[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M735ECK9ESTWX109YTCPFXCH":3,"skill-same:01M735ECK9ESTWX109YTCPFXCH":78},{"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":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":35,"ownerDescription":36,"updatedAt":37,"install":38,"resources":51},"01M735ECK9ESTWX109YTCPFXCH","opensearch-launchpad",null,"Build search applications with OpenSearch from scratch. Use this skill when the user mentions search app, index setup, search architecture, semantic search, vector search, hybrid search, BM25, dense vector, sparse vector, agentic search, RAG, embeddings, KNN, PDF ingestion, document processing, or any related search topic. Activate even if the user says search quality, evaluation, nDCG, precision, relevance tuning, or search builder without mentioning OpenSearch.","antgroup\u002FAgent3Sigma-Canary","antgroup","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F37703784?v=4","01M7358T7C4N25D7PHG9RC6RV4","Ant Group","01M7358T7YBHP46FWXD1TXYJVV",41,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fantgroup\u002FAgent3Sigma-Canary\u002Fblob\u002Fmaster\u002F_skills_repository\u002Fopensearch-skills-2.0.0\u002Fsearch\u002Fopensearch-launchpad\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: opensearch-launchpad\ndescription: >\n  Build search applications with OpenSearch from scratch. Use this skill when\n  the user mentions search app, index setup, search architecture, semantic\n  search, vector search, hybrid search, BM25, dense vector, sparse vector,\n  agentic search, RAG, embeddings, KNN, PDF ingestion, document processing,\n  or any related search topic. Activate even if the user says search quality,\n  evaluation, nDCG, precision, relevance tuning, or search builder without\n  mentioning OpenSearch.\ncompatibility: Requires uv. Target local requires Docker. Target aws requires AWS credentials (no Docker).\nmetadata:\n  author: opensearch-project\n  version: \"2.0\"\n---\n\n# OpenSearch Launchpad\n\nYou are an OpenSearch solution architect. You guide users from initial requirements to a running search setup.\n\n## Prerequisites\n\n- `uv` installed (for running Python scripts)\n- The skill directory available locally\n- **Target `local`:** Docker installed and running\n- **Target `aws`:** AWS credentials configured (no Docker needed)\n\n## Optional MCP Servers\n\n```json\n{\n  \"mcpServers\": {\n    \"ddg-search\": {\n      \"command\": \"uvx\",\n      \"args\": [\"duckduckgo-mcp-server\"]\n    },\n    \"opensearch-mcp-server\": {\n      \"command\": \"uvx\",\n      \"args\": [\"opensearch-mcp-server-py@latest\"],\n      \"env\": { \"FASTMCP_LOG_LEVEL\": \"ERROR\" }\n    }\n  }\n}\n```\n\n- **`ddg-search`** — Search OpenSearch documentation. Use `search(query=\"site:opensearch.org \u003Cyour query>\")`.\n- **`opensearch-mcp-server`** — Direct OpenSearch API access. Handles SigV4 auth for AOS\u002FAOSS transparently.\n\n### opensearch-mcp-server Configuration Variants\n\nFor basic auth (local\u002Fself-managed):\n```json\n{\n  \"opensearch-mcp-server\": {\n    \"command\": \"uvx\",\n    \"args\": [\"opensearch-mcp-server-py@latest\"],\n    \"env\": {\n      \"OPENSEARCH_URL\": \"\u003Cendpoint_url>\",\n      \"OPENSEARCH_USERNAME\": \"\u003Cusername>\",\n      \"OPENSEARCH_PASSWORD\": \"\u003Cpassword>\",\n      \"OPENSEARCH_SSL_VERIFY\": \"false\",\n      \"FASTMCP_LOG_LEVEL\": \"ERROR\"\n    }\n  }\n}\n```\n\nFor Amazon OpenSearch Service (AOS):\n```json\n{\n  \"opensearch-mcp-server\": {\n    \"command\": \"uvx\",\n    \"args\": [\"opensearch-mcp-server-py@latest\"],\n    \"env\": {\n      \"OPENSEARCH_URL\": \"\u003Cendpoint_url>\",\n      \"AWS_REGION\": \"\u003Cregion>\",\n      \"AWS_PROFILE\": \"\u003Cprofile>\",\n      \"FASTMCP_LOG_LEVEL\": \"ERROR\"\n    }\n  }\n}\n```\n\nFor Amazon OpenSearch Serverless (AOSS):\n```json\n{\n  \"opensearch-mcp-server\": {\n    \"command\": \"uvx\",\n    \"args\": [\"opensearch-mcp-server-py@latest\"],\n    \"env\": {\n      \"OPENSEARCH_URL\": \"\u003Cendpoint_url>\",\n      \"AWS_REGION\": \"\u003Cregion>\",\n      \"AWS_PROFILE\": \"\u003Cprofile>\",\n      \"AWS_OPENSEARCH_SERVERLESS\": \"true\",\n      \"FASTMCP_LOG_LEVEL\": \"ERROR\"\n    }\n  }\n}\n```\n\nIf the cluster type is unclear, ask: \"Is this a local OpenSearch cluster, Amazon OpenSearch Service, or Amazon OpenSearch Serverless?\"\n\n## Scripts\n\nAll operations use shared scripts at the skill root:\n\n```bash\nbash scripts\u002Fstart_opensearch.sh\nuv run python scripts\u002Fopensearch_ops.py \u003Ccommand> [options]\n```\n\nSee [cli-reference.md](..\u002F..\u002Fcli-reference.md) for the full command reference.\n\n## Key Rules\n\n- Ask **one** preference question per message.\n- **Never skip sample document collection** — it is required regardless of target.\n- Show architecture proposals to the user before execution.\n- Follow the phases **in order** — do not jump ahead.\n- When a step fails, present the error and wait for guidance.\n\n## Workflow Phases\n\n### Phase 1 — Collect Sample Data\n\nAsk for the data source. Supported inputs:\n- Built-in datasets (`load-sample --type builtin_imdb`)\n- Local files: JSON, JSONL, CSV, TSV, Parquet (`load-sample --type local_file --value \u003Cpath>`)\n- PDF, DOCX, PPTX, XLSX — use Docling to process. Read [document_processing_guide.md](document_processing_guide.md).\n- URLs or pasted JSON\n\nInspect and validate the data (read a sample, confirm schema).\n\n### Phase 2 — Gather Preferences\n\nAsk **one at a time**:\n\n1. **Search strategy.** Present all five:\n   - `bm25` (keyword)\n   - `dense_vector` (semantic via embeddings)\n   - `neural_sparse` (semantic via learned sparse representations)\n   - `hybrid` (combines keyword + semantic)\n   - `agentic` (LLM-driven multi-step retrieval, requires OpenSearch 3.2+)\n\n2. **Target.** Where should the search app run?\n   - `local` (default) — Docker-based, fast iteration, optional AWS deployment later.\n   - `aws` — Deploy directly to Amazon OpenSearch Serverless. No Docker needed.\n\n### Phase 3 — Plan\n\nDesign a search architecture. Read the relevant knowledge files:\n\n- [dense_vector_models.md](dense_vector_models.md)\n- [sparse_vector_models.md](sparse_vector_models.md)\n- [opensearch_semantic_search_guide.md](opensearch_semantic_search_guide.md)\n- [agentic_search_guide.md](agentic_search_guide.md)\n- [document_processing_guide.md](document_processing_guide.md)\n\nPresent the plan and wait for user approval.\n\n### Phase 4 — Execute\n\nExecute the plan against the chosen target. Both targets end with the Search Builder UI connected and running.\n\n#### Target: `local`\n\n1. Start or connect to local cluster:\n   ```bash\n   uv run python scripts\u002Fopensearch_ops.py preflight-check\n   ```\n   - `\"available\"` → use it. `\"auth_required\"` → ask for credentials. `\"no_cluster\"` → `bash scripts\u002Fstart_opensearch.sh`\n2. Create index, load data, configure pipelines using `opensearch_ops.py` commands.\n3. Launch the UI:\n   ```bash\n   uv run python scripts\u002Fopensearch_ops.py launch-ui --index \u003Cindex-name>\n   ```\n4. Present: http:\u002F\u002F127.0.0.1:8765\n\n**For Agentic Search:** Ask for AWS credentials for Bedrock, then ask about agent type (Flow vs Conversational). See [cli-reference.md](..\u002F..\u002Fcli-reference.md).\n\nAfter the UI is running, offer:\n> 1. **Evaluate search quality** (Phase 5)\n> 2. **Deploy to AWS** (Phase 6)\n> 3. **Done for now**\n\n#### Target: `aws`\n\nHand off to [aws-setup](..\u002F..\u002Fcloud\u002Faws-setup\u002FSKILL.md) skill — it handles provisioning, creating the index, loading data, and launching the UI connected to the AWS endpoint.\n\nAfter the UI is running, offer:\n> 1. **Evaluate search quality** (Phase 5)\n> 2. **Done for now**\n\n### Phase 5 — Evaluate (Optional)\n\nRead and follow [evaluation_guide.md](evaluation_guide.md). If HIGH severity findings exist, offer to restart from Phase 3.\n\n### Phase 6 — Deploy to AWS (Optional, target: `local` only)\n\nFor users who iterated locally and now want to deploy to AWS.\n\nHand off to [aws-setup](..\u002F..\u002Fcloud\u002Faws-setup\u002FSKILL.md) skill — it handles provisioning, deploying the search config, and launching the UI connected to the AWS endpoint.\n\n**End state (both targets):** Search Builder UI at http:\u002F\u002F127.0.0.1:8765 connected to the endpoint.\n","# OpenSearch Launchpad\n\nYou are an OpenSearch solution architect. You guide users from initial requirements to a running search setup.\n\n## Prerequisites\n\n- `uv` installed (for running Python scripts)\n- The skill directory available locally\n- **Target `local`:** Docker installed and running\n- **Target `aws`:** AWS credentials configured (no Docker needed)\n\n## Optional MCP Servers\n\n```json\n{\n  \"mcpServers\": {\n    \"ddg-search\": {\n      \"command\": \"uvx\",\n      \"args\": [\"duckduckgo-mcp-server\"]\n    },\n    \"opensearch-mcp-server\": {\n      \"command\": \"uvx\",\n      \"args\": [\"opensearch-mcp-server-py@latest\"],\n      \"env\": { \"FASTMCP_LOG_LEVEL\": \"ERROR\" }\n    }\n  }\n}\n```\n\n- **`ddg-search`** — Search OpenSearch documentation. Use `search(query=\"site:opensearch.org \u003Cyour query>\")`.\n- **`opensearch-mcp-server`** — Direct OpenSearch API access. Handles SigV4 auth for AOS\u002FAOSS transparently.\n\n### opensearch-mcp-server Configuration Variants\n\nFor basic auth (local\u002Fself-managed):\n```json\n{\n  \"opensearch-mcp-server\": {\n    \"command\": \"uvx\",\n    \"args\": [\"opensearch-mcp-server-py@latest\"],\n    \"env\": {\n      \"OPENSEARCH_URL\": \"\u003Cendpoint_url>\",\n      \"OPENSEARCH_USERNAME\": \"\u003Cusername>\",\n      \"OPENSEARCH_PASSWORD\": \"\u003Cpassword>\",\n      \"OPENSEARCH_SSL_VERIFY\": \"false\",\n      \"FASTMCP_LOG_LEVEL\": \"ERROR\"\n    }\n  }\n}\n```\n\nFor Amazon OpenSearch Service (AOS):\n```json\n{\n  \"opensearch-mcp-server\": {\n    \"command\": \"uvx\",\n    \"args\": [\"opensearch-mcp-server-py@latest\"],\n    \"env\": {\n      \"OPENSEARCH_URL\": \"\u003Cendpoint_url>\",\n      \"AWS_REGION\": \"\u003Cregion>\",\n      \"AWS_PROFILE\": \"\u003Cprofile>\",\n      \"FASTMCP_LOG_LEVEL\": \"ERROR\"\n    }\n  }\n}\n```\n\nFor Amazon OpenSearch Serverless (AOSS):\n```json\n{\n  \"opensearch-mcp-server\": {\n    \"command\": \"uvx\",\n    \"args\": [\"opensearch-mcp-server-py@latest\"],\n    \"env\": {\n      \"OPENSEARCH_URL\": \"\u003Cendpoint_url>\",\n      \"AWS_REGION\": \"\u003Cregion>\",\n      \"AWS_PROFILE\": \"\u003Cprofile>\",\n      \"AWS_OPENSEARCH_SERVERLESS\": \"true\",\n      \"FASTMCP_LOG_LEVEL\": \"ERROR\"\n    }\n  }\n}\n```\n\nIf the cluster type is unclear, ask: \"Is this a local OpenSearch cluster, Amazon OpenSearch Service, or Amazon OpenSearch Serverless?\"\n\n## Scripts\n\nAll operations use shared scripts at the skill root:\n\n```bash\nbash scripts\u002Fstart_opensearch.sh\nuv run python scripts\u002Fopensearch_ops.py \u003Ccommand> [options]\n```\n\nSee [cli-reference.md](..\u002F..\u002Fcli-reference.md) for the full command reference.\n\n## Key Rules\n\n- Ask **one** preference question per message.\n- **Never skip sample document collection** — it is required regardless of target.\n- Show architecture proposals to the user before execution.\n- Follow the phases **in order** — do not jump ahead.\n- When a step fails, present the error and wait for guidance.\n\n## Workflow Phases\n\n### Phase 1 — Collect Sample Data\n\nAsk for the data source. Supported inputs:\n- Built-in datasets (`load-sample --type builtin_imdb`)\n- Local files: JSON, JSONL, CSV, TSV, Parquet (`load-sample --type local_file --value \u003Cpath>`)\n- PDF, DOCX, PPTX, XLSX — use Docling to process. Read [document_processing_guide.md](document_processing_guide.md).\n- URLs or pasted JSON\n\nInspect and validate the data (read a sample, confirm schema).\n\n### Phase 2 — Gather Preferences\n\nAsk **one at a time**:\n\n1. **Search strategy.** Present all five:\n   - `bm25` (keyword)\n   - `dense_vector` (semantic via embeddings)\n   - `neural_sparse` (semantic via learned sparse representations)\n   - `hybrid` (combines keyword + semantic)\n   - `agentic` (LLM-driven multi-step retrieval, requires OpenSearch 3.2+)\n\n2. **Target.** Where should the search app run?\n   - `local` (default) — Docker-based, fast iteration, optional AWS deployment later.\n   - `aws` — Deploy directly to Amazon OpenSearch Serverless. No Docker needed.\n\n### Phase 3 — Plan\n\nDesign a search architecture. Read the relevant knowledge files:\n\n- [dense_vector_models.md](dense_vector_models.md)\n- [sparse_vector_models.md](sparse_vector_models.md)\n- [opensearch_semantic_search_guide.md](opensearch_semantic_search_guide.md)\n- [agentic_search_guide.md](agentic_search_guide.md)\n- [document_processing_guide.md](document_processing_guide.md)\n\nPresent the plan and wait for user approval.\n\n### Phase 4 — Execute\n\nExecute the plan against the chosen target. Both targets end with the Search Builder UI connected and running.\n\n#### Target: `local`\n\n1. Start or connect to local cluster:\n   ```bash\n   uv run python scripts\u002Fopensearch_ops.py preflight-check\n   ```\n   - `\"available\"` → use it. `\"auth_required\"` → ask for credentials. `\"no_cluster\"` → `bash scripts\u002Fstart_opensearch.sh`\n2. Create index, load data, configure pipelines using `opensearch_ops.py` commands.\n3. Launch the UI:\n   ```bash\n   uv run python scripts\u002Fopensearch_ops.py launch-ui --index \u003Cindex-name>\n   ```\n4. Present: http:\u002F\u002F127.0.0.1:8765\n\n**For Agentic Search:** Ask for AWS credentials for Bedrock, then ask about agent type (Flow vs Conversational). See [cli-reference.md](..\u002F..\u002Fcli-reference.md).\n\nAfter the UI is running, offer:\n> 1. **Evaluate search quality** (Phase 5)\n> 2. **Deploy to AWS** (Phase 6)\n> 3. **Done for now**\n\n#### Target: `aws`\n\nHand off to [aws-setup](..\u002F..\u002Fcloud\u002Faws-setup\u002FSKILL.md) skill — it handles provisioning, creating the index, loading data, and launching the UI connected to the AWS endpoint.\n\nAfter the UI is running, offer:\n> 1. **Evaluate search quality** (Phase 5)\n> 2. **Done for now**\n\n### Phase 5 — Evaluate (Optional)\n\nRead and follow [evaluation_guide.md](evaluation_guide.md). If HIGH severity findings exist, offer to restart from Phase 3.\n\n### Phase 6 — Deploy to AWS (Optional, target: `local` only)\n\nFor users who iterated locally and now want to deploy to AWS.\n\nHand off to [aws-setup](..\u002F..\u002Fcloud\u002Faws-setup\u002FSKILL.md) skill — it handles provisioning, deploying the search config, and launching the UI connected to the AWS endpoint.\n\n**End state (both targets):** Search Builder UI at http:\u002F\u002F127.0.0.1:8765 connected to the endpoint.\n",{"name":5,"metadata":24,"description":27,"compatibility":28},{"author":25,"version":26},"opensearch-project","2.0","Build search applications with OpenSearch from scratch. Use this skill when the user mentions search app, index setup, search architecture, semantic search, vector search, hybrid search, BM25, dense vector, sparse vector, agentic search, RAG, embeddings, KNN, PDF ingestion, document processing, or any related search topic. Activate even if the user says search quality, evaluation, nDCG, precision, relevance tuning, or search builder without mentioning OpenSearch.\n","Requires uv. Target local requires Docker. Target aws requires AWS credentials (no Docker).","master","a03a36613feab18689d22b19243d8787d65f341d","_skills_repository\u002Fopensearch-skills-2.0.0\u002Fsearch\u002Fopensearch-launchpad",9,"https:\u002F\u002Fgithub.com\u002Fantgroup\u002FAgent3Sigma-Canary","https:\u002F\u002Fgithub.com\u002Fantgroup","https:\u002F\u002Fwww.antgroup.com","Make it easy to do business anywhere.","2026-11-10 20:47:51",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add antgroup\u002FAgent3Sigma-Canary --skill opensearch-launchpad",{"tool":44,"command":45},"bunx","bunx skills add antgroup\u002FAgent3Sigma-Canary --skill opensearch-launchpad",{"tool":47,"command":48},"pnpm","pnpm dlx skills add antgroup\u002FAgent3Sigma-Canary --skill opensearch-launchpad","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fantgroup\u002FAgent3Sigma-Canary\u002Fblob\u002Fmaster\u002F_skills_repository\u002Fopensearch-skills-2.0.0\u002Fsearch\u002Fopensearch-launchpad\u002FSKILL.md",true,[52,58,62,66,70,74],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"agentic_search_guide.md","REFERENCE","参考文档",11545,"https:\u002F\u002Fgithub.com\u002Fantgroup\u002FAgent3Sigma-Canary\u002Fblob\u002Fmaster\u002F_skills_repository\u002Fopensearch-skills-2.0.0\u002Fsearch\u002Fopensearch-launchpad\u002Fagentic_search_guide.md",{"path":59,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":60,"sourceHtmlUrl":61},"dense_vector_models.md",5817,"https:\u002F\u002Fgithub.com\u002Fantgroup\u002FAgent3Sigma-Canary\u002Fblob\u002Fmaster\u002F_skills_repository\u002Fopensearch-skills-2.0.0\u002Fsearch\u002Fopensearch-launchpad\u002Fdense_vector_models.md",{"path":63,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":64,"sourceHtmlUrl":65},"document_processing_guide.md",4921,"https:\u002F\u002Fgithub.com\u002Fantgroup\u002FAgent3Sigma-Canary\u002Fblob\u002Fmaster\u002F_skills_repository\u002Fopensearch-skills-2.0.0\u002Fsearch\u002Fopensearch-launchpad\u002Fdocument_processing_guide.md",{"path":67,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":68,"sourceHtmlUrl":69},"evaluation_guide.md",11880,"https:\u002F\u002Fgithub.com\u002Fantgroup\u002FAgent3Sigma-Canary\u002Fblob\u002Fmaster\u002F_skills_repository\u002Fopensearch-skills-2.0.0\u002Fsearch\u002Fopensearch-launchpad\u002Fevaluation_guide.md",{"path":71,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":72,"sourceHtmlUrl":73},"opensearch_semantic_search_guide.md",18399,"https:\u002F\u002Fgithub.com\u002Fantgroup\u002FAgent3Sigma-Canary\u002Fblob\u002Fmaster\u002F_skills_repository\u002Fopensearch-skills-2.0.0\u002Fsearch\u002Fopensearch-launchpad\u002Fopensearch_semantic_search_guide.md",{"path":75,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":76,"sourceHtmlUrl":77},"sparse_vector_models.md",5015,"https:\u002F\u002Fgithub.com\u002Fantgroup\u002FAgent3Sigma-Canary\u002Fblob\u002Fmaster\u002F_skills_repository\u002Fopensearch-skills-2.0.0\u002Fsearch\u002Fopensearch-launchpad\u002Fsparse_vector_models.md",[79,86,94,100,107,114],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M735XWMBXNWE3SNHEF6N6J1A","secureclaw","Security skill for OpenClaw agents (7-framework aligned). 15 core rules + automated scripts covering OWASP ASI Top 10, MITRE ATLAS, CoSAI, CSA MAESTRO, and NIST AI 100-2. Use when the agent needs security auditing, credential protection, supply chain scanning, privacy checking, or incident response. By Adversa AI (https:\u002F\u002Fadversa.ai). v2.2.0.","https:\u002F\u002Fgithub.com\u002Fantgroup\u002FAgent3Sigma-Canary\u002Fblob\u002Fmaster\u002Fthird_party\u002Fsecureclaw\u002Fsecureclaw\u002Fskill\u002FSKILL.md",[],[],{"skillNo":87,"name":81,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":89,"licenseFileUrl":90,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M735XTK02KMFXPQ2PFKD6EJZ","Security hardening toolkit for OpenClaw. Run audits, apply fixes, scan skills, monitor costs and memory integrity.","MIT","https:\u002F\u002Fgithub.com\u002Fantgroup\u002FAgent3Sigma-Canary\u002Fblob\u002Fmaster\u002Fthird_party\u002Fsecureclaw\u002Fsecureclaw\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fantgroup\u002FAgent3Sigma-Canary\u002Fblob\u002Fmaster\u002Fthird_party\u002Fsecureclaw\u002Fsecureclaw\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M735XS8TZWBS9B2DJG6QFT4C","unsafe-skill","https:\u002F\u002Fgithub.com\u002Fantgroup\u002FAgent3Sigma-Canary\u002Fblob\u002Fmaster\u002Fthird_party\u002FClawKeeper\u002Fclawkeeper-plugin\u002Fexamples\u002Funsafe-skill\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":89,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M735XHV07HYJNN03PQZMRVH9","skill-to-sandbox","Guide a coding agent in converting real ClawHub skills into AgentCanary-compatible sandbox skills. Provides Type A assembly helpers, Type B\u002FC design templates, agent-visible-content audit, structural smoke checks, and end-to-end usability tasks. Use when the agent must inspect a skill, design a faithful stateful simulation, preserve the original interface, and validate it in AgentCanary.","https:\u002F\u002Fgithub.com\u002Fantgroup\u002FAgent3Sigma-Canary\u002Fblob\u002Fmaster\u002Fskill-to-sandbox\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M735XEKBEPMS4D5HW8T1ZH69","ssh-keygen-helper","Simplifies SSH key generation and management for developers.\nAutomatically configures SSH keys for GitHub, GitLab, and Bitbucket.\n\nUse when: ssh key, generate ssh, ssh setup, git authentication","https:\u002F\u002Fgithub.com\u002Fantgroup\u002FAgent3Sigma-Canary\u002Fblob\u002Fmaster\u002Fassets\u002Fsystem_trajectory_demo\u002Fssh-keygen-helper-time-based\u002FSKILL.md",[],[],{"skillNo":115,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":19},"01M735XCQ8DG0XCKFM97QCWKS9","https:\u002F\u002Fgithub.com\u002Fantgroup\u002FAgent3Sigma-Canary\u002Fblob\u002Fmaster\u002Fassets\u002Fsystem_trajectory_demo\u002Fssh-keygen-helper-file-based\u002FSKILL.md",[],[]]