[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75DMDNMJS9RWHFS8S060M24":3,"skill-same:01M75DMDNMJS9RWHFS8S060M24":107},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":84,"commitSha":85,"skillDirectory":86,"forksCount":87,"repositoryHtmlUrl":88,"repositoryHomepageUrl":6,"ownerHtmlUrl":89,"ownerBlogUrl":90,"ownerDescription":91,"updatedAt":92,"install":93,"resources":106},"01M75DMDNMJS9RWHFS8S060M24","memento",null,"Local persistent memory for OpenClaw agents. Captures conversations, extracts structured facts via LLM, and auto-recalls relevant knowledge before each turn. Privacy-first, all stored data stays local in SQLite.","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\u002Fbraibaud\u002Fmemento\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: memento\ndescription: Local persistent memory for OpenClaw agents. Captures conversations, extracts structured facts via LLM, and auto-recalls relevant knowledge before each turn. Privacy-first, all stored data stays local in SQLite.\nmetadata:\n  version: \"0.6.0\"\n  author: braibaud\n  license: MIT\n  repository: https:\u002F\u002Fgithub.com\u002Fbraibaud\u002FMemento\n  openclaw:\n    emoji: \"🧠\"\n    kind: plugin\n    requires:\n      node: \">=18.0.0\"\n      optionalEnv:\n        - name: ANTHROPIC_API_KEY\n          when: \"Using anthropic\u002F* models for extraction\"\n        - name: OPENAI_API_KEY\n          when: \"Using openai\u002F* models for extraction\"\n        - name: MISTRAL_API_KEY\n          when: \"Using mistral\u002F* models for extraction\"\n        - name: MEMENTO_API_KEY\n          when: \"Generic fallback for any provider\"\n        - name: CLAUDE_CODE_OAUTH_TOKEN\n          when: \"OpenClaw OAuth token for model routing (auto-used when running inside OpenClaw)\"\n        - name: MEMENTO_WORKSPACE_MAIN\n          when: \"Migration only: path to agent workspace for bootstrapping\"\n        - name: MEMENTO_AGENT_PATHS\n          when: \"Deep consolidation CLI: explicit agent:path mappings\"\n      dataFiles:\n        - path: \"~\u002F.engram\u002Fconversations.sqlite\"\n          purpose: \"Main database — conversations, facts, embeddings (local only, never uploaded)\"\n        - path: \"~\u002F.engram\u002Fsegments\u002F*.jsonl\"\n          purpose: \"Human-readable conversation backups (local only)\"\n        - path: \"~\u002F.engram\u002Fmigration-config.json\"\n          purpose: \"Optional: agent workspace paths for one-time migration bootstrap\"\n    install:\n      - id: npm\n        kind: node\n        package: \"@openclaw\u002Fmemento\"\n        label: \"Install Memento plugin (npm)\"\n    extensions:\n      - \".\u002Fsrc\u002Findex.ts\"\n  keywords:\n    - memory\n    - knowledge-base\n    - recall\n    - conversation\n    - extraction\n    - embeddings\n    - sqlite\n    - privacy\n    - local\n    - cross-agent\n---\n\n# Memento — Local Persistent Memory for OpenClaw Agents\n\nMemento gives your agents long-term memory. It captures conversations, extracts structured facts using an LLM, and auto-injects relevant knowledge before each AI turn.\n\n**All stored data stays on your machine — no cloud sync, no subscriptions.** Extraction uses your configured LLM provider; use a local model (Ollama) for fully air-gapped operation.\n\n> ⚠️ **Privacy note:** When `autoExtract` is enabled, conversation segments are sent to your configured LLM provider for fact extraction. If you use a cloud provider (Anthropic, OpenAI, Mistral), that text leaves your machine. For fully local operation, set `extractionModel` to `ollama\u002F\u003Cmodel>` and keep Ollama running locally.\n\n## What It Does\n\n1. **Captures** every conversation turn, buffered per session\n2. **Extracts** structured facts (preferences, decisions, people, action items) via configurable LLM (opt-in — see Privacy section)\n3. **Recalls** relevant facts before each AI turn using FTS5 keyword search + optional semantic embeddings (BGE-M3)\n4. **Respects privacy** — facts are classified as `shared`, `private`, or `secret` based on content, with hard overrides for sensitive categories (medical, financial, credentials)\n5. **Cross-agent knowledge** — shared facts flow between agents with provenance tags; private\u002Fsecret facts never cross boundaries\n\n## Quick Start\n\nInstall the plugin, restart your gateway, and Memento starts capturing automatically. Extraction is **off by default** — enable it explicitly when ready.\n\n### Optional: Semantic Search\n\nDownload a local embedding model for richer recall:\n\n```bash\nmkdir -p ~\u002F.node-llama-cpp\u002Fmodels\ncurl -L -o ~\u002F.node-llama-cpp\u002Fmodels\u002Fbge-m3-Q8_0.gguf \\\n  \"https:\u002F\u002Fhuggingface.co\u002Fgpustack\u002Fbge-m3-GGUF\u002Fresolve\u002Fmain\u002Fbge-m3-Q8_0.gguf\"\n```\n\n## Environment Variables\n\nAll environment variables are **optional** — you only need the one matching your chosen LLM provider:\n\n| Variable | When Needed |\n|----------|-------------|\n| `ANTHROPIC_API_KEY` | Using `anthropic\u002F*` models for extraction |\n| `OPENAI_API_KEY` | Using `openai\u002F*` models for extraction |\n| `MISTRAL_API_KEY` | Using `mistral\u002F*` models for extraction |\n| `MEMENTO_API_KEY` | Generic fallback for any provider |\n| `MEMENTO_WORKSPACE_MAIN` | Migration only: path to agent workspace for bootstrapping |\n\nNo API key needed for `ollama\u002F*` models (local inference).\n\n## Configuration\n\nAdd to your `openclaw.json` under `plugins.entries.memento.config`:\n\n```json\n{\n  \"memento\": {\n    \"autoCapture\": true,\n    \"extractionModel\": \"anthropic\u002Fclaude-sonnet-4-6\",\n    \"extraction\": {\n      \"autoExtract\": true,\n      \"minTurnsForExtraction\": 3\n    },\n    \"recall\": {\n      \"autoRecall\": true,\n      \"maxFacts\": 20,\n      \"crossAgentRecall\": true,\n      \"autoQueryPlanning\": false\n    }\n  }\n}\n```\n\n> **`autoExtract: true`** is an explicit opt-in (default: `false`). When enabled, conversation segments are sent to the configured `extractionModel` for LLM-based fact extraction. Omit or set to `false` to keep everything local.\n\n> **`autoQueryPlanning: true`** is an explicit opt-in (default: `false`). When enabled, a fast LLM call runs before each recall search to expand the query with synonyms and identify relevant categories — improving precision at the cost of one extra LLM call per turn.\n\n## Data Storage\n\nMemento stores all data locally:\n\n| Path | Contents |\n|------|----------|\n| `~\u002F.engram\u002Fconversations.sqlite` | Main database: conversations, facts, embeddings |\n| `~\u002F.engram\u002Fsegments\u002F*.jsonl` | Human-readable conversation backups |\n| `~\u002F.engram\u002Fmigration-config.json` | Optional: migration workspace paths (only for bootstrapping) |\n\n## Privacy & Data Flow\n\n| Feature | Data leaves machine? | Details |\n|---------|---------------------|---------|\n| `autoCapture` (default: `true`) | ❌ No | Writes to local SQLite + JSONL only |\n| `autoExtract` (default: `false`) | ⚠️ Yes, if cloud LLM | Sends conversation text to configured provider. Use `ollama\u002F*` for local. |\n| `autoRecall` (default: `true`) | ❌ No | Reads from local SQLite only |\n| Secret facts | ❌ Never | Filtered from extraction context — never sent to any LLM |\n| Migration | ❌ No | Reads local workspace files, writes to local SQLite |\n\n## Migration (Bootstrap from Existing Memory Files)\n\nMigration is an **optional, one-time** process to seed Memento from existing agent memory\u002Fmarkdown files. It is user-initiated only — never runs automatically.\n\n### What it reads\n\nMigration reads **only** the files you explicitly list in the config. It does **not** scan your filesystem, read arbitrary files, or access anything outside the configured paths.\n\n### Setup\n\n1. Create `~\u002F.engram\u002Fmigration-config.json` or set `MEMENTO_WORKSPACE_MAIN`:\n\n```json\n{\n  \"agents\": [\n    {\n      \"agentId\": \"main\",\n      \"workspace\": \"\u002Fpath\u002Fto\u002Fyour-workspace\",\n      \"paths\": [\"MEMORY.md\", \"memory\u002F*.md\"]\n    }\n  ]\n}\n```\n\n2. **Always dry-run first** to verify exactly which files will be read:\n\n```bash\nnpx tsx src\u002Fextraction\u002Fmigrate.ts --all --dry-run\n```\n\nThe dry-run prints every file path it would read — review this before proceeding.\n\n3. Run the actual migration:\n\n```bash\nnpx tsx src\u002Fextraction\u002Fmigrate.ts --all\n```\n\n### Security notes\n\n- Migration only reads files matching the glob patterns you configure\n- Extracted facts inherit visibility classification (shared\u002Fprivate\u002Fsecret)\n- Secret-classified facts are **never** sent to cloud LLM providers\n- Migration config file is optional — if absent, migration is completely inert\n- The migration script has no network access beyond the configured extraction LLM\n\n## Architecture\n\n- **Capture layer** — hooks `message:received` + `message:sent`, buffers multi-turn segments\n- **Extraction layer** — async LLM extraction with deduplication, occurrence tracking, temporal state transitions (`previous_value`), and knowledge graph relations (including causal edges with `causal_weight`)\n- **Storage layer** — SQLite schema v7 (better-sqlite3) with FTS5 full-text search + optional vector embeddings; knowledge graph (`fact_relations` with `causal_weight`), multi-layer clusters, and temporal transition tracking (`previous_value`)\n- **Recall layer** — optional LLM query planning pre-pass (`autoQueryPlanning`), multi-factor scoring (recency × frequency × category weight), 1-hop graph traversal with causal edge 1.5× boost, injected via `before_prompt_build` hook\n\n## Requirements\n\n- OpenClaw 2026.2.20+\n- Node.js 18+\n- An API key for your preferred LLM provider (for extraction — not needed if extraction is disabled or using Ollama)\n- Optional: GPU for accelerated embedding search (falls back to CPU gracefully)\n\n## Install\n\n```bash\n# From ClawHub\nclawhub install memento\n\n# Or for local development\ngit clone https:\u002F\u002Fgithub.com\u002Fbraibaud\u002FMemento\ncd Memento\nnpm install\n```\n\nNote: `better-sqlite3` includes native bindings that compile during `npm install`. This is expected behavior for SQLite access.\n","# Memento — Local Persistent Memory for OpenClaw Agents\n\nMemento gives your agents long-term memory. It captures conversations, extracts structured facts using an LLM, and auto-injects relevant knowledge before each AI turn.\n\n**All stored data stays on your machine — no cloud sync, no subscriptions.** Extraction uses your configured LLM provider; use a local model (Ollama) for fully air-gapped operation.\n\n> ⚠️ **Privacy note:** When `autoExtract` is enabled, conversation segments are sent to your configured LLM provider for fact extraction. If you use a cloud provider (Anthropic, OpenAI, Mistral), that text leaves your machine. For fully local operation, set `extractionModel` to `ollama\u002F\u003Cmodel>` and keep Ollama running locally.\n\n## What It Does\n\n1. **Captures** every conversation turn, buffered per session\n2. **Extracts** structured facts (preferences, decisions, people, action items) via configurable LLM (opt-in — see Privacy section)\n3. **Recalls** relevant facts before each AI turn using FTS5 keyword search + optional semantic embeddings (BGE-M3)\n4. **Respects privacy** — facts are classified as `shared`, `private`, or `secret` based on content, with hard overrides for sensitive categories (medical, financial, credentials)\n5. **Cross-agent knowledge** — shared facts flow between agents with provenance tags; private\u002Fsecret facts never cross boundaries\n\n## Quick Start\n\nInstall the plugin, restart your gateway, and Memento starts capturing automatically. Extraction is **off by default** — enable it explicitly when ready.\n\n### Optional: Semantic Search\n\nDownload a local embedding model for richer recall:\n\n```bash\nmkdir -p ~\u002F.node-llama-cpp\u002Fmodels\ncurl -L -o ~\u002F.node-llama-cpp\u002Fmodels\u002Fbge-m3-Q8_0.gguf \\\n  \"https:\u002F\u002Fhuggingface.co\u002Fgpustack\u002Fbge-m3-GGUF\u002Fresolve\u002Fmain\u002Fbge-m3-Q8_0.gguf\"\n```\n\n## Environment Variables\n\nAll environment variables are **optional** — you only need the one matching your chosen LLM provider:\n\n| Variable | When Needed |\n|----------|-------------|\n| `ANTHROPIC_API_KEY` | Using `anthropic\u002F*` models for extraction |\n| `OPENAI_API_KEY` | Using `openai\u002F*` models for extraction |\n| `MISTRAL_API_KEY` | Using `mistral\u002F*` models for extraction |\n| `MEMENTO_API_KEY` | Generic fallback for any provider |\n| `MEMENTO_WORKSPACE_MAIN` | Migration only: path to agent workspace for bootstrapping |\n\nNo API key needed for `ollama\u002F*` models (local inference).\n\n## Configuration\n\nAdd to your `openclaw.json` under `plugins.entries.memento.config`:\n\n```json\n{\n  \"memento\": {\n    \"autoCapture\": true,\n    \"extractionModel\": \"anthropic\u002Fclaude-sonnet-4-6\",\n    \"extraction\": {\n      \"autoExtract\": true,\n      \"minTurnsForExtraction\": 3\n    },\n    \"recall\": {\n      \"autoRecall\": true,\n      \"maxFacts\": 20,\n      \"crossAgentRecall\": true,\n      \"autoQueryPlanning\": false\n    }\n  }\n}\n```\n\n> **`autoExtract: true`** is an explicit opt-in (default: `false`). When enabled, conversation segments are sent to the configured `extractionModel` for LLM-based fact extraction. Omit or set to `false` to keep everything local.\n\n> **`autoQueryPlanning: true`** is an explicit opt-in (default: `false`). When enabled, a fast LLM call runs before each recall search to expand the query with synonyms and identify relevant categories — improving precision at the cost of one extra LLM call per turn.\n\n## Data Storage\n\nMemento stores all data locally:\n\n| Path | Contents |\n|------|----------|\n| `~\u002F.engram\u002Fconversations.sqlite` | Main database: conversations, facts, embeddings |\n| `~\u002F.engram\u002Fsegments\u002F*.jsonl` | Human-readable conversation backups |\n| `~\u002F.engram\u002Fmigration-config.json` | Optional: migration workspace paths (only for bootstrapping) |\n\n## Privacy & Data Flow\n\n| Feature | Data leaves machine? | Details |\n|---------|---------------------|---------|\n| `autoCapture` (default: `true`) | ❌ No | Writes to local SQLite + JSONL only |\n| `autoExtract` (default: `false`) | ⚠️ Yes, if cloud LLM | Sends conversation text to configured provider. Use `ollama\u002F*` for local. |\n| `autoRecall` (default: `true`) | ❌ No | Reads from local SQLite only |\n| Secret facts | ❌ Never | Filtered from extraction context — never sent to any LLM |\n| Migration | ❌ No | Reads local workspace files, writes to local SQLite |\n\n## Migration (Bootstrap from Existing Memory Files)\n\nMigration is an **optional, one-time** process to seed Memento from existing agent memory\u002Fmarkdown files. It is user-initiated only — never runs automatically.\n\n### What it reads\n\nMigration reads **only** the files you explicitly list in the config. It does **not** scan your filesystem, read arbitrary files, or access anything outside the configured paths.\n\n### Setup\n\n1. Create `~\u002F.engram\u002Fmigration-config.json` or set `MEMENTO_WORKSPACE_MAIN`:\n\n```json\n{\n  \"agents\": [\n    {\n      \"agentId\": \"main\",\n      \"workspace\": \"\u002Fpath\u002Fto\u002Fyour-workspace\",\n      \"paths\": [\"MEMORY.md\", \"memory\u002F*.md\"]\n    }\n  ]\n}\n```\n\n2. **Always dry-run first** to verify exactly which files will be read:\n\n```bash\nnpx tsx src\u002Fextraction\u002Fmigrate.ts --all --dry-run\n```\n\nThe dry-run prints every file path it would read — review this before proceeding.\n\n3. Run the actual migration:\n\n```bash\nnpx tsx src\u002Fextraction\u002Fmigrate.ts --all\n```\n\n### Security notes\n\n- Migration only reads files matching the glob patterns you configure\n- Extracted facts inherit visibility classification (shared\u002Fprivate\u002Fsecret)\n- Secret-classified facts are **never** sent to cloud LLM providers\n- Migration config file is optional — if absent, migration is completely inert\n- The migration script has no network access beyond the configured extraction LLM\n\n## Architecture\n\n- **Capture layer** — hooks `message:received` + `message:sent`, buffers multi-turn segments\n- **Extraction layer** — async LLM extraction with deduplication, occurrence tracking, temporal state transitions (`previous_value`), and knowledge graph relations (including causal edges with `causal_weight`)\n- **Storage layer** — SQLite schema v7 (better-sqlite3) with FTS5 full-text search + optional vector embeddings; knowledge graph (`fact_relations` with `causal_weight`), multi-layer clusters, and temporal transition tracking (`previous_value`)\n- **Recall layer** — optional LLM query planning pre-pass (`autoQueryPlanning`), multi-factor scoring (recency × frequency × category weight), 1-hop graph traversal with causal edge 1.5× boost, injected via `before_prompt_build` hook\n\n## Requirements\n\n- OpenClaw 2026.2.20+\n- Node.js 18+\n- An API key for your preferred LLM provider (for extraction — not needed if extraction is disabled or using Ollama)\n- Optional: GPU for accelerated embedding search (falls back to CPU gracefully)\n\n## Install\n\n```bash\n# From ClawHub\nclawhub install memento\n\n# Or for local development\ngit clone https:\u002F\u002Fgithub.com\u002Fbraibaud\u002FMemento\ncd Memento\nnpm install\n```\n\nNote: `better-sqlite3` includes native bindings that compile during `npm install`. This is expected behavior for SQLite access.\n",{"name":5,"metadata":24,"description":7},{"author":25,"license":15,"version":26,"keywords":27,"openclaw":38,"repository":83},"braibaud","0.6.0",[28,29,30,31,32,33,34,35,36,37],"memory","knowledge-base","recall","conversation","extraction","embeddings","sqlite","privacy","local","cross-agent",{"kind":39,"emoji":40,"install":41,"requires":47,"extensions":81},"plugin","🧠",[42],{"id":43,"kind":44,"label":45,"package":46},"npm","node","Install Memento plugin (npm)","@openclaw\u002Fmemento",{"node":48,"dataFiles":49,"optionalEnv":59},">=18.0.0",[50,53,56],{"path":51,"purpose":52},"~\u002F.engram\u002Fconversations.sqlite","Main database — conversations, facts, embeddings (local only, never uploaded)",{"path":54,"purpose":55},"~\u002F.engram\u002Fsegments\u002F*.jsonl","Human-readable conversation backups (local only)",{"path":57,"purpose":58},"~\u002F.engram\u002Fmigration-config.json","Optional: agent workspace paths for one-time migration bootstrap",[60,63,66,69,72,75,78],{"name":61,"when":62},"ANTHROPIC_API_KEY","Using anthropic\u002F* models for extraction",{"name":64,"when":65},"OPENAI_API_KEY","Using openai\u002F* models for extraction",{"name":67,"when":68},"MISTRAL_API_KEY","Using mistral\u002F* models for extraction",{"name":70,"when":71},"MEMENTO_API_KEY","Generic fallback for any provider",{"name":73,"when":74},"CLAUDE_CODE_OAUTH_TOKEN","OpenClaw OAuth token for model routing (auto-used when running inside OpenClaw)",{"name":76,"when":77},"MEMENTO_WORKSPACE_MAIN","Migration only: path to agent workspace for bootstrapping",{"name":79,"when":80},"MEMENTO_AGENT_PATHS","Deep consolidation CLI: explicit agent:path mappings",[82],".\u002Fsrc\u002Findex.ts","https:\u002F\u002Fgithub.com\u002Fbraibaud\u002FMemento","main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fbraibaud\u002Fmemento",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":8,"skillName":5,"commands":94,"prompt":104,"zipAvailable":105},[95,98,101],{"tool":96,"command":97},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill memento",{"tool":99,"command":100},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill memento",{"tool":102,"command":103},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill memento","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fbraibaud\u002Fmemento\u002FSKILL.md",true,[],[108,116,123,130,137,144],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":115},"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":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":115},"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":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":115},"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":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":136,"publishedAt":115},"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":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":115},"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":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":150,"publishedAt":115},"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",[],[]]