clawhub.ai/user/madebydia)\n\n### License/Terms of Use:\n\nMIT\n\n## Use Case:\n\nExternal users and developers use this skill to track ongoing research topics, keep local research state, and guide an agent through scheduled or manual research digest workflows.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill maintains local research state and report files.\n\nMitigation: Use a workspace where deep-current/currents.json and deep-current-reports/ are acceptable write targets, and review generated reports before relying on them.\n\nRisk: The optional nightly workflow can cause the agent to search the web and write reports on a schedule.\n\nMitigation: Review the cron prompt, selected model, timeout, and scheduling policy before enabling unattended runs.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/madebydia/skills/deep-current)\n- [Project homepage](https://github.com/madebydia/deep-current)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [CLI text output, JSON state files, and markdown research reports]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Writes local research state under deep-current/ and dated reports under deep-current-reports/ when configured by the user.]\n\n## Skill Version(s):\n\n2.0.1 (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\nFile v2.0.1:LICENSE\n\nMIT License\n\nCopyright (c) 2026 Diana Park\n\nPermission is hereby granted, free of charge, to any person obtaining a copy\nof this software and associated documentation files (the \"Software\"), to deal\nin the Software without restriction, including without limitation the rights\nto use, copy, modify, merge, publish, distribute, sublicense, and/or sell\ncopies of the Software, and to permit persons to whom the Software is\nfurnished to do so, subject to the following conditions:\n\nThe above copyright notice and this permission notice shall be included in all\ncopies or substantial portions of the Software.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\nIMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\nFITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\nAUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\nLIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\nOUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE\nSOFTWARE.\n\nArchive v2.0.0: 5 files, 8612 bytes\n\nFiles: README.md (3117b), scripts/deep-current.py (10318b), skill-card.md (1845b), SKILL.md (4865b), _meta.json (131b)\n\nFile v2.0.0:SKILL.md\n\n---\nname: deep-current\ndescription: Persistent research thread manager with a CLI for tracking topics, notes, sources, and findings. Pair with a nightly cron job to build a personal research digest over time. The shipped code is a local Python CLI for thread management — research is performed by the agent using its standard web_search and web_fetch tools.\nmetadata: {\"openclaw\":{\"requires\":{\"bins\":[\"python3\"]},\"permissions\":{\"filesystem\":\"read/write within workspace deep-current-reports/ and deep-current-threads/ directories\"},\"homepage\":\"https://github.com/meimakes/deep-current\",\"author\":\"Mei Park (@meimakes)\"}}\n---\n\n# Deep Current\n\nA research thread manager for agents. Track topics you care about, accumulate notes and sources over time, and pair with a scheduled cron job to produce regular research digests.\n\n## Architecture\n\nThis skill ships **one component**: a Python CLI (`scripts/deep-current.py`) that manages research threads as local JSON data. It handles:\n- Creating, listing, and updating research threads\n- Storing notes, sources, and findings per thread\n- Thread lifecycle (active/paused/resolved) and decay\n\n**What this skill does NOT ship:** web search, link following, or report generation. Those capabilities come from the agent's built-in tools (`web_search`, `web_fetch`). The cron job prompt instructs the agent to use those tools to research threads, then write findings to a report file.\n\nIn short: the CLI manages *what* to research. The agent's existing tools do the *how*.\n\n## How It Works\n\n1. **Threads** — Long-running research topics stored in `deep-current/currents.json`\n2. **Nightly job** — A cron job tells the agent which threads to research (agent uses its own `web_search`/`web_fetch` tools)\n3. **Reports** — Each night's findings are written to `deep-current-reports/YYYY-MM-DD.md` (one file per run)\n4. **Thread CLI** — Manage threads between sessions (add, note, source, finding, status)\n\n## Setup\n\n### 1. Create data directory\n\n```bash\nmkdir -p deep-current\n```\n\n### 2. Initialize currents.json\n\n```json\n{\n  \"threads\": []\n}\n```\n\n### 3. Schedule the cron job\n\nCreate an isolated cron job that runs nightly. The agent will use its own `web_search` and `web_fetch` tools to research each thread, then use the CLI to record findings. Example prompt:\n\n```\nYou are running a Deep Current research session.\n\n1. Run `python3 scripts/deep-current.py list` to see all active threads.\n2. Run `python3 scripts/deep-current.py covered` to see topics and URLs already covered in recent reports. AVOID repeating these.\n3. Pick TWO threads based on current relevance — check recent context to decide.\n4. For each thread, use web_search and web_fetch to research the topic. Follow interesting links and cross-reference claims. Find NEW angles, developments, or sources not already covered.\n5. Update each thread with notes/sources/findings using the deep-current.py CLI.\n\n## Output Format\nCreate a new file in deep-current-reports/ named YYYY-MM-DD.md:\n\n# Deep Current — [tonight's date]\n## [catchy title for thread 1]\n[findings with inline source links]\n## [catchy title for thread 2]\n[findings with inline source links]\n\nKeep it dense and interesting. No fluff. Link to sources. Flag anything actionable.\n```\n\nRecommended: run at 1-3am, use a capable model, 30min timeout.\n\n## Thread CLI\n\nManage research threads with `scripts/deep-current.py`:\n\n| Command | Purpose |\n|---------|---------|\n| `list` | Show all threads with status |\n| `show <id>` | Full thread details |\n| `add <title>` | Create new thread |\n| `note <id> <text>` | Add dated research note |\n| `source <id> <url> [desc]` | Add source/reference |\n| `finding <id> <text>` | Record key finding |\n| `status <id> <active\\|paused\\|resolved>` | Change thread status |\n| `digest` | Summary of all active threads |\n| `decay` | Prune stale threads (>90 days inactive + no recent notes) |\n| `covered [days]` | Show topics & URLs from recent reports (default 14 days) to avoid duplication |\n\nThread IDs are auto-generated slugs from the title. Prefix matching works for short IDs.\n\n## Report Format\n\nEach run creates a standalone file in `deep-current-reports/YYYY-MM-DD.md`. Each report contains:\n- Date header\n- 2+ research threads with catchy titles\n- Dense findings with inline source links\n- Actionable flags for anything the user should act on\n\nOne file per run — easy to browse, search, or archive.\n\n## Research Quality Guidelines\n\nWhen running a research session (nightly or manual), the agent should:\n- Use `web_search` to find sources, `web_fetch` to read them\n- Cross-reference claims across multiple sources\n- Cite sources inline with markdown links\n- Flag actionable items explicitly\n- Write for a smart reader — dense, no filler\n- Use catchy thread titles (this is morning reading, make it engaging)\n- Distinguish speculation from sourced facts\n\nFile v2.0.0:README.md\n\n# Deep Current\n\nA research thread manager for AI agents. Track topics over time, accumulate notes and sources, and pair with scheduled jobs to produce regular research digests.\n\nYour agent picks the threads. Your agent does the searching. This tool keeps the state.\n\n## What It Does\n\n**Ships:** A zero-dependency Python CLI (`scripts/deep-current.py`) that manages research threads as local JSON.\n\n**Doesn't ship:** Web search, link following, or report generation. Those come from your agent's own tools.\n\nThe CLI handles *what* to research. Your agent handles *how*.\n\n## Quick Start\n\n```bash\n# Create a thread\npython3 scripts/deep-current.py add \"Carnivore Diet Research\"\n\n# Add notes, sources, findings as you go\npython3 scripts/deep-current.py note carnivore \"New study on protein satiety in women\"\npython3 scripts/deep-current.py source carnivore \"https://example.com/study\" \"2024 protein satiety meta-analysis\"\npython3 scripts/deep-current.py finding carnivore \"High-protein diets show 25% better satiety scores\"\n\n# See what you're tracking\npython3 scripts/deep-current.py list\npython3 scripts/deep-current.py show carnivore\npython3 scripts/deep-current.py digest\n```\n\n## CLI Reference\n\n| Command | Purpose |\n|---------|---------|\n| `list` | Show all threads with status |\n| `show <id>` | Full thread details |\n| `add <title>` | Create new thread |\n| `note <id> <text>` | Add dated research note |\n| `source <id> <url> [desc]` | Add source/reference |\n| `finding <id> <text>` | Record key finding |\n| `status <id> <active\\|paused\\|resolved>` | Change thread status |\n| `digest` | Summary of all active threads |\n| `decay` | Prune stale threads (>90 days inactive) |\n\nThread IDs are auto-generated slugs. Prefix matching works (`carn` matches `carnivore-diet-research`).\n\n## Agent Integration\n\n### OpenClaw\n\nInstall from [ClawHub](https://clawhub.com):\n\n```bash\nclawhub install deep-current\n```\n\nSchedule a nightly cron job that tells your agent to pick threads, research them with `web_search`/`web_fetch`, and write findings to `deep-current-reports/YYYY-MM-DD.md`. See [SKILL.md](SKILL.md) for the full cron prompt template.\n\n### Other Agent Frameworks\n\nThe CLI is framework-agnostic. Any agent that can:\n\n1. Run shell commands (to call the CLI)\n2. Search the web (to do the actual research)\n3. Write files (to output reports)\n\n...can use Deep Current. Point your agent at the CLI, give it a prompt like \"pick a thread, research it, write findings,\" and you're set.\n\n### Manual / Script Use\n\nIt's just Python with no dependencies. Use it as a personal research tracker without any agent at all:\n\n```bash\npython3 scripts/deep-current.py add \"Topic I'm curious about\"\npython3 scripts/deep-current.py note topic \"Found an interesting paper on...\"\npython3 scripts/deep-current.py digest\n```\n\n## Data\n\nEverything lives in `deep-current/currents.json` — a single JSON file. Back it up, version it, move it between machines. Reports go to `deep-current-reports/` as individual dated markdown files.\n\n## License\n\nMIT\n\n---\n\nBuilt by [@meimakes](https://x.com/meimakes) · Available on [ClawHub](https://clawhub.com)\n\nFile v2.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn711gxkbyw34qye3faaqw24yn8163fm\",\n  \"slug\": \"deep-current\",\n  \"version\": \"2.0.0\",\n  \"publishedAt\": 1774372688340\n}\n\nFile v2.0.0:skill-card.md\n\n## Description: <br>\nPersistent research thread manager with a local Python CLI for tracking topics, notes, sources, and findings while guiding agents that use their own web tools to build recurring research digests. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[meimakes](https://clawhub.ai/user/meimakes) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers, researchers, and agent users use Deep Current to keep persistent local research threads, record notes, sources, and findings, and guide scheduled agents that produce recurring research digests. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Review before execution as proposals could introduce incorrect or misleading guidance into skills. <br>\nMitigation: Review and scan skill before deployment. <br>\n\n## Reference(s): <br>\n- [ClawHub listing](https://clawhub.ai/meimakes/deep-current) <br>\n- [Project homepage](https://github.com/meimakes/deep-current) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance] <br>\n**Output Format:** [CLI text output, local JSON research-thread state, and Markdown research reports.] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [The skill can persist local thread state and report files; use the scheduled workflow only when unattended web research and local file updates are acceptable.] <br>\n\n## Skill Version(s): <br>\n2.0.0 (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 v1.1.0: 4 files, 7454 bytes\n\nFiles: README.md (3117b), scripts/deep-current.py (10318b), SKILL.md (4603b), _meta.json (131b)\n\nFile v1.1.0:SKILL.md\n\n---\nname: deep-current\ndescription: Persistent research thread manager with a CLI for tracking topics, notes, sources, and findings. Pair with a nightly cron job to build a personal research digest over time. The shipped code is a local Python CLI for thread management — research is performed by the agent using its standard web_search and web_fetch tools.\n---\n\n# Deep Current\n\nA research thread manager for agents. Track topics you care about, accumulate notes and sources over time, and pair with a scheduled cron job to produce regular research digests.\n\n## Architecture\n\nThis skill ships **one component**: a Python CLI (`scripts/deep-current.py`) that manages research threads as local JSON data. It handles:\n- Creating, listing, and updating research threads\n- Storing notes, sources, and findings per thread\n- Thread lifecycle (active/paused/resolved) and decay\n\n**What this skill does NOT ship:** web search, link following, or report generation. Those capabilities come from the agent's built-in tools (`web_search`, `web_fetch`). The cron job prompt instructs the agent to use those tools to research threads, then write findings to a report file.\n\nIn short: the CLI manages *what* to research. The agent's existing tools do the *how*.\n\n## How It Works\n\n1. **Threads** — Long-running research topics stored in `deep-current/currents.json`\n2. **Nightly job** — A cron job tells the agent which threads to research (agent uses its own `web_search`/`web_fetch` tools)\n3. **Reports** — Each night's findings are written to `deep-current-reports/YYYY-MM-DD.md` (one file per run)\n4. **Thread CLI** — Manage threads between sessions (add, note, source, finding, status)\n\n## Setup\n\n### 1. Create data directory\n\n```bash\nmkdir -p deep-current\n```\n\n### 2. Initialize currents.json\n\n```json\n{\n  \"threads\": []\n}\n```\n\n### 3. Schedule the cron job\n\nCreate an isolated cron job that runs nightly. The agent will use its own `web_search` and `web_fetch` tools to research each thread, then use the CLI to record findings. Example prompt:\n\n```\nYou are running a Deep Current research session.\n\n1. Run `python3 scripts/deep-current.py list` to see all active threads.\n2. Run `python3 scripts/deep-current.py covered` to see topics and URLs already covered in recent reports. AVOID repeating these.\n3. Pick TWO threads based on current relevance — check recent context to decide.\n4. For each thread, use web_search and web_fetch to research the topic. Follow interesting links and cross-reference claims. Find NEW angles, developments, or sources not already covered.\n5. Update each thread with notes/sources/findings using the deep-current.py CLI.\n\n## Output Format\nCreate a new file in deep-current-reports/ named YYYY-MM-DD.md:\n\n# Deep Current — [tonight's date]\n## [catchy title for thread 1]\n[findings with inline source links]\n## [catchy title for thread 2]\n[findings with inline source links]\n\nKeep it dense and interesting. No fluff. Link to sources. Flag anything actionable.\n```\n\nRecommended: run at 1-3am, use a capable model, 30min timeout.\n\n## Thread CLI\n\nManage research threads with `scripts/deep-current.py`:\n\n| Command | Purpose |\n|---------|---------|\n| `list` | Show all threads with status |\n| `show <id>` | Full thread details |\n| `add <title>` | Create new thread |\n| `note <id> <text>` | Add dated research note |\n| `source <id> <url> [desc]` | Add source/reference |\n| `finding <id> <text>` | Record key finding |\n| `status <id> <active\\|paused\\|resolved>` | Change thread status |\n| `digest` | Summary of all active threads |\n| `decay` | Prune stale threads (>90 days inactive + no recent notes) |\n| `covered [days]` | Show topics & URLs from recent reports (default 14 days) to avoid duplication |\n\nThread IDs are auto-generated slugs from the title. Prefix matching works for short IDs.\n\n## Report Format\n\nEach run creates a standalone file in `deep-current-reports/YYYY-MM-DD.md`. Each report contains:\n- Date header\n- 2+ research threads with catchy titles\n- Dense findings with inline source links\n- Actionable flags for anything the user should act on\n\nOne file per run — easy to browse, search, or archive.\n\n## Research Quality Guidelines\n\nWhen running a research session (nightly or manual), the agent should:\n- Use `web_search` to find sources, `web_fetch` to read them\n- Cross-reference claims across multiple sources\n- Cite sources inline with markdown links\n- Flag actionable items explicitly\n- Write for a smart reader — dense, no filler\n- Use catchy thread titles (this is morning reading, make it engaging)\n- Distinguish speculation from sourced facts\n\nFile v1.1.0:README.md\n\n# Deep Current\n\nA research thread manager for AI agents. Track topics over time, accumulate notes and sources, and pair with scheduled jobs to produce regular research digests.\n\nYour agent picks the threads. Your agent does the searching. This tool keeps the state.\n\n## What It Does\n\n**Ships:** A zero-dependency Python CLI (`scripts/deep-current.py`) that manages research threads as local JSON.\n\n**Doesn't ship:** Web search, link following, or report generation. Those come from your agent's own tools.\n\nThe CLI handles *what* to research. Your agent handles *how*.\n\n## Quick Start\n\n```bash\n# Create a thread\npython3 scripts/deep-current.py add \"Carnivore Diet Research\"\n\n# Add notes, sources, findings as you go\npython3 scripts/deep-current.py note carnivore \"New study on protein satiety in women\"\npython3 scripts/deep-current.py source carnivore \"https://example.com/study\" \"2024 protein satiety meta-analysis\"\npython3 scripts/deep-current.py finding carnivore \"High-protein diets show 25% better satiety scores\"\n\n# See what you're tracking\npython3 scripts/deep-current.py list\npython3 scripts/deep-current.py show carnivore\npython3 scripts/deep-current.py digest\n```\n\n## CLI Reference\n\n| Command | Purpose |\n|---------|---------|\n| `list` | Show all threads with status |\n| `show <id>` | Full thread details |\n| `add <title>` | Create new thread |\n| `note <id> <text>` | Add dated research note |\n| `source <id> <url> [desc]` | Add source/reference |\n| `finding <id> <text>` | Record key finding |\n| `status <id> <active\\|paused\\|resolved>` | Change thread status |\n| `digest` | Summary of all active threads |\n| `decay` | Prune stale threads (>90 days inactive) |\n\nThread IDs are auto-generated slugs. Prefix matching works (`carn` matches `carnivore-diet-research`).\n\n## Agent Integration\n\n### OpenClaw\n\nInstall from [ClawHub](https://clawhub.com):\n\n```bash\nclawhub install deep-current\n```\n\nSchedule a nightly cron job that tells your agent to pick threads, research them with `web_search`/`web_fetch`, and write findings to `deep-current-reports/YYYY-MM-DD.md`. See [SKILL.md](SKILL.md) for the full cron prompt template.\n\n### Other Agent Frameworks\n\nThe CLI is framework-agnostic. Any agent that can:\n\n1. Run shell commands (to call the CLI)\n2. Search the web (to do the actual research)\n3. Write files (to output reports)\n\n...can use Deep Current. Point your agent at the CLI, give it a prompt like \"pick a thread, research it, write findings,\" and you're set.\n\n### Manual / Script Use\n\nIt's just Python with no dependencies. Use it as a personal research tracker without any agent at all:\n\n```bash\npython3 scripts/deep-current.py add \"Topic I'm curious about\"\npython3 scripts/deep-current.py note topic \"Found an interesting paper on...\"\npython3 scripts/deep-current.py digest\n```\n\n## Data\n\nEverything lives in `deep-current/currents.json` — a single JSON file. Back it up, version it, move it between machines. Reports go to `deep-current-reports/` as individual dated markdown files.\n\n## License\n\nMIT\n\n---\n\nBuilt by [@meimakes](https://x.com/meimakes) · Available on [ClawHub](https://clawhub.com)\n\nFile v1.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn711gxkbyw34qye3faaqw24yn8163fm\",\n  \"slug\": \"deep-current\",\n  \"version\": \"1.1.0\",\n  \"publishedAt\": 1771989872056\n}\n\nArchive v1.0.1: 3 files, 4971 bytes\n\nFiles: scripts/deep-current.py (8031b), SKILL.md (4309b), _meta.json (131b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: deep-current\ndescription: Persistent research thread manager with a CLI for tracking topics, notes, sources, and findings. Pair with a nightly cron job to build a personal research digest over time. The shipped code is a local Python CLI for thread management — research is performed by the agent using its standard web_search and web_fetch tools.\n---\n\n# Deep Current\n\nA research thread manager for agents. Track topics you care about, accumulate notes and sources over time, and pair with a scheduled cron job to produce regular research digests.\n\n## Architecture\n\nThis skill ships **one component**: a Python CLI (`scripts/deep-current.py`) that manages research threads as local JSON data. It handles:\n- Creating, listing, and updating research threads\n- Storing notes, sources, and findings per thread\n- Thread lifecycle (active/paused/resolved) and decay\n\n**What this skill does NOT ship:** web search, link following, or report generation. Those capabilities come from the agent's built-in tools (`web_search`, `web_fetch`). The cron job prompt instructs the agent to use those tools to research threads, then write findings to a report file.\n\nIn short: the CLI manages *what* to research. The agent's existing tools do the *how*.\n\n## How It Works\n\n1. **Threads** — Long-running research topics stored in `deep-current/currents.json`\n2. **Nightly job** — A cron job tells the agent which threads to research (agent uses its own `web_search`/`web_fetch` tools)\n3. **Reports** — Each night's findings are written to `deep-current-reports/YYYY-MM-DD.md` (one file per run)\n4. **Thread CLI** — Manage threads between sessions (add, note, source, finding, status)\n\n## Setup\n\n### 1. Create data directory\n\n```bash\nmkdir -p deep-current\n```\n\n### 2. Initialize currents.json\n\n```json\n{\n  \"threads\": []\n}\n```\n\n### 3. Schedule the cron job\n\nCreate an isolated cron job that runs nightly. The agent will use its own `web_search` and `web_fetch` tools to research each thread, then use the CLI to record findings. Example prompt:\n\n```\nYou are running a Deep Current research session.\n\n1. Run `python3 scripts/deep-current.py list` to see all active threads.\n2. Pick TWO threads based on current relevance — check recent context to decide.\n3. For each thread, use web_search and web_fetch to research the topic. Follow interesting links and cross-reference claims.\n4. Update each thread with notes/sources/findings using the deep-current.py CLI.\n\n## Output Format\nCreate a new file in deep-current-reports/ named YYYY-MM-DD.md:\n\n# Deep Current — [tonight's date]\n## [catchy title for thread 1]\n[findings with inline source links]\n## [catchy title for thread 2]\n[findings with inline source links]\n\nKeep it dense and interesting. No fluff. Link to sources. Flag anything actionable.\n```\n\nRecommended: run at 1-3am, use a capable model, 30min timeout.\n\n## Thread CLI\n\nManage research threads with `scripts/deep-current.py`:\n\n| Command | Purpose |\n|---------|---------|\n| `list` | Show all threads with status |\n| `show <id>` | Full thread details |\n| `add <title>` | Create new thread |\n| `note <id> <text>` | Add dated research note |\n| `source <id> <url> [desc]` | Add source/reference |\n| `finding <id> <text>` | Record key finding |\n| `status <id> <active\\|paused\\|resolved>` | Change thread status |\n| `digest` | Summary of all active threads |\n| `decay` | Prune stale threads (>90 days inactive + no recent notes) |\n\nThread IDs are auto-generated slugs from the title. Prefix matching works for short IDs.\n\n## Report Format\n\nEach run creates a standalone file in `deep-current-reports/YYYY-MM-DD.md`. Each report contains:\n- Date header\n- 2+ research threads with catchy titles\n- Dense findings with inline source links\n- Actionable flags for anything the user should act on\n\nOne file per run — easy to browse, search, or archive.\n\n## Research Quality Guidelines\n\nWhen running a research session (nightly or manual), the agent should:\n- Use `web_search` to find sources, `web_fetch` to read them\n- Cross-reference claims across multiple sources\n- Cite sources inline with markdown links\n- Flag actionable items explicitly\n- Write for a smart reader — dense, no filler\n- Use catchy thread titles (this is morning reading, make it engaging)\n- Distinguish speculation from sourced facts\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn711gxkbyw34qye3faaqw24yn8163fm\",\n  \"slug\": \"deep-current\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1771782436077\n}\n\nArchive v1.0.0: 3 files, 4625 bytes\n\nFiles: scripts/deep-current.py (8031b), SKILL.md (3394b), _meta.json (131b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: deep-current\ndescription: Nightly autonomous research engine that explores topics you care about and writes dense, source-linked briefings. Manages persistent research threads with notes, sources, and findings. Use when setting up automated research, managing research threads, running a research session, or generating research digests. Also use when the user says \"deep current\", \"research thread\", or \"nightly research\".\n---\n\n# Deep Current\n\nAn autonomous research skill. Define topics you care about, schedule a nightly cron, and wake up to dense briefings with sources. Research threads persist across sessions.\n\n## How It Works\n\n1. **Threads** — Long-running research topics stored in `deep-current/currents.json`\n2. **Nightly job** — A cron job picks threads and does deep web research\n3. **Reports** — Each night's findings are written to `deep-current-reports/YYYY-MM-DD.md` (one file per run)\n4. **Thread CLI** — Manage threads between sessions (add, note, source, finding, status)\n\n## Setup\n\n### 1. Create data directory\n\n```bash\nmkdir -p deep-current\n```\n\n### 2. Initialize currents.json\n\n```json\n{\n  \"threads\": []\n}\n```\n\n### 3. Schedule the cron job\n\nCreate an isolated cron job that runs nightly. Example prompt for the cron payload:\n\n```\nYou are running a Deep Current nightly research job.\n\n1. Run `python3 scripts/deep-current.py list` to see all active threads.\n2. Pick TWO threads based on current relevance — check recent context to decide.\n3. For each, search the web extensively, follow interesting links, and write up findings.\n4. Update each thread with notes/sources/findings using the deep-current.py CLI.\n\n## Output Format\nCreate a new file in deep-current-reports/ named YYYY-MM-DD.md:\n\n# Deep Current — [tonight's date]\n## [catchy title for thread 1]\n[findings]\n## [catchy title for thread 2]\n[findings]\n\nKeep it dense and interesting. No fluff. Link to sources. Flag anything actionable.\n```\n\nRecommended: run at 1-3am, use a capable model, 30min timeout.\n\n## Thread CLI\n\nManage research threads with `scripts/deep-current.py`:\n\n| Command | Purpose |\n|---------|---------|\n| `list` | Show all threads with status |\n| `show <id>` | Full thread details |\n| `add <title>` | Create new thread |\n| `note <id> <text>` | Add dated research note |\n| `source <id> <url> [desc]` | Add source/reference |\n| `finding <id> <text>` | Record key finding |\n| `status <id> <active\\|paused\\|resolved>` | Change thread status |\n| `digest` | Summary of all active threads |\n| `decay` | Prune stale threads (>90 days inactive + no recent notes) |\n\nThread IDs are auto-generated slugs from the title. Prefix matching works for short IDs.\n\n## Report Format\n\nEach nightly run creates a standalone file in `deep-current-reports/YYYY-MM-DD.md`. Each report contains:\n- Date header\n- 2+ research threads with catchy titles\n- Dense findings with inline source links\n- Actionable flags for anything the user should act on\n\nOne file per night — easy to browse, search, or archive.\n\n## Research Quality Guidelines\n\nWhen running a research session (nightly or manual):\n- Search extensively — follow links, cross-reference claims\n- Cite sources inline with markdown links\n- Flag actionable items explicitly\n- Write for a smart reader — dense, no filler\n- Use catchy thread titles (this is morning reading, make it engaging)\n- Distinguish speculation from sourced facts\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn711gxkbyw34qye3faaqw24yn8163fm\",\n  \"slug\": \"deep-current\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1771780343165\n}","readmeExcerpt":"Skill: Deep Current Owner: madebydia Summary: Persistent research thread manager with a CLI for tracking topics, notes, sources, and findings. Pair with a nightly cron job to build a personal research di... Tags: latest:2.0.1 Version history: v2.0.1 | 2026-06-07T03:31:41.596Z | user Refresh publisher identity and metadata for madebydia v2.0.0 | 2026-03-24T17:18:08.340Z | user Add metadata, fix ClawHub listing v1.1.0 ","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"mkdir -p deep-current"},{"language":"json","snippet":"{\n  \"threads\": []\n}"},{"language":"text","snippet":"You are running a Deep Current research session.\n\n1. Run `python3 scripts/deep-current.py list` to see all active threads.\n2. Run `python3 scripts/deep-current.py covered` to see topics and URLs already covered in recent reports. AVOID repeating these.\n3. Pick TWO threads based on current relevance — check recent context to decide.\n4. For each thread, use web_search and web_fetch to research the topic. Follow interesting links and cross-reference claims. Find NEW angles, developments, or sources not already covered.\n5. Update each thread with notes/sources/findings using the deep-current.py CLI.\n\n## Output Format\nCreate a new file in deep-current-reports/ named YYYY-MM-DD.md:\n\n# Deep Current — [tonight's date]\n## [catchy title for thread 1]\n[findings with inline source links]\n## [catchy title for thread 2]\n[findings with inline source links]\n\nKeep it dense and interesting. No fluff. Link to sources. Flag anything actionable."},{"language":"bash","snippet":"# Create a thread\npython3 scripts/deep-current.py add \"Carnivore Diet Research\"\n\n# Add notes, sources, findings as you go\npython3 scripts/deep-current.py note carnivore \"New study on protein satiety in women\"\npython3 scripts/deep-current.py source carnivore \"https://example.com/study\" \"2024 protein satiety meta-analysis\"\npython3 scripts/deep-current.py finding carnivore \"High-protein diets show 25% better satiety scores\"\n\n# See what you're tracking\npython3 scripts/deep-current.py list\npython3 scripts/deep-current.py show carnivore\npython3 scripts/deep-current.py digest"},{"language":"bash","snippet":"openclaw skills install deep-current"},{"language":"bash","snippet":"python3 scripts/deep-current.py add \"Topic I'm curious about\"\npython3 scripts/deep-current.py note topic \"Found an interesting paper on...\"\npython3 scripts/deep-current.py digest"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: deep-current\ndescription: Persistent research thread manager with a CLI for tracking topics, notes, sources, and findings. Pair with a nightly cron job to build a personal research digest over time. The shipped code is a local Python CLI for thread management — research is performed by the agent using its standard web_search and web_fetch tools.\nmetadata: {\"openclaw\":{\"requires\":{\"bins\":[\"python3\"]},\"writablePaths\":[\"deep-current/\",\"deep-current-reports/\"],\"homepage\":\"https://github.com/madebydia/deep-current\",\"author\":\"Diana Park (@madebydia)\"}}\n---\n\n# Deep Current\n\nA research thread manager for agents. Track topics you care about, accumulate notes and sources over time, and pair with a scheduled cron job to produce regular research digests.\n\n## Architecture\n\nThis skill ships **one component**: a Python CLI (`scripts/deep-current.py`) that manages research threads as local JSON data. It handles:\n- Creating, listing, and updating research threads\n- Storing notes, sources, and findings per thread\n- Thread lifecycle (active/paused/resolved) and decay\n\n**What this skill does NOT ship:** web search, link following, or report generation. Those capabilities come from the agent's built-in tools (`web_search`, `web_fetch`). The cron job prompt instructs the agent to use those tools to research threads, then write findings to a report file.\n\nIn short: the CLI manages *what* to research. The agent's existing tools do the *how*.\n\n## How It Works\n\n1. **Threads** — Long-running research topics stored in `deep-current/currents.json`\n2. **Nightly job** — A cron job tells the agent which threads to research (agent uses its own `web_search`/`web_fetch` tools)\n3. **Reports** — Each night's findings are written to `deep-current-reports/YYYY-MM-DD.md` (one file per run)\n4. **Thread CLI** — Manage threads between sessions (add, note, source, finding, status)\n\n## Setup\n\n### 1. Create data directory\n\n```bash\nmkdir -p deep-current\n```\n\n### 2. Initialize currents.json\n\n```json\n{\n  \"threads\": []\n}\n```\n\n### 3. Schedule the cron job\n\nCreate an isolated cron job that runs nightly. The agent will use its own `web_search` and `web_fetch` tools to research each thread, then use the CLI to record findings. Example prompt:\n\n```\nYou are running a Deep Current research session.\n\n1. Run `python3 scripts/deep-current.py list` to see all active threads.\n2. Run `python3 scripts/deep-current.py covered` to see topics and URLs already covered in recent reports. AVOID repeating these.\n3. Pick TWO threads based on current relevance — check recent context to decide.\n4. For each thread, use web_search and web_fetch to research the topic. Follow interesting links and cross-reference claims. Find NEW angles, developments, or sources not already covered.\n5. Update each thread with notes/sources/findings using the deep-current.py CLI.\n\n## Output Format\nCreate a new file in deep-current-reports/ named YYYY-MM-DD.md:\n\n# Deep Current — [tonight's date]\n## [catchy title for thread 1]\n[find"},{"path":"README.md","content":"# Deep Current\n\nA research thread manager for AI agents. Track topics over time, accumulate notes and sources, and pair with scheduled jobs to produce regular research digests.\n\nYour agent picks the threads. Your agent does the searching. This tool keeps the state.\n\n## What It Does\n\n**Ships:** A zero-dependency Python CLI (`scripts/deep-current.py`) that manages research threads as local JSON.\n\n**Doesn't ship:** Web search, link following, or report generation. Those come from your agent's own tools.\n\nThe CLI handles *what* to research. Your agent handles *how*.\n\n## Quick Start\n\n```bash\n# Create a thread\npython3 scripts/deep-current.py add \"Carnivore Diet Research\"\n\n# Add notes, sources, findings as you go\npython3 scripts/deep-current.py note carnivore \"New study on protein satiety in women\"\npython3 scripts/deep-current.py source carnivore \"https://example.com/study\" \"2024 protein satiety meta-analysis\"\npython3 scripts/deep-current.py finding carnivore \"High-protein diets show 25% better satiety scores\"\n\n# See what you're tracking\npython3 scripts/deep-current.py list\npython3 scripts/deep-current.py show carnivore\npython3 scripts/deep-current.py digest\n```\n\n## CLI Reference\n\n| Command | Purpose |\n|---------|---------|\n| `list` | Show all threads with status |\n| `show <id>` | Full thread details |\n| `add <title>` | Create new thread |\n| `note <id> <text>` | Add dated research note |\n| `source <id> <url> [desc]` | Add source/reference |\n| `finding <id> <text>` | Record key finding |\n| `status <id> <active\\|paused\\|resolved>` | Change thread status |\n| `digest` | Summary of all active threads |\n| `decay` | Prune stale threads (>90 days inactive) |\n\nThread IDs are auto-generated slugs. Prefix matching works (`carn` matches `carnivore-diet-research`).\n\n## Agent Integration\n\n### OpenClaw\n\nInstall from [ClawHub](https://clawhub.ai/madebydia/deep-current):\n\n```bash\nopenclaw skills install deep-current\n```\n\nSchedule a nightly cron job that tells your agent to pick threads, research them with `web_search`/`web_fetch`, and write findings to `deep-current-reports/YYYY-MM-DD.md`. See [SKILL.md](SKILL.md) for the full cron prompt template.\n\n### Other Agent Frameworks\n\nThe CLI is framework-agnostic. Any agent that can:\n\n1. Run shell commands (to call the CLI)\n2. Search the web (to do the actual research)\n3. Write files (to output reports)\n\n...can use Deep Current. Point your agent at the CLI, give it a prompt like \"pick a thread, research it, write findings,\" and you're set.\n\n### Manual / Script Use\n\nIt's just Python with no dependencies. Use it as a personal research tracker without any agent at all:\n\n```bash\npython3 scripts/deep-current.py add \"Topic I'm curious about\"\npython3 scripts/deep-current.py note topic \"Found an interesting paper on...\"\npython3 scripts/deep-current.py digest\n```\n\n## Data\n\nEverything lives in `deep-current/currents.json` — a single JSON file. Back it up, version it, move it between machines. Reports go to `deep-current-reports/` as ind"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn711gxkbyw34qye3faaqw24yn8163fm\",\n  \"slug\": \"deep-current\",\n  \"version\": \"2.0.1\",\n  \"publishedAt\": 1780803101596\n}"},{"path":"skill-card.md","content":"## Description:\n\nDeep Current helps agents maintain long-running research threads with a local Python CLI for topics, notes, sources, findings, and dated markdown reports.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[madebydia](https://clawhub.ai/user/madebydia)\n\n### License/Terms of Use:\n\nMIT\n\n## Use Case:\n\nExternal users and developers use this skill to track ongoing research topics, keep local research state, and guide an agent through scheduled or manual research digest workflows.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill maintains local research state and report files.\n\nMitigation: Use a workspace where deep-current/currents.json and deep-current-reports/ are acceptable write targets, and review generated reports before relying on them.\n\nRisk: The optional nightly workflow can cause the agent to search the web and write reports on a schedule.\n\nMitigation: Review the cron prompt, selected model, timeout, and scheduling policy before enabling unattended runs.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/madebydia/skills/deep-current)\n- [Project homepage](https://github.com/madebydia/deep-current)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [CLI text output, JSON state files, and markdown research reports]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Writes local research state under deep-current/ and dated reports under deep-current-reports/ when configured by the user.]\n\n## Skill Version(s):\n\n2.0.1 (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."},{"path":"LICENSE","content":"MIT License\n\nCopyright (c) 2026 Diana Park\n\nPermission is hereby granted, free of charge, to any person obtaining a copy\nof this software and associated documentation files (the \"Software\"), to deal\nin the Software without restriction, including without limitation the rights\nto use, copy, modify, merge, publish, distribute, sublicense, and/or sell\ncopies of the Software, and to permit persons to whom the Software is\nfurnished to do so, subject to the following conditions:\n\nThe above copyright notice and this permission notice shall be included in all\ncopies or substantial portions of the Software.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\nIMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\nFITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\nAUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\nLIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\nOUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE\nSOFTWARE."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Persistent research thread manager with a CLI for tracking topics, notes, sources, and findings. Pair with a nightly cron job to build a personal research di... Skill: Deep Current Owner: madebydia Summary: Persistent research thread manager with a CLI for tracking topics, notes, sources, and findings. Pair with a nightly cron job to build a personal research di... Tags: latest:2.0.1 Version history: v2.0.1 | 2026-06-07T03:31:41.596Z | user Refresh publisher identity and metadata for madebydia v2.0.0 | 2026-03-24T17:18:08.340Z | user Add metadata, fix ClawHub listing v1.1.0","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1344,"uniquenessScore":47,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-10T12:26:32.550Z","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":"2026-10-10T12:26:32.550Z","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":"2026-10-10T14:43:17.941Z","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"}]}}}