[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75CAM33838SWZP439GEXHAQ":3,"skill-same:01M75CAM33838SWZP439GEXHAQ":45},{"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":24,"forksCount":25,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":28,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M75CAM33838SWZP439GEXHAQ","snipara-mcp",null,"javimosch\u002Fopen-claw-skills","javimosch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12900508?v=4","01M6D3F2AS6PV75ET9PZ1QGP8J","Javier Leandro Arancibia","01M75B8NCTAJG9WH5YNZH7C3D8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Falopez3006\u002Fsnipara-mcp\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"name: Snipara MCP - Smart Documentation Search\ndescription: Find answers in your codebase 10x faster with semantic search. Query multiple repos at once. AI remembers your preferences across sessions.\n\n---\n\n# System Instructions for AI Agents\n\nYou are an AI assistant with access to Snipara MCP tools. Use these tools to provide faster, more accurate answers by querying pre-indexed documentation instead of reading files one-by-one.\n\n## When to Use Snipara Tools\n\n✅ **USE Snipara when:**\n\n- User asks \"How does X work?\" → Use `rlm_ask` or `rlm_context_query`\n- User asks \"Where do we do X?\" → Use `rlm_multi_project_query` (if Team plan)\n- User asks \"What are my preferences?\" → Use `rlm_recall`\n- You need to find code patterns across multiple repos\n- You need to understand architecture\u002Fdocumentation\n\n❌ **DON'T use Snipara when:**\n\n- User asks you to read a SPECIFIC file they named → Use native Read tool\n- User asks you to edit\u002Fwrite code → Use native Edit\u002FWrite tools\n- User asks to run commands → Use native Bash tool\n- Snipara API returns error → Fall back to native tools\n\n## Recommended Workflow\n\n1. **First query:** Always start with `rlm_ask` (fast, works on Free plan)\n2. **If not found:** Try `rlm_context_query` with `search_mode: \"semantic\"` (requires Pro)\n3. **Multi-repo search:** Use `rlm_multi_project_query` if user has Team plan\n4. **Remember decisions:** Use `rlm_remember` to store important info for future sessions\n\n## Error Handling\n\nIf Snipara returns an error:\n\n- Check if user has required plan (Free\u002FPro\u002FTeam)\n- Check if docs are indexed (user needs to upload to dashboard first)\n- Fall back to native Read\u002FGrep\u002FGlob tools\n- Explain to user what went wrong and suggest solution\n\n## Example Usage\n\n```\nUser: \"How does our authentication system work?\"\n\nGood response:\n1. Call rlm_ask(\"authentication system\")\n2. Get relevant docs in 2 seconds\n3. Synthesize answer from returned context\n\nBad response:\n1. Use Grep to search for \"auth\"\n2. Read 10 files sequentially\n3. Hit token limits\n4. Give incomplete answer\n```\n\n---\n\n# Get Started in 2 Minutes\n\n## The Problem You Have Right Now\n\nYour AI assistant searches files one-by-one using grep\u002Ffind. With large codebases:\n\n- ❌ Queries take 20+ seconds\n- ❌ AI reads 50K tokens to answer simple questions\n- ❌ You manually search 5 repos to find \"how we do X\"\n- ❌ AI forgets your preferences next session\n\n## The Solution (30 seconds from now)\n\n```bash\n# 1. Install\npip install snipara-mcp   # Python\nnpm install snipara-mcp   # Node.js\n\n# 2. Get your API key\n# Sign up at https:\u002F\u002Fsnipara.com (Free: 100 queries\u002Fmonth)\n\n# 3. Set environment variable\nexport SNIPARA_API_KEY=\"your-key-here\"\n\n# 4. Add to your MCP client (Claude Code, Cline, Roo Code, etc.)\n# Done! Start using rlm_ask() in your next chat\n```\n\n## Your First Query (Try This Now)\n\n```\nYou: \"How does authentication work in my codebase?\"\n\nBehind the scenes:\n  rlm_context_query(\"authentication\")\n  → 2 seconds later\n  → Returns top 3 relevant docs (3K tokens instead of 50K)\n\nResult: Instant, accurate answer\n```\n\n**Note:** Before querying, index your docs at https:\u002F\u002Fsnipara.com\u002Fdashboard (upload .md\u002F.txt\u002F.mdx files).\n\n---\n\n## Core Capabilities (Pick What You Need)\n\n### 🎯 Quick Answers (Start Here)\n\n**Plan Required:** ✅ FREE (100 queries\u002Fmo)\n\n**Tool:** `rlm_ask`\n**Use when:** You need a fast answer from your docs\n**Example:** `rlm_ask(\"API rate limits\")`\n**Time saved:** 20 seconds → 2 seconds per query\n\n```json\n{ \"query\": \"How do we handle webhooks?\" }\n```\n\n---\n\n### 🔍 Deep Research (Complex Questions)\n\n**Plan Required:** ✅ FREE (keyword only) | 🔥 PRO ($19\u002Fmo for semantic)\n\n**Tool:** `rlm_context_query`\n**Use when:** You need semantic search with precise token control\n**Example:** Find conceptually related content, not just keyword matches\n**Benefit:** 90% context reduction (500K → 5K tokens)\n\n```json\n{\n  \"query\": \"authentication implementation\",\n  \"max_tokens\": 6000,\n  \"search_mode\": \"hybrid\"\n}\n```\n\n**Search modes by plan:**\n\n- `keyword` - Fast term matching ✅ **FREE**\n- `semantic` - Embedding similarity 🔥 **PRO+**\n- `hybrid` - Best of both worlds 🔥 **PRO+**\n\n---\n\n### 🌐 Multi-Repo Search\n\n**Plan Required:** 👥 TEAM ($49\u002Fmo) or ENTERPRISE\n\n**Tool:** `rlm_multi_project_query`\n**Use when:** You have 5+ repos and don't know which has the answer\n**Example:** One query searches ALL your team's projects\n**Time saved:** 5 minutes of manual searching → 3 seconds\n\n```json\n{\n  \"query\": \"Where do we send email notifications?\",\n  \"project_ids\": [],\n  \"max_tokens\": 8000\n}\n```\n\n⚠️ **Not available on Free\u002FPro plans** - Requires Team plan for multi-project access.\n\n---\n\n### 🧠 AI Memory (Remember Preferences)\n\n**Plan Required:** 🔥 PRO ($39\u002Fmo Agents) or 👥 TEAM ($79\u002Fmo Agents)\n\n**Tools:** `rlm_remember` + `rlm_recall`\n**Use when:** You want AI to remember your coding style\u002Fdecisions\n**Benefit:** Consistent code across sessions\n\n**Store a memory:**\n\n```json\n{\n  \"content\": \"User prefers TypeScript strict mode with functional components\",\n  \"type\": \"preference\",\n  \"scope\": \"project\"\n}\n```\n\n**Recall later:**\n\n```json\n{\n  \"query\": \"What are my coding preferences?\",\n  \"limit\": 5\n}\n```\n\n**Memory types:** `fact`, `decision`, `learning`, `preference`, `todo`, `context`\n\n⚠️ **Requires separate Agents plan** - Memory is part of Agents features, not Context plans.\n\n---\n\n### 👥 Team Standards (Auto-Enforce Rules)\n\n**Plan Required:** 👥 TEAM ($49\u002Fmo) or ENTERPRISE\n\n**Tool:** `rlm_shared_context`\n**Use when:** Your team needs consistent coding practices\n**Setup once:** Upload coding standards to Shared Collection\n**Every dev gets:** Auto-injected team rules in every query\n\n```json\n{\n  \"categories\": [\"MANDATORY\", \"BEST_PRACTICES\"],\n  \"max_tokens\": 4000\n}\n```\n\n**Categories by priority:**\n\n- `MANDATORY` - Non-negotiable rules (security, architecture)\n- `BEST_PRACTICES` - Recommended patterns (40% token budget)\n- `GUIDELINES` - Helpful suggestions\n- `REFERENCE` - Background info\n\n⚠️ **Not available on Free\u002FPro plans** - Team-wide features require Team plan.\n\n---\n\n### 🔧 Power User Tools\n\n**Multi-Query (Parallel Searches):**\n\n```json\n{\n  \"queries\": [\n    { \"query\": \"auth flow\", \"max_tokens\": 3000 },\n    { \"query\": \"session management\", \"max_tokens\": 3000 }\n  ]\n}\n```\n\n**Decompose (Break Down Complex Questions):**\n\n```json\n{ \"query\": \"Explain the complete payment system architecture\" }\n```\n\n**Plan (Preview Execution):**\n\n```json\n{ \"query\": \"Find all API endpoints\", \"strategy\": \"relevance_first\" }\n```\n\n**Search (Regex Pattern Matching):**\n\n```json\n{ \"pattern\": \"async def|async function\", \"max_results\": 20 }\n```\n\n**Session Context (Inject Standards):**\n\n```json\n{ \"context\": \"Use Python 3.11+, prefer dataclasses over Pydantic\" }\n```\n\n---\n\n### 📄 Document Management\n\n**Upload Single Doc:**\n\n```json\n{ \"path\": \"docs\u002Fapi.md\", \"content\": \"# API Documentation...\" }\n```\n\n**Bulk Sync (CI\u002FCD Integration):**\n\n```json\n{\n  \"documents\": [\n    { \"path\": \"docs\u002Fauth.md\", \"content\": \"...\" },\n    { \"path\": \"docs\u002Fapi.md\", \"content\": \"...\" }\n  ],\n  \"delete_missing\": false\n}\n```\n\n**Check Stats:**\n\n```json\n{}\n```\n\n---\n\n## ROI Calculator\n\n### Scenario 1: Solo Developer (Large Codebase)\n\n**Current pain:** Grep\u002Ffind searches take 20+ seconds, read 50K tokens per query\n\n| Metric         | Before Snipara | With Snipara | Savings                  |\n| -------------- | -------------- | ------------ | ------------------------ |\n| Query speed    | 20 seconds     | 2 seconds    | 18 seconds               |\n| Daily queries  | 50             | 50           | -                        |\n| Time per day   | 16 minutes     | 1.6 minutes  | **14.4 min\u002Fday**         |\n| Time per month | 7.2 hours      | 0.72 hours   | **6.5 hours\u002Fmonth**      |\n| **Cost**       | **$0**         | **$0-19\u002Fmo** | **ROI: 6.5 hours saved** |\n\n**Plan recommendation:** Start with **FREE** (100 queries), upgrade to **PRO** ($19\u002Fmo) if you need semantic search.\n\n---\n\n### Scenario 2: Team (5+ Repositories)\n\n**Current pain:** Switch between 5 projects manually, 5 minutes per search\n\n| Metric            | Before Snipara | With Snipara    | Savings                   |\n| ----------------- | -------------- | --------------- | ------------------------- |\n| Multi-repo search | 5 min          | 3 seconds       | 4.97 min                  |\n| Searches per day  | 10             | 10              | -                         |\n| Time per day      | 50 minutes     | 30 seconds      | **49.5 min\u002Fday**          |\n| Time per month    | 24.75 hours    | 0.25 hours      | **24.5 hours\u002Fmonth**      |\n| **Cost**          | **$0**         | **$49\u002Fmo Team** | **ROI: 24.5 hours saved** |\n\n**Plan recommendation:** **TEAM** ($49\u002Fmo) for `rlm_multi_project_query` + shared standards.\n\n---\n\n### Scenario 3: Enterprise (Consistent Standards)\n\n**Current pain:** 10 devs ask \"how do we do X?\" daily, inconsistent code\n\n| Before                         | With Snipara Shared Context               |\n| ------------------------------ | ----------------------------------------- |\n| ❌ Each dev googles\u002Fasks Slack | ✅ Standards auto-injected in every query |\n| ❌ Inconsistent patterns       | ✅ Enforced team conventions              |\n| ❌ Onboarding takes 2 weeks    | ✅ New devs get standards instantly       |\n| ❌ Code review conflicts       | ✅ Code follows standards from day 1      |\n\n**Cost:** $49\u002Fmo Team or $499\u002Fmo Enterprise\n**ROI:** Consistency + faster onboarding = easily 20+ hours\u002Fmonth saved\n\n---\n\n## Quick Start by Use Case\n\n### Use Case 1: \"I have huge docs and grep is slow\"\n\n**Plan:** ✅ FREE (100 queries\u002Fmo)\n\n```bash\n# 1. Index your docs once\nVisit https:\u002F\u002Fsnipara.com\u002Fdashboard → Create project → Upload .md\u002F.txt files\n\n# 2. Query instantly\nrlm_ask(\"How does authentication work?\")\n```\n\n---\n\n### Use Case 2: \"I work on 10 microservices\"\n\n**Plan:** 👥 TEAM ($49\u002Fmo)\n\n```bash\n# 1. Create 10 projects on Snipara dashboard\n# 2. Enable Team plan\n\n# 3. Query all repos at once\nrlm_multi_project_query(\"How do we handle rate limiting?\")\n```\n\n⚠️ **Requires Team plan** - Multi-project search not available on Free\u002FPro.\n\n---\n\n### Use Case 3: \"AI keeps forgetting my preferences\"\n\n**Plan:** 🔥 PRO Agents ($39\u002Fmo) or 👥 TEAM Agents ($79\u002Fmo)\n\n```bash\n# 1. Enable Agents plan (separate from Context plan)\n\n# 2. Store your preferences once\nrlm_remember(type=\"preference\", content=\"Use functional React components\")\n\n# 3. AI recalls them forever\nrlm_recall(\"my coding preferences\")\n```\n\n⚠️ **Requires separate Agents subscription** - Memory features not included in Context plans.\n\n---\n\n## Pricing (Two Subscription Types)\n\n### Context Plans (Documentation Search)\n\n| Plan           | Price   | Queries\u002Fmo | Search Mode       | Multi-Project |\n| -------------- | ------- | ---------- | ----------------- | ------------- |\n| **FREE**       | $0      | 100        | Keyword only      | ❌            |\n| **PRO**        | $19\u002Fmo  | 5,000      | Semantic + Hybrid | ❌            |\n| **TEAM**       | $49\u002Fmo  | 20,000     | Semantic + Hybrid | ✅            |\n| **ENTERPRISE** | $499\u002Fmo | Unlimited  | Semantic + Hybrid | ✅            |\n\n### Agents Plans (Memory & Swarms)\n\n| Plan           | Price   | Prerequisite       | Features                    |\n| -------------- | ------- | ------------------ | --------------------------- |\n| **STARTER**    | $15\u002Fmo  | None               | Basic memory (100 memories) |\n| **PRO**        | $39\u002Fmo  | None               | Unlimited memories, swarms  |\n| **TEAM**       | $79\u002Fmo  | Context TEAM+      | Team-wide memory sharing    |\n| **ENTERPRISE** | $199\u002Fmo | Context ENTERPRISE | Advanced coordination       |\n\n⚠️ **Two separate subscriptions:** Context plans for search, Agents plans for memory\u002Fswarms.\n\n**Try free first:** 100 queries is ~5 days of usage to test value.\n\n---\n\n## Example Workflows\n\n### Example 1: Quick Answer (FREE plan)\n\n```\nUser: \"What are our API rate limits?\"\n\nYou call: rlm_ask(\"API rate limits\")\n\nResult: Returns relevant docs in 2 seconds\n```\n\n---\n\n### Example 2: Semantic Search (PRO plan)\n\n```\nUser: \"How do we validate user input?\"\n\nYou call: rlm_context_query(\"user input validation\", search_mode=\"semantic\")\n\nResult: Finds docs about \"sanitization\", \"XSS prevention\", \"schema validation\"\n        even if they don't contain exact keywords\n```\n\n---\n\n### Example 3: Multi-Repo Search (TEAM plan)\n\n```\nUser: \"Show me all webhook implementations across our projects\"\n\nYou call: rlm_multi_project_query(\"webhook implementation\")\n\nResult: Returns implementations from all 10 microservices in 3 seconds\n```\n\n---\n\n### Example 4: Persistent Memory (PRO Agents plan)\n\n```\nSession 1 (Monday):\n  User: \"I prefer TypeScript strict mode and functional components\"\n  You call: rlm_remember(type=\"preference\", content=\"Prefers TS strict + functional\")\n\nSession 2 (Friday - NEW SESSION):\n  User: \"Create a new React component\"\n  You call: rlm_recall(\"coding preferences\")\n  Result: AI remembers to use functional components from Monday!\n```\n\n---\n\n### Example 5: Team Standards (TEAM plan)\n\n```\nSetup (Admin does once):\n  - Upload coding standards to Shared Context Collection\n  - Link collection to all team projects\n\nEvery developer:\n  User: \"Write a new API endpoint\"\n  You call: rlm_shared_context(categories=[\"MANDATORY\"])\n  Result: Auto-injects team's API design rules, security requirements, etc.\n```\n\n---\n\n## Support & Resources\n\n- **Website:** https:\u002F\u002Fsnipara.com\n- **Documentation:** https:\u002F\u002Fdocs.snipara.com\n- **GitHub:** https:\u002F\u002Fgithub.com\u002Fsnipara\u002Fsnipara-mcp\n- **Issues:** https:\u002F\u002Fgithub.com\u002Fsnipara\u002Fsnipara-mcp\u002Fissues\n- **Email:** support@snipara.com\n\n---\n\n## Quick Tips\n\n1. **Start small:** Use `rlm_ask` for quick answers on FREE plan\n2. **Upgrade smart:** Get PRO when keyword search isn't finding what you need\n3. **Team value:** Multi-project search pays for itself with 5+ repos\n4. **Memory requires separate plan:** Context + Agents are two subscriptions\n5. **Index first:** Upload docs to dashboard before querying\n\n**When in doubt, start with FREE and upgrade based on value received. 🚀**\n\n---\n\n## Complete Tool Reference (For Power Users)\n\n### Query Tools (All Plans)\n\n**rlm_ask** - Quick keyword search\n\n```json\n{ \"query\": \"API rate limits\" }\n```\n\n**rlm_context_query** - Full-featured semantic search\n\n```json\n{\n  \"query\": \"authentication\",\n  \"max_tokens\": 6000,\n  \"search_mode\": \"hybrid\",\n  \"include_metadata\": true\n}\n```\n\n**rlm_search** - Regex pattern search\n\n```json\n{\n  \"pattern\": \"async def|async function\",\n  \"max_results\": 20\n}\n```\n\n**rlm_inject** - Set session context\n\n```json\n{\n  \"context\": \"Use Python 3.11+, prefer dataclasses\",\n  \"append\": false\n}\n```\n\n**rlm_context** - Show current session context\n\n```json\n{}\n```\n\n**rlm_clear_context** - Clear session context\n\n```json\n{}\n```\n\n---\n\n### Advanced Query Tools (Pro+)\n\n**rlm_multi_query** - Parallel queries\n\n```json\n{\n  \"queries\": [\n    { \"query\": \"auth flow\", \"max_tokens\": 3000 },\n    { \"query\": \"session management\", \"max_tokens\": 3000 }\n  ],\n  \"max_tokens\": 8000\n}\n```\n\n**rlm_decompose** - Break down complex questions\n\n```json\n{\n  \"query\": \"Explain payment system architecture\",\n  \"max_depth\": 2\n}\n```\n\n**rlm_plan** - Generate execution plan\n\n```json\n{\n  \"query\": \"Find all API endpoints\",\n  \"strategy\": \"relevance_first\",\n  \"max_tokens\": 16000\n}\n```\n\n---\n\n### Team Tools (Team+ Plan)\n\n**rlm_multi_project_query** - Search across all repos\n\n```json\n{\n  \"query\": \"webhook implementation\",\n  \"project_ids\": [],\n  \"exclude_project_ids\": [],\n  \"max_tokens\": 8000,\n  \"per_project_limit\": 3\n}\n```\n\n**rlm_shared_context** - Get team standards\n\n```json\n{\n  \"categories\": [\"MANDATORY\", \"BEST_PRACTICES\"],\n  \"max_tokens\": 4000,\n  \"include_content\": true\n}\n```\n\n**rlm_list_templates** - Browse prompt templates\n\n```json\n{\n  \"category\": \"code-review\"\n}\n```\n\n**rlm_get_template** - Use template with variables\n\n```json\n{\n  \"slug\": \"security-review\",\n  \"variables\": {\n    \"author\": \"John\",\n    \"pr_number\": \"123\"\n  }\n}\n```\n\n**rlm_list_collections** - List shared collections\n\n```json\n{\n  \"include_public\": true\n}\n```\n\n**rlm_upload_shared_document** - Upload to shared collection\n\n```json\n{\n  \"collection_id\": \"col_abc123\",\n  \"title\": \"TypeScript Standards\",\n  \"content\": \"# Standards...\",\n  \"category\": \"BEST_PRACTICES\",\n  \"priority\": 90\n}\n```\n\n---\n\n### Memory Tools (Agents Plan)\n\n**rlm_remember** - Store memory\n\n```json\n{\n  \"content\": \"User prefers functional components\",\n  \"type\": \"preference\",\n  \"scope\": \"project\",\n  \"category\": \"coding-style\",\n  \"ttl_days\": null\n}\n```\n\n**rlm_recall** - Query memories\n\n```json\n{\n  \"query\": \"What are my preferences?\",\n  \"type\": \"preference\",\n  \"limit\": 5,\n  \"min_relevance\": 0.5\n}\n```\n\n**rlm_memories** - List all memories\n\n```json\n{\n  \"type\": \"preference\",\n  \"category\": \"coding-style\",\n  \"limit\": 20,\n  \"offset\": 0\n}\n```\n\n**rlm_forget** - Delete memories\n\n```json\n{\n  \"memory_id\": \"mem_abc123\"\n}\n```\n\n---\n\n### Document Management Tools\n\n**rlm_upload_document** - Upload single doc\n\n```json\n{\n  \"path\": \"docs\u002Fapi.md\",\n  \"content\": \"# API Documentation...\"\n}\n```\n\n**rlm_sync_documents** - Bulk upload\n\n```json\n{\n  \"documents\": [\n    { \"path\": \"docs\u002Fauth.md\", \"content\": \"...\" },\n    { \"path\": \"docs\u002Fapi.md\", \"content\": \"...\" }\n  ],\n  \"delete_missing\": false\n}\n```\n\n**rlm_store_summary** - Store document summary\n\n```json\n{\n  \"document_path\": \"docs\u002Fapi.md\",\n  \"summary\": \"RESTful API with OAuth2 auth...\",\n  \"summary_type\": \"concise\",\n  \"generated_by\": \"claude-3.5-sonnet\"\n}\n```\n\n**rlm_get_summaries** - Get stored summaries\n\n```json\n{\n  \"document_path\": \"docs\u002Fapi.md\",\n  \"summary_type\": \"concise\"\n}\n```\n\n**rlm_stats** - Get documentation stats\n\n```json\n{}\n```\n\n**rlm_sections** - List indexed sections\n\n```json\n{\n  \"filter\": \"auth\",\n  \"limit\": 50,\n  \"offset\": 0\n}\n```\n\n**rlm_read** - Read specific lines\n\n```json\n{\n  \"start_line\": 1,\n  \"end_line\": 100\n}\n```\n\n---\n\n### Advanced Features (Enterprise)\n\n**rlm_swarm_create** - Create agent swarm\n\n```json\n{\n  \"name\": \"code-review-swarm\",\n  \"description\": \"Parallel code review\",\n  \"max_agents\": 10\n}\n```\n\n**rlm_swarm_join** - Join swarm\n\n```json\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"role\": \"worker\",\n  \"capabilities\": [\"review\", \"test\"]\n}\n```\n\n**rlm_claim** - Claim resource for exclusive access\n\n```json\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"resource_type\": \"file\",\n  \"resource_id\": \"src\u002Fauth.ts\",\n  \"timeout_seconds\": 300\n}\n```\n\n**rlm_release** - Release claimed resource\n\n```json\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"claim_id\": \"claim_abc123\"\n}\n```\n\n**rlm_state_get** - Read swarm state\n\n```json\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"key\": \"progress\"\n}\n```\n\n**rlm_state_set** - Write swarm state\n\n```json\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"key\": \"progress\",\n  \"value\": { \"completed\": 5, \"total\": 10 },\n  \"expected_version\": 1\n}\n```\n\n**rlm_broadcast** - Broadcast event to swarm\n\n```json\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"event_type\": \"task_completed\",\n  \"payload\": { \"task_id\": \"task_1\" }\n}\n```\n\n**rlm_task_create** - Create swarm task\n\n```json\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"title\": \"Review auth module\",\n  \"description\": \"Security review\",\n  \"priority\": 90\n}\n```\n\n**rlm_task_claim** - Claim task from queue\n\n```json\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"task_id\": \"task_abc123\"\n}\n```\n\n**rlm_task_complete** - Mark task complete\n\n```json\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"task_id\": \"task_abc123\",\n  \"success\": true,\n  \"result\": { \"issues_found\": 0 }\n}\n```\n\n---\n\n## Settings & Configuration\n\n**rlm_settings** - Get project settings\n\n```json\n{\n  \"refresh\": false\n}\n```\n\nReturns current project configuration including:\n\n- Max tokens per query\n- Default search mode\n- Rate limits\n- Enabled features\n\n---\n\n**For complete API documentation, visit: https:\u002F\u002Fdocs.snipara.com**\n",{},"main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Falopez3006\u002Fsnipara-mcp",1,"https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills","https:\u002F\u002Fgithub.com\u002Fjavimosch","intrane.fr","Building robust, open-source infrastructure for the commons. AI-leveraged, self-hosted, built to last.","2026-06-07 03:34:58",{"source":7,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill snipara-mcp",{"tool":37,"command":38},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill snipara-mcp",{"tool":40,"command":41},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill snipara-mcp","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Falopez3006\u002Fsnipara-mcp\u002FSKILL.md",true,[],[46,54,61,68,75,82],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":53},"01M778GGXG2VQ0YF31W2MKGMQZ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":53},"01M778G7BH8SBJ9FJ6C3G7CB1K","ceaser","Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir\u002FUltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":53},"01M778FYCJQZWFKKX5FYMK3S47","ceaser-send","Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir\u002FUltraHonk zero-knowledge proofs.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser-send\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":53},"01M778FQQNSEYA3HJKZBPQ4M9Z","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":53},"01M778FGVZX7QA2TF9BFMM37FY","moldium","Post and manage content on the Moldium blog platform. Triggered by \"post to Moldium\", \"write a blog post\", \"publish an article\", etc.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyom45\u002Fmoldium\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":53},"01M778F88D8PQ9MQ0KNW2TJ8ZH","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http:\u002F\u002Fweakaccept.top:8000\u002F.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[],[]]