{ "schemaVersion": "1.0", "item": { "slug": "anshumanbh-qmd", "name": "QMD Search", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/anshumanbh/anshumanbh-qmd", "canonicalUrl": "https://clawhub.ai/anshumanbh/anshumanbh-qmd", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/anshumanbh-qmd", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=anshumanbh-qmd", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-07T17:22:31.273Z", "expiresAt": "2026-05-14T17:22:31.273Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentDisposition": "attachment; filename=\"afrexai-annual-report-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/anshumanbh-qmd" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/anshumanbh-qmd", "agentPageUrl": "https://openagent3.xyz/skills/anshumanbh-qmd/agent", "manifestUrl": "https://openagent3.xyz/skills/anshumanbh-qmd/agent.json", "briefUrl": "https://openagent3.xyz/skills/anshumanbh-qmd/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "QMD Search Skill", "body": "Search markdown knowledge bases efficiently using qmd, a local indexing tool that uses BM25 + vector embeddings to return only relevant snippets instead of full files." }, { "title": "Why Use This", "body": "96% token reduction - Returns relevant snippets instead of reading entire files\nInstant results - Pre-indexed content means fast searches\nLocal & private - All indexing and search happens locally\nHybrid search - BM25 for keyword matching, vector search for semantic similarity" }, { "title": "Search (BM25 keyword matching)", "body": "qmd search \"your query\" --collection \n\nFast, accurate keyword-based search. Best for specific terms or phrases." }, { "title": "Vector Search (semantic)", "body": "qmd vsearch \"your query\" --collection \n\nSemantic similarity search. Best for conceptual queries where exact words may vary." }, { "title": "Hybrid Search (both + reranking)", "body": "qmd hybrid \"your query\" --collection \n\nCombines both approaches with LLM reranking. Most thorough but often overkill." }, { "title": "How to Use", "body": "Check if collection exists:\nqmd collection list\n\n\n\nSearch the collection:\n# For specific terms\nqmd search \"api authentication\" --collection notes\n\n# For conceptual queries\nqmd vsearch \"how to handle errors gracefully\" --collection notes\n\n\n\nRead results: qmd returns relevant snippets with file paths and context" }, { "title": "Setup (if qmd not installed)", "body": "# Install qmd\nbun install -g https://github.com/tobi/qmd\n\n# Add a collection (e.g., Obsidian vault)\nqmd collection add ~/path/to/vault --name notes\n\n# Generate embeddings for vector search\nqmd embed --collection notes" }, { "title": "Invocation Examples", "body": "/qmd api authentication # BM25 search for \"api authentication\"\n/qmd how to handle errors --semantic # Vector search for conceptual query\n/qmd --setup # Guide through initial setup" }, { "title": "Best Practices", "body": "Use BM25 search (qmd search) for specific terms, names, or technical keywords\nUse vector search (qmd vsearch) when looking for concepts where wording may vary\nAvoid hybrid search unless you need maximum recall - it's slower\nRe-run qmd embed after adding significant new content to keep vectors current" }, { "title": "Handling Arguments", "body": "$ARGUMENTS contains the full search query\nIf --semantic flag is present, use qmd vsearch instead of qmd search\nIf --setup flag is present, guide user through installation and collection setup\nIf --collection is specified, use that collection; otherwise default to checking available collections" }, { "title": "Workflow", "body": "Parse arguments from $ARGUMENTS\nCheck if qmd is installed (which qmd)\nIf not installed, offer to guide setup\nIf searching:\n\nList collections if none specified\nRun appropriate search command\nPresent results to user with file paths\n\n\nIf user wants to read a specific result, use the Read tool on the file path" } ], "body": "QMD Search Skill\n\nSearch markdown knowledge bases efficiently using qmd, a local indexing tool that uses BM25 + vector embeddings to return only relevant snippets instead of full files.\n\nWhy Use This\n96% token reduction - Returns relevant snippets instead of reading entire files\nInstant results - Pre-indexed content means fast searches\nLocal & private - All indexing and search happens locally\nHybrid search - BM25 for keyword matching, vector search for semantic similarity\nCommands\nSearch (BM25 keyword matching)\nqmd search \"your query\" --collection \n\n\nFast, accurate keyword-based search. Best for specific terms or phrases.\n\nVector Search (semantic)\nqmd vsearch \"your query\" --collection \n\n\nSemantic similarity search. Best for conceptual queries where exact words may vary.\n\nHybrid Search (both + reranking)\nqmd hybrid \"your query\" --collection \n\n\nCombines both approaches with LLM reranking. Most thorough but often overkill.\n\nHow to Use\n\nCheck if collection exists:\n\nqmd collection list\n\n\nSearch the collection:\n\n# For specific terms\nqmd search \"api authentication\" --collection notes\n\n# For conceptual queries\nqmd vsearch \"how to handle errors gracefully\" --collection notes\n\n\nRead results: qmd returns relevant snippets with file paths and context\n\nSetup (if qmd not installed)\n# Install qmd\nbun install -g https://github.com/tobi/qmd\n\n# Add a collection (e.g., Obsidian vault)\nqmd collection add ~/path/to/vault --name notes\n\n# Generate embeddings for vector search\nqmd embed --collection notes\n\nInvocation Examples\n/qmd api authentication # BM25 search for \"api authentication\"\n/qmd how to handle errors --semantic # Vector search for conceptual query\n/qmd --setup # Guide through initial setup\n\nBest Practices\nUse BM25 search (qmd search) for specific terms, names, or technical keywords\nUse vector search (qmd vsearch) when looking for concepts where wording may vary\nAvoid hybrid search unless you need maximum recall - it's slower\nRe-run qmd embed after adding significant new content to keep vectors current\nHandling Arguments\n$ARGUMENTS contains the full search query\nIf --semantic flag is present, use qmd vsearch instead of qmd search\nIf --setup flag is present, guide user through installation and collection setup\nIf --collection is specified, use that collection; otherwise default to checking available collections\nWorkflow\nParse arguments from $ARGUMENTS\nCheck if qmd is installed (which qmd)\nIf not installed, offer to guide setup\nIf searching:\nList collections if none specified\nRun appropriate search command\nPresent results to user with file paths\nIf user wants to read a specific result, use the Read tool on the file path" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/anshumanbh/anshumanbh-qmd", "publisherUrl": "https://clawhub.ai/anshumanbh/anshumanbh-qmd", "owner": "anshumanbh", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/anshumanbh-qmd", "downloadUrl": "https://openagent3.xyz/downloads/anshumanbh-qmd", "agentUrl": "https://openagent3.xyz/skills/anshumanbh-qmd/agent", "manifestUrl": "https://openagent3.xyz/skills/anshumanbh-qmd/agent.json", "briefUrl": "https://openagent3.xyz/skills/anshumanbh-qmd/agent.md" } }