{ "schemaVersion": "1.0", "item": { "slug": "mindgraph", "name": "Mindgraph", "source": "tencent", "type": "skill", "category": "ζ•ˆηŽ‡ζε‡", "sourceUrl": "https://clawhub.ai/hulkworks/mindgraph", "canonicalUrl": "https://clawhub.ai/hulkworks/mindgraph", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/mindgraph", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=mindgraph", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "SKILL.md", "mindskills/knockout-test/PROCESS.md", "mindskills/knockout-test/results/example-pet-tracker.md", "references/philosophy.md", "scripts/mindgraph.py" ], "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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/mindgraph" }, "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/mindgraph", "agentPageUrl": "https://openagent3.xyz/skills/mindgraph/agent", "manifestUrl": "https://openagent3.xyz/skills/mindgraph/agent.json", "briefUrl": "https://openagent3.xyz/skills/mindgraph/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "MindGraph πŸ•ΈοΈπŸ§ ", "body": "A knowledge graph + learnable process engine for OpenClaw. Two core features:\n\nKnowledge Graph β€” Obsidian-style [[wikilinks]] across all workspace files\nMindSkills β€” Learned, repeatable processes that save graph-connected results" }, { "title": "Always-On Rules", "body": "Every time you write or edit a markdown file, use [[wikilinks]] for:\n\nPeople: [[Alice]], [[Bob]]\nProjects: [[my-saas]], [[landing-page]]\nCompanies/tools: [[Stripe]], [[Vercel]], [[GitHub]]\nConcepts/frameworks: [[Knockout Test]], [[B2B SaaS]]\nOther agents/models: [[Claude Code]], [[Sonnet]]\n\nThis is not optional. Links are how knowledge connects. No links = isolated notes = useless.\n\nNEVER use [[wikilinks]] in messages to the user (Telegram, Discord, etc.). Wikilinks are for workspace files only. In conversations, write names plain: \"Alice\", not \"[[Alice]]\".\n\nAfter significant file changes, rebuild the index:\n\npython3 skills/mindgraph/scripts/mindgraph.py index" }, { "title": "Graph Commands", "body": "# Build/rebuild index\npython3 skills/mindgraph/scripts/mindgraph.py index\n\n# Query a topic (backlinks + context + connections)\npython3 skills/mindgraph/scripts/mindgraph.py query \"\"\n\n# Backlinks only (what references this?)\npython3 skills/mindgraph/scripts/mindgraph.py backlinks \"\"\n\n# Forward links (what does this link to?)\npython3 skills/mindgraph/scripts/mindgraph.py links \"\"\n\n# Bidirectional connections\npython3 skills/mindgraph/scripts/mindgraph.py connections \"\"\n\n# ASCII tree visualization\npython3 skills/mindgraph/scripts/mindgraph.py tree \"\" [depth]\n\n# Find orphans, dead links, unconnected files\npython3 skills/mindgraph/scripts/mindgraph.py orphans\npython3 skills/mindgraph/scripts/mindgraph.py deadlinks\npython3 skills/mindgraph/scripts/mindgraph.py lonely\n\n# Full statistics\npython3 skills/mindgraph/scripts/mindgraph.py stats" }, { "title": "MindSkills β€” Learned Processes", "body": "MindSkills are repeatable frameworks stored in skills/mindgraph/mindskills/. Each has a defined process and saves results as graph-connected markdown." }, { "title": "Using a MindSkill", "body": "# List all learned mindskills\npython3 skills/mindgraph/scripts/mindgraph.py skills\n\n# Show a mindskill's process\npython3 skills/mindgraph/scripts/mindgraph.py skill \n\n# List results for a mindskill\npython3 skills/mindgraph/scripts/mindgraph.py results \n\nWhen a user asks to run a process (e.g., \"run the knockout test on X\"), follow this flow:\n\nRead the mindskill's PROCESS.md for the process definition\nExecute the process conversationally\nSave the result to skills/mindgraph/mindskills//results/.md\nUse [[wikilinks]] throughout the result file\nInclude YAML frontmatter with metadata\nRebuild the graph index\n\nResult file template:\n\n---\nmindskill: \nsubject: \ndate: \nverdict: \naliases: []\n---\n# [[]]: [[]]\n\n\n\n## Connections\n- Related: [[link1]], [[link2]]" }, { "title": "Learning a New MindSkill", "body": "When a user says \"learn a mindskill called X\" or describes a repeatable process:\n\n# Create a new mindskill\npython3 skills/mindgraph/scripts/mindgraph.py learn \"\"\n\nThis creates the directory structure. Then write the PROCESS.md based on the user's description.\n\nA good PROCESS.md contains:\n\nPurpose: What this process does and when to use it\nTrigger phrases: What the user might say to invoke this\nSteps: The actual process to follow (numbered)\nOutput format: What the result file should contain\nVerdict/scoring: How to summarize the outcome (if applicable)" }, { "title": "Discovering MindSkills", "body": "When a user's request matches a learned mindskill, proactively suggest it:\n\n\"Want me to run the [[Knockout Test]] on that?\"\n\"I have an [[SEO Validator]] mindskill β€” should I audit that?\"\n\"This looks like a [[Competitor Analysis]] β€” want the full framework?\"" }, { "title": "Link Resolution", "body": "Links match (case-insensitive) against:\n\nFile basenames: [[MEMORY]] β†’ MEMORY.md\nProject dirs: [[my-saas]] β†’ projects/my-saas/\nMindSkill results: [[Pet Tracker KT]] β†’ knockout test result\nYAML aliases: aliases: [AV-Check] β†’ [[AV-Check]] resolves\nUnresolved β†’ concept node (still tracked for backlinks)" }, { "title": "File Locations", "body": "Graph index: mindgraph.json (workspace root)\nMindSkills: skills/mindgraph/mindskills/\nScript: skills/mindgraph/scripts/mindgraph.py" } ], "body": "MindGraph πŸ•ΈοΈπŸ§ \n\nA knowledge graph + learnable process engine for OpenClaw. Two core features:\n\nKnowledge Graph β€” Obsidian-style [[wikilinks]] across all workspace files\nMindSkills β€” Learned, repeatable processes that save graph-connected results\nAlways-On Rules\n\nEvery time you write or edit a markdown file, use [[wikilinks]] for:\n\nPeople: [[Alice]], [[Bob]]\nProjects: [[my-saas]], [[landing-page]]\nCompanies/tools: [[Stripe]], [[Vercel]], [[GitHub]]\nConcepts/frameworks: [[Knockout Test]], [[B2B SaaS]]\nOther agents/models: [[Claude Code]], [[Sonnet]]\n\nThis is not optional. Links are how knowledge connects. No links = isolated notes = useless.\n\nNEVER use [[wikilinks]] in messages to the user (Telegram, Discord, etc.). Wikilinks are for workspace files only. In conversations, write names plain: \"Alice\", not \"[[Alice]]\".\n\nAfter significant file changes, rebuild the index:\n\npython3 skills/mindgraph/scripts/mindgraph.py index\n\nGraph Commands\n# Build/rebuild index\npython3 skills/mindgraph/scripts/mindgraph.py index\n\n# Query a topic (backlinks + context + connections)\npython3 skills/mindgraph/scripts/mindgraph.py query \"\"\n\n# Backlinks only (what references this?)\npython3 skills/mindgraph/scripts/mindgraph.py backlinks \"\"\n\n# Forward links (what does this link to?)\npython3 skills/mindgraph/scripts/mindgraph.py links \"\"\n\n# Bidirectional connections\npython3 skills/mindgraph/scripts/mindgraph.py connections \"\"\n\n# ASCII tree visualization\npython3 skills/mindgraph/scripts/mindgraph.py tree \"\" [depth]\n\n# Find orphans, dead links, unconnected files\npython3 skills/mindgraph/scripts/mindgraph.py orphans\npython3 skills/mindgraph/scripts/mindgraph.py deadlinks\npython3 skills/mindgraph/scripts/mindgraph.py lonely\n\n# Full statistics\npython3 skills/mindgraph/scripts/mindgraph.py stats\n\nMindSkills β€” Learned Processes\n\nMindSkills are repeatable frameworks stored in skills/mindgraph/mindskills/. Each has a defined process and saves results as graph-connected markdown.\n\nUsing a MindSkill\n# List all learned mindskills\npython3 skills/mindgraph/scripts/mindgraph.py skills\n\n# Show a mindskill's process\npython3 skills/mindgraph/scripts/mindgraph.py skill \n\n# List results for a mindskill\npython3 skills/mindgraph/scripts/mindgraph.py results \n\n\nWhen a user asks to run a process (e.g., \"run the knockout test on X\"), follow this flow:\n\nRead the mindskill's PROCESS.md for the process definition\nExecute the process conversationally\nSave the result to skills/mindgraph/mindskills//results/.md\nUse [[wikilinks]] throughout the result file\nInclude YAML frontmatter with metadata\nRebuild the graph index\n\nResult file template:\n\n---\nmindskill: \nsubject: \ndate: \nverdict: \naliases: []\n---\n# [[]]: [[]]\n\n\n\n## Connections\n- Related: [[link1]], [[link2]]\n\nLearning a New MindSkill\n\nWhen a user says \"learn a mindskill called X\" or describes a repeatable process:\n\n# Create a new mindskill\npython3 skills/mindgraph/scripts/mindgraph.py learn \"\"\n\n\nThis creates the directory structure. Then write the PROCESS.md based on the user's description.\n\nA good PROCESS.md contains:\n\nPurpose: What this process does and when to use it\nTrigger phrases: What the user might say to invoke this\nSteps: The actual process to follow (numbered)\nOutput format: What the result file should contain\nVerdict/scoring: How to summarize the outcome (if applicable)\nDiscovering MindSkills\n\nWhen a user's request matches a learned mindskill, proactively suggest it:\n\n\"Want me to run the [[Knockout Test]] on that?\"\n\"I have an [[SEO Validator]] mindskill β€” should I audit that?\"\n\"This looks like a [[Competitor Analysis]] β€” want the full framework?\"\nLink Resolution\n\nLinks match (case-insensitive) against:\n\nFile basenames: [[MEMORY]] β†’ MEMORY.md\nProject dirs: [[my-saas]] β†’ projects/my-saas/\nMindSkill results: [[Pet Tracker KT]] β†’ knockout test result\nYAML aliases: aliases: [AV-Check] β†’ [[AV-Check]] resolves\nUnresolved β†’ concept node (still tracked for backlinks)\nFile Locations\nGraph index: mindgraph.json (workspace root)\nMindSkills: skills/mindgraph/mindskills/\nScript: skills/mindgraph/scripts/mindgraph.py" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/hulkworks/mindgraph", "publisherUrl": "https://clawhub.ai/hulkworks/mindgraph", "owner": "hulkworks", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/mindgraph", "downloadUrl": "https://openagent3.xyz/downloads/mindgraph", "agentUrl": "https://openagent3.xyz/skills/mindgraph/agent", "manifestUrl": "https://openagent3.xyz/skills/mindgraph/agent.json", "briefUrl": "https://openagent3.xyz/skills/mindgraph/agent.md" } }