[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M757BN932CS2GFD8FFZ8CDMS":3,"skill-same:01M757BN932CS2GFD8FFZ8CDMS":105},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":5,"forksCount":13,"repositoryHtmlUrl":24,"repositoryHomepageUrl":6,"ownerHtmlUrl":25,"ownerBlogUrl":26,"ownerDescription":27,"updatedAt":28,"install":29,"resources":42},"01M757BN932CS2GFD8FFZ8CDMS","openclaw",null,"chicago-joe\u002Fmanymems","chicago-joe","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F28772631?v=4","01M757BH8BAJCECP10RF770KGX","Joseph Loss","01M757BH9GKTF48WY2ZDYSQYF1",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fchicago-joe\u002Fmanymems\u002Fblob\u002Fmain\u002Fopenclaw\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"# Claude-Mem OpenClaw Plugin — Setup Guide\n\nThis guide walks through setting up the claude-mem plugin on an OpenClaw gateway. By the end, your agents will have persistent memory across sessions via system prompt context injection, and optionally a real-time observation feed streaming to a messaging channel.\n\n## Quick Install (Recommended)\n\nRun this one-liner to install everything automatically:\n\n```bash\ncurl -fsSL https:\u002F\u002Finstall.cmem.ai\u002Fopenclaw.sh | bash\n```\n\nThe installer handles dependency checks (Bun, uv), plugin installation, memory slot configuration, AI provider setup, worker startup, and optional observation feed configuration — all interactively.\n\n### Install with options\n\nPre-select your AI provider and API key to skip interactive prompts:\n\n```bash\ncurl -fsSL https:\u002F\u002Finstall.cmem.ai\u002Fopenclaw.sh | bash -s -- --provider=gemini --api-key=YOUR_KEY\n```\n\nFor fully unattended installation (defaults to Claude Max Plan, skips observation feed):\n\n```bash\ncurl -fsSL https:\u002F\u002Finstall.cmem.ai\u002Fopenclaw.sh | bash -s -- --non-interactive\n```\n\nTo upgrade an existing installation (preserves settings, updates plugin):\n\n```bash\ncurl -fsSL https:\u002F\u002Finstall.cmem.ai\u002Fopenclaw.sh | bash -s -- --upgrade\n```\n\nAfter installation, skip to [Step 4: Restart the Gateway and Verify](#step-4-restart-the-gateway-and-verify) to confirm everything is working.\n\n---\n\n## Manual Setup\n\nThe steps below are for manual installation if you prefer not to use the automated installer, or need to troubleshoot individual steps.\n\n### Step 1: Clone the Claude-Mem Repo\n\nFirst, clone the claude-mem repository to a location accessible by your OpenClaw gateway. This gives you the worker service source and the plugin code.\n\n```bash\ncd \u002Fopt  # or wherever you want to keep it\ngit clone https:\u002F\u002Fgithub.com\u002Fthedotmack\u002Fclaude-mem.git\ncd claude-mem\nnpm install\nnpm run build\n```\n\nYou'll need **bun** installed for the worker service. If you don't have it:\n\n```bash\ncurl -fsSL https:\u002F\u002Fbun.sh\u002Finstall | bash\n```\n\n### Step 2: Get the Worker Running\n\nThe claude-mem worker is an HTTP service on port 37777. It stores observations, generates summaries, and serves the context timeline. The plugin talks to it over HTTP — it doesn't matter where the worker is running, just that it's reachable on localhost:37777.\n\n#### Check if it's already running\n\nIf this machine also runs Claude Code with claude-mem installed, the worker may already be running:\n\n```bash\ncurl http:\u002F\u002Flocalhost:37777\u002Fapi\u002Fhealth\n```\n\n**Got `{\"status\":\"ok\"}`?** The worker is already running. Skip to Step 3.\n\n**Got connection refused or no response?** The worker isn't running. Continue below.\n\n#### If Claude Code has claude-mem installed\n\nIf claude-mem is installed as a Claude Code plugin (at `~\u002F.claude\u002Fplugins\u002Fmarketplaces\u002Fthedotmack\u002F`), start the worker from that installation:\n\n```bash\ncd ~\u002F.claude\u002Fplugins\u002Fmarketplaces\u002Fthedotmack\nnpm run worker:restart\n```\n\nVerify:\n```bash\ncurl http:\u002F\u002Flocalhost:37777\u002Fapi\u002Fhealth\n```\n\n**Got `{\"status\":\"ok\"}`?** You're set. Skip to Step 3.\n\n**Still not working?** Check `npm run worker:status` for error details, or check that bun is installed and on your PATH.\n\n#### If there's no Claude Code installation\n\nRun the worker from the cloned repo:\n\n```bash\ncd \u002Fopt\u002Fclaude-mem  # wherever you cloned it\nnpm run worker:start\n```\n\nVerify:\n```bash\ncurl http:\u002F\u002Flocalhost:37777\u002Fapi\u002Fhealth\n```\n\n**Got `{\"status\":\"ok\"}`?** You're set. Move to Step 3.\n\n**Still not working?** Debug steps:\n- Check that bun is installed: `bun --version`\n- Check the worker status: `npm run worker:status`\n- Check if something else is using port 37777: `lsof -i :37777`\n- Check logs: `npm run worker:logs` (if available)\n- Try running it directly to see errors: `bun plugin\u002Fscripts\u002Fworker-service.cjs start`\n\n### Step 3: Add the Plugin to Your Gateway\n\nAdd the `claude-mem` plugin to your OpenClaw gateway configuration:\n\n```json\n{\n  \"plugins\": {\n    \"claude-mem\": {\n      \"enabled\": true,\n      \"config\": {\n        \"project\": \"my-project\",\n        \"syncMemoryFile\": true,\n        \"workerPort\": 37777\n      }\n    }\n  }\n}\n```\n\n#### Config fields explained\n\n- **`project`** (string, default: `\"openclaw\"`) — The project name that scopes all observations in the memory database. Use a unique name per gateway\u002Fuse-case so observations don't mix. For example, if this gateway runs a coding bot, use `\"coding-bot\"`.\n\n- **`syncMemoryFile`** (boolean, default: `true`) — When enabled, the plugin injects the observation timeline into each agent's system prompt via the `before_prompt_build` hook. This gives agents cross-session context without writing to MEMORY.md. Set to `false` to disable context injection entirely (observations are still recorded).\n\n- **`syncMemoryFileExclude`** (string[], default: `[]`) — Agent IDs excluded from automatic context injection. Useful for agents that curate their own memory. Observations are still recorded for excluded agents.\n\n- **`workerPort`** (number, default: `37777`) — The port where the claude-mem worker service is listening. Only change this if you configured the worker to use a different port.\n\n---\n\n## Step 4: Restart the Gateway and Verify\n\nRestart your OpenClaw gateway so it picks up the new plugin configuration. After restart, check the gateway logs for:\n\n```\n[claude-mem] OpenClaw plugin loaded — v1.0.0 (worker: 127.0.0.1:37777)\n```\n\nIf you see this, the plugin is loaded. You can also verify by running `\u002Fclaude_mem_status` in any OpenClaw chat:\n\n```\nClaude-Mem Worker Status\nStatus: ok\nPort: 37777\nActive sessions: 0\nObservation feed: disconnected\n```\n\nThe observation feed shows `disconnected` because we haven't configured it yet. That's next.\n\n## Step 5: Verify Observations Are Being Recorded\n\nHave an agent do some work. The plugin automatically records observations through these OpenClaw events:\n\n1. **`before_agent_start`** — Initializes a claude-mem session when the agent starts\n2. **`before_prompt_build`** — Injects the observation timeline into the agent's system prompt (cached for 60s)\n3. **`tool_result_persist`** — Records each tool use (Read, Write, Bash, etc.) as an observation\n4. **`agent_end`** — Summarizes the session and marks it complete\n\nAll of this happens automatically. No additional configuration needed.\n\nTo verify it's working, check the worker's viewer UI at http:\u002F\u002Flocalhost:37777 to see observations appearing after the agent runs.\n\nYou can also check the worker's viewer UI at http:\u002F\u002Flocalhost:37777 to see observations appearing in real time.\n\n## Step 6: Set Up the Observation Feed (Streaming to a Channel)\n\nThe observation feed connects to the claude-mem worker's SSE (Server-Sent Events) stream and forwards every new observation to a messaging channel in real time. Your agents learn things, and you see them learning in your Telegram\u002FDiscord\u002FSlack\u002Fetc.\n\n### What you'll see\n\nEvery time claude-mem creates a new observation from your agent's tool usage, a message like this appears in your channel:\n\n```\n🧠 Claude-Mem Observation\n**Implemented retry logic for API client**\nAdded exponential backoff with configurable max retries to handle transient failures\n```\n\n### Pick your channel\n\nYou need two things:\n- **Channel type** — Must match a channel plugin already running on your OpenClaw gateway\n- **Target ID** — The chat\u002Fchannel\u002Fuser ID where messages go\n\n#### Telegram\n\nChannel type: `telegram`\n\nTo find your chat ID:\n1. Message @userinfobot on Telegram — https:\u002F\u002Ft.me\u002Fuserinfobot\n2. It replies with your numeric chat ID (e.g., `123456789`)\n3. For group chats, the ID is negative (e.g., `-1001234567890`)\n\n```json\n\"observationFeed\": {\n  \"enabled\": true,\n  \"channel\": \"telegram\",\n  \"to\": \"123456789\"\n}\n```\n\n#### Discord\n\nChannel type: `discord`\n\nTo find your channel ID:\n1. Enable Developer Mode in Discord: Settings → Advanced → Developer Mode\n2. Right-click the target channel → Copy Channel ID\n\n```json\n\"observationFeed\": {\n  \"enabled\": true,\n  \"channel\": \"discord\",\n  \"to\": \"1234567890123456789\"\n}\n```\n\n#### Slack\n\nChannel type: `slack`\n\nTo find your channel ID (not the channel name):\n1. Open the channel in Slack\n2. Click the channel name at the top\n3. Scroll to the bottom of the channel details — the ID looks like `C01ABC2DEFG`\n\n```json\n\"observationFeed\": {\n  \"enabled\": true,\n  \"channel\": \"slack\",\n  \"to\": \"C01ABC2DEFG\"\n}\n```\n\n#### Signal\n\nChannel type: `signal`\n\nUse the phone number or group ID configured in your OpenClaw gateway's Signal plugin.\n\n```json\n\"observationFeed\": {\n  \"enabled\": true,\n  \"channel\": \"signal\",\n  \"to\": \"+1234567890\"\n}\n```\n\n#### WhatsApp\n\nChannel type: `whatsapp`\n\nUse the phone number or group JID configured in your OpenClaw gateway's WhatsApp plugin.\n\n```json\n\"observationFeed\": {\n  \"enabled\": true,\n  \"channel\": \"whatsapp\",\n  \"to\": \"+1234567890\"\n}\n```\n\n#### LINE\n\nChannel type: `line`\n\nUse the user ID or group ID from the LINE Developer Console.\n\n```json\n\"observationFeed\": {\n  \"enabled\": true,\n  \"channel\": \"line\",\n  \"to\": \"U1234567890abcdef\"\n}\n```\n\n### Add it to your config\n\nYour complete plugin config should now look like this (using Telegram as an example):\n\n```json\n{\n  \"plugins\": {\n    \"claude-mem\": {\n      \"enabled\": true,\n      \"config\": {\n        \"project\": \"my-project\",\n        \"syncMemoryFile\": true,\n        \"workerPort\": 37777,\n        \"observationFeed\": {\n          \"enabled\": true,\n          \"channel\": \"telegram\",\n          \"to\": \"123456789\"\n        }\n      }\n    }\n  }\n}\n```\n\n### Restart and verify\n\nRestart the gateway. Check the logs for these three lines in order:\n\n```\n[claude-mem] Observation feed starting — channel: telegram, target: 123456789\n[claude-mem] Connecting to SSE stream at http:\u002F\u002Flocalhost:37777\u002Fstream\n[claude-mem] Connected to SSE stream\n```\n\nThen run `\u002Fclaude_mem_feed` in any OpenClaw chat:\n\n```\nClaude-Mem Observation Feed\nEnabled: yes\nChannel: telegram\nTarget: 123456789\nConnection: connected\n```\n\nIf `Connection` shows `connected`, you're done. Have an agent do some work and watch observations stream to your channel.\n\n## Commands Reference\n\nThe plugin registers two commands:\n\n### \u002Fclaude_mem_status\n\nReports worker health and current session state.\n\n```\n\u002Fclaude_mem_status\n```\n\nOutput:\n```\nClaude-Mem Worker Status\nStatus: ok\nPort: 37777\nActive sessions: 2\nObservation feed: connected\n```\n\n### \u002Fclaude_mem_feed\n\nShows observation feed status. Accepts optional `on`\u002F`off` argument.\n\n```\n\u002Fclaude_mem_feed          — show status\n\u002Fclaude_mem_feed on       — request enable (update config to persist)\n\u002Fclaude_mem_feed off      — request disable (update config to persist)\n```\n\n## How It All Works\n\n```\nOpenClaw Gateway\n  │\n  ├── before_agent_start ───→ Init session\n  ├── before_prompt_build ──→ Inject context into system prompt\n  ├── tool_result_persist ──→ Record observation\n  ├── agent_end ────────────→ Summarize + Complete session\n  └── gateway_start ────────→ Reset session tracking + context cache\n                    │\n                    ▼\n         Claude-Mem Worker (localhost:37777)\n           ├── POST \u002Fapi\u002Fsessions\u002Finit\n           ├── POST \u002Fapi\u002Fsessions\u002Fobservations\n           ├── POST \u002Fapi\u002Fsessions\u002Fsummarize\n           ├── POST \u002Fapi\u002Fsessions\u002Fcomplete\n           ├── GET  \u002Fapi\u002Fcontext\u002Finject ──→ System prompt context\n           └── GET  \u002Fstream ─────────────→ SSE → Messaging channels\n```\n\n### System prompt context injection\n\nThe plugin injects the observation timeline into each agent's system prompt via the `before_prompt_build` hook. The content comes from the worker's `GET \u002Fapi\u002Fcontext\u002Finject` endpoint. Context is cached for 60 seconds per project to avoid re-fetching on every LLM turn. The cache is cleared on gateway restart.\n\nThis keeps MEMORY.md under the agent's control for curated long-term memory, while the observation timeline is delivered through the system prompt.\n\n### Observation recording\n\nEvery tool use (Read, Write, Bash, etc.) is sent to the claude-mem worker as an observation. The worker's AI agent processes it into a structured observation with title, subtitle, facts, concepts, and narrative. Tools prefixed with `memory_` are skipped to avoid recursive recording.\n\n### Session lifecycle\n\n- **`before_agent_start`** — Creates a session in the worker.\n- **`before_prompt_build`** — Fetches the observation timeline and returns it as `appendSystemContext`. Cached for 60s.\n- **`tool_result_persist`** — Records observation (fire-and-forget). Tool responses are truncated to 1000 characters.\n- **`agent_end`** — Sends the last assistant message for summarization, then completes the session. Both fire-and-forget.\n- **`gateway_start`** — Clears all session tracking (session IDs, context cache) so agents start fresh.\n\n### Observation feed\n\nA background service connects to the worker's SSE stream and forwards `new_observation` events to a configured messaging channel. The connection auto-reconnects with exponential backoff (1s → 30s max).\n\n## Troubleshooting\n\n| Problem | What to check |\n|---------|---------------|\n| Worker health check fails | Is bun installed? (`bun --version`). Is something else on port 37777? (`lsof -i :37777`). Try running directly: `bun plugin\u002Fscripts\u002Fworker-service.cjs start` |\n| Worker started from Claude Code install but not responding | Check `cd ~\u002F.claude\u002Fplugins\u002Fmarketplaces\u002Fthedotmack && npm run worker:status`. May need `npm run worker:restart`. |\n| Worker started from cloned repo but not responding | Check `cd \u002Fpath\u002Fto\u002Fclaude-mem && npm run worker:status`. Make sure you ran `npm install && npm run build` first. |\n| No context in agent system prompt | Check that `syncMemoryFile` is not set to `false`. Check that the agent's ID is not in `syncMemoryFileExclude`. Verify the worker is running and has observations. |\n| Observations not being recorded | Check gateway logs for `[claude-mem]` messages. The worker must be running and reachable on localhost:37777. |\n| Feed shows `disconnected` | Worker's `\u002Fstream` endpoint not reachable. Check `workerPort` matches the actual worker port. |\n| Feed shows `reconnecting` | Connection dropped. The plugin auto-reconnects — wait up to 30 seconds. |\n| `Unknown channel type` in logs | The channel plugin (e.g., telegram) isn't loaded on your gateway. Make sure the channel is configured and running. |\n| `Observation feed disabled` in logs | Set `observationFeed.enabled` to `true` in your config. |\n| `Observation feed misconfigured` in logs | Both `observationFeed.channel` and `observationFeed.to` are required. |\n| No messages in channel despite `connected` | The feed only sends processed observations, not raw tool usage. There's a 1-2 second delay. Make sure the worker is actually processing observations (check http:\u002F\u002Flocalhost:37777). |\n\n## Full Config Reference\n\n```json\n{\n  \"plugins\": {\n    \"claude-mem\": {\n      \"enabled\": true,\n      \"config\": {\n        \"project\": \"openclaw\",\n        \"syncMemoryFile\": true,\n        \"workerPort\": 37777,\n        \"observationFeed\": {\n          \"enabled\": false,\n          \"channel\": \"telegram\",\n          \"to\": \"123456789\"\n        }\n      }\n    }\n  }\n}\n```\n\n| Field | Type | Default | Description |\n|-------|------|---------|-------------|\n| `project` | string | `\"openclaw\"` | Project name scoping observations in the database |\n| `syncMemoryFile` | boolean | `true` | Inject observation context into agent system prompt |\n| `syncMemoryFileExclude` | string[] | `[]` | Agent IDs excluded from context injection |\n| `workerPort` | number | `37777` | Claude-mem worker service port |\n| `observationFeed.enabled` | boolean | `false` | Stream observations to a messaging channel |\n| `observationFeed.channel` | string | — | Channel type: `telegram`, `discord`, `slack`, `signal`, `whatsapp`, `line` |\n| `observationFeed.to` | string | — | Target chat\u002Fchannel\u002Fuser ID |\n",{},"main","9351205c08d659f36c13c5930b2ce612ff448bbe","https:\u002F\u002Fgithub.com\u002Fchicago-joe\u002Fmanymems","https:\u002F\u002Fgithub.com\u002Fchicago-joe","https:\u002F\u002Fchicagojoe.dev","M.S. Financial Engineering 2019\r\nUniversity of Illinois at Urbana-Champaign","2026-06-10 05:58:26",{"source":7,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add chicago-joe\u002Fmanymems --skill openclaw",{"tool":35,"command":36},"bunx","bunx skills add chicago-joe\u002Fmanymems --skill openclaw",{"tool":38,"command":39},"pnpm","pnpm dlx skills add chicago-joe\u002Fmanymems --skill openclaw","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fchicago-joe\u002Fmanymems\u002Fblob\u002Fmain\u002Fopenclaw\u002FSKILL.md",true,[43,49,53,57,63,67,73,77,81,85,89,93,97,101],{"path":44,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":47,"sourceHtmlUrl":48},".gitignore","OTHER","其他",20,"https:\u002F\u002Fgithub.com\u002Fchicago-joe\u002Fmanymems\u002Fblob\u002Fmain\u002Fopenclaw\u002F.gitignore",{"path":50,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":51,"sourceHtmlUrl":52},".npmignore",14,"https:\u002F\u002Fgithub.com\u002Fchicago-joe\u002Fmanymems\u002Fblob\u002Fmain\u002Fopenclaw\u002F.npmignore",{"path":54,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":55,"sourceHtmlUrl":56},"Dockerfile.e2e",1332,"https:\u002F\u002Fgithub.com\u002Fchicago-joe\u002Fmanymems\u002Fblob\u002Fmain\u002Fopenclaw\u002FDockerfile.e2e",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"e2e-verify.sh","SCRIPT","脚本",5465,"https:\u002F\u002Fgithub.com\u002Fchicago-joe\u002Fmanymems\u002Fblob\u002Fmain\u002Fopenclaw\u002Fe2e-verify.sh",{"path":64,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":65,"sourceHtmlUrl":66},"install.sh",52283,"https:\u002F\u002Fgithub.com\u002Fchicago-joe\u002Fmanymems\u002Fblob\u002Fmain\u002Fopenclaw\u002Finstall.sh",{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"openclaw.plugin.json","REFERENCE","参考文档",3902,"https:\u002F\u002Fgithub.com\u002Fchicago-joe\u002Fmanymems\u002Fblob\u002Fmain\u002Fopenclaw\u002Fopenclaw.plugin.json",{"path":74,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":75,"sourceHtmlUrl":76},"package.json",400,"https:\u002F\u002Fgithub.com\u002Fchicago-joe\u002Fmanymems\u002Fblob\u002Fmain\u002Fopenclaw\u002Fpackage.json",{"path":78,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":79,"sourceHtmlUrl":80},"src\u002Findex.test.ts",41795,"https:\u002F\u002Fgithub.com\u002Fchicago-joe\u002Fmanymems\u002Fblob\u002Fmain\u002Fopenclaw\u002Fsrc\u002Findex.test.ts",{"path":82,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":83,"sourceHtmlUrl":84},"src\u002Findex.ts",35704,"https:\u002F\u002Fgithub.com\u002Fchicago-joe\u002Fmanymems\u002Fblob\u002Fmain\u002Fopenclaw\u002Fsrc\u002Findex.ts",{"path":86,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":87,"sourceHtmlUrl":88},"test-e2e.sh",1204,"https:\u002F\u002Fgithub.com\u002Fchicago-joe\u002Fmanymems\u002Fblob\u002Fmain\u002Fopenclaw\u002Ftest-e2e.sh",{"path":90,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":91,"sourceHtmlUrl":92},"test-install.sh",59722,"https:\u002F\u002Fgithub.com\u002Fchicago-joe\u002Fmanymems\u002Fblob\u002Fmain\u002Fopenclaw\u002Ftest-install.sh",{"path":94,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":95,"sourceHtmlUrl":96},"test-sse-consumer.js",2871,"https:\u002F\u002Fgithub.com\u002Fchicago-joe\u002Fmanymems\u002Fblob\u002Fmain\u002Fopenclaw\u002Ftest-sse-consumer.js",{"path":98,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":99,"sourceHtmlUrl":100},"TESTING.md",6675,"https:\u002F\u002Fgithub.com\u002Fchicago-joe\u002Fmanymems\u002Fblob\u002Fmain\u002Fopenclaw\u002FTESTING.md",{"path":102,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":103,"sourceHtmlUrl":104},"tsconfig.json",544,"https:\u002F\u002Fgithub.com\u002Fchicago-joe\u002Fmanymems\u002Fblob\u002Fmain\u002Fopenclaw\u002Ftsconfig.json",[106,113,120,127,134,141],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":18},"01M76TW5JVMBEGA7V98MC16WKH","wowerpoint","Turn one document into a kawaii NotebookLM slide-deck PDF. Use for \"wowerpoint this\", \"make a deck about \u003Cfile>\", \"turn this report into slides\", or any request to render a single document as shareable narrative slides.","https:\u002F\u002Fgithub.com\u002Fchicago-joe\u002Fmanymems\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fwowerpoint\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":18},"01M76TW3G047YPZRM2DK0YRBXR","what-happened","Investigate why a code block changed using provenance and observations. Use when the user asks \"why did this change\", \"what broke here\", \"what session produced this commit\".","https:\u002F\u002Fgithub.com\u002Fchicago-joe\u002Fmanymems\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fwhat-happened\u002FSKILL.md",[],[],{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":18},"01M76TVXD5JVZ6Q1MFA68JSZ04","weekly-digests","Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for \"weekly digests\", \"week-by-week story\", \"serial timeline\", or \"narrative chapters\" of a project's history.","https:\u002F\u002Fgithub.com\u002Fchicago-joe\u002Fmanymems\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fweekly-digests\u002FSKILL.md",[],[],{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":18},"01M76TVT491VCH2YDQA4XVVFFM","claude-code-plugin-release","Automated semantic versioning and release workflow for Claude Code plugins. Handles version increments across package.json, marketplace.json, plugin.json manifests, npm publishing (so `npx claude-mem@X.Y.Z` resolves), build verification, git tagging, GitHub releases, and changelog generation.","https:\u002F\u002Fgithub.com\u002Fchicago-joe\u002Fmanymems\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fversion-bump\u002FSKILL.md",[],[],{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":140,"publishedAt":18},"01M757DSBWAR27JRAX6QPGDAP6","timeline-report","Generate a \"Journey Into [Project]\" narrative report analyzing a project's entire development history from claude-mem's timeline. Use when asked for a timeline report, project history analysis, development journey, or full project report.","https:\u002F\u002Fgithub.com\u002Fchicago-joe\u002Fmanymems\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Ftimeline-report\u002FSKILL.md",[],[],{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":18},"01M757DNBBDV4NTAPJ9HNQHSTE","smart-explore","Token-optimized structural code search using tree-sitter AST parsing. Use instead of reading full files when you need to understand code structure, find functions, or explore a codebase efficiently.","https:\u002F\u002Fgithub.com\u002Fchicago-joe\u002Fmanymems\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fsmart-explore\u002FSKILL.md",[],[]]