[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CSMPJW23G8K55Z9WRM56V2":3,"skill-same:01M6CSMPJW23G8K55Z9WRM56V2":70},{"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":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":14,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":48,"ownerDescription":49,"updatedAt":50,"install":51,"resources":63},"01M6CSMPJW23G8K55Z9WRM56V2","garden-health",null,"Use when the user wants to maintain vault health, garden the knowledge base, check for orphans, find what is stale, audit structural gaps, or see a vault health report. Composes analysis tools into a full health picture before proposing any remediation.","ThatDevStudio\u002Fztlctl","ThatDevStudio","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F168217678?v=4","01M6CSMDK6RNT910MHNQ51PHAX","ThatDev Studio","01M6CSMDQ6BDK686J8ZEH97DVC",0,"MIT","https:\u002F\u002Fgithub.com\u002FThatDevStudio\u002Fztlctl\u002Fblob\u002Fdevelop\u002Fplugin\u002Fskills\u002Fgarden-health\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34],"health","garden health","report","audit","remediation","Tools","analysis","vault","knowledge","find","check","user","use","stale","maintain","base","2026-11-10 10:12:30",false,"---\nname: garden-health\ndescription: >\n  Use when the user wants to maintain vault health, garden the knowledge base,\n  check for orphans, find what is stale, audit structural gaps, or see a vault\n  health report. Composes analysis tools into a full health picture before\n  proposing any remediation.\nversion: 1.0.0\ndisable-model-invocation: true\n---\n\n# Garden Health Audit\n\nGarden and maintain the vault by composing a full structural health picture before\nproposing any remediation. This skill uses the Fan-Out pattern: run all analysis\ntools in parallel, synthesize the report, then confirm with the user before any\nwrites.\n\n## Iron Laws\n\n**Audit first, act second.** Complete the full analysis (steps 1-5) before\nproposing any remediation. Never suggest fixes mid-audit — the full picture\nchanges the priority order.\n\n**Never remediate without confirmation.** Present the complete maintenance report\nand wait for explicit user approval before any writes. Orphan reweave, maturity\npromotion, and note creation are all write operations.\n\n**Check `result.success` after every MCP call.** If any analysis tool fails,\nnote the failure, continue the remaining reads, and report the partial results.\n\n## Workflow\n\n1. **Read `ztlctl:\u002F\u002Fgarden\u002Fbacklog`** — load stale seeds (age, last-modified)\n   and orphan notes (link counts). This is the maintenance backlog candidates list.\n\n2. **Read `ztlctl:\u002F\u002Freview\u002Fdashboard`** — load the external review workbench\n   snapshot: pending reviews, external sources awaiting processing.\n\n3. **`vault_review()`** — comprehensive aggregate snapshot: total notes, stale\n   count, orphan count, maturity distribution, content type breakdown. Check\n   `result.success`.\n\n4. **`graph_gaps(top=10)`** — find structurally isolated clusters with no\n   inter-cluster edges. These are knowledge islands that may need bridging notes.\n\n5. **`graph_bridges(top=10)`** — find high-value bridge nodes whose removal\n   would disconnect clusters. High-risk bridge nodes deserve protection or\n   redundant linking.\n\n6. **Synthesize health report** — combine all reads into a prioritized summary:\n   - Orphan count and worst offenders (0 links, old age)\n   - Stale seed count and top candidates for promotion\n   - Structural gap clusters (isolated groups with no cross-links)\n   - Bridge nodes at risk (high bridge_score, low redundancy)\n   - External review backlog (pending sources from dashboard)\n\n7. **Present action list with confirmation gate** — propose prioritized\n   remediation with scope options:\n   - Connect orphans: `reweave(content_id=\"\u003Cid>\")` for each orphan\n   - Promote stale seeds: `update_content(content_id=\"\u003Cid>\", changes={\"maturity\": \"budding\"})`\n   - Document gaps: `create_note(title=\"\u003Cbridging topic>\")` to link isolated clusters\n\n   Ask: \"Process all \u002F connect orphans only \u002F promote seeds only \u002F select\n   specific items?\" Wait for user response before any writes.\n\n## Distinction from ztl:review-triage\n\nztl:review-triage focuses on the **work queue**: actionable items (tasks, stale\nnotes, drafts needing updates). ztl:garden-health focuses on **structural vault\nhealth**: orphans, gaps, bridges, and maturity staleness across the full vault.\nWhen the user asks \"what needs attention,\" clarify: work queue items or vault\nstructure?\n\n---\n\nSee `references\u002Fgarden-audit.md` for tool output schemas and remediation option\ndetails.\n","# Garden Health Audit\n\nGarden and maintain the vault by composing a full structural health picture before\nproposing any remediation. This skill uses the Fan-Out pattern: run all analysis\ntools in parallel, synthesize the report, then confirm with the user before any\nwrites.\n\n## Iron Laws\n\n**Audit first, act second.** Complete the full analysis (steps 1-5) before\nproposing any remediation. Never suggest fixes mid-audit — the full picture\nchanges the priority order.\n\n**Never remediate without confirmation.** Present the complete maintenance report\nand wait for explicit user approval before any writes. Orphan reweave, maturity\npromotion, and note creation are all write operations.\n\n**Check `result.success` after every MCP call.** If any analysis tool fails,\nnote the failure, continue the remaining reads, and report the partial results.\n\n## Workflow\n\n1. **Read `ztlctl:\u002F\u002Fgarden\u002Fbacklog`** — load stale seeds (age, last-modified)\n   and orphan notes (link counts). This is the maintenance backlog candidates list.\n\n2. **Read `ztlctl:\u002F\u002Freview\u002Fdashboard`** — load the external review workbench\n   snapshot: pending reviews, external sources awaiting processing.\n\n3. **`vault_review()`** — comprehensive aggregate snapshot: total notes, stale\n   count, orphan count, maturity distribution, content type breakdown. Check\n   `result.success`.\n\n4. **`graph_gaps(top=10)`** — find structurally isolated clusters with no\n   inter-cluster edges. These are knowledge islands that may need bridging notes.\n\n5. **`graph_bridges(top=10)`** — find high-value bridge nodes whose removal\n   would disconnect clusters. High-risk bridge nodes deserve protection or\n   redundant linking.\n\n6. **Synthesize health report** — combine all reads into a prioritized summary:\n   - Orphan count and worst offenders (0 links, old age)\n   - Stale seed count and top candidates for promotion\n   - Structural gap clusters (isolated groups with no cross-links)\n   - Bridge nodes at risk (high bridge_score, low redundancy)\n   - External review backlog (pending sources from dashboard)\n\n7. **Present action list with confirmation gate** — propose prioritized\n   remediation with scope options:\n   - Connect orphans: `reweave(content_id=\"\u003Cid>\")` for each orphan\n   - Promote stale seeds: `update_content(content_id=\"\u003Cid>\", changes={\"maturity\": \"budding\"})`\n   - Document gaps: `create_note(title=\"\u003Cbridging topic>\")` to link isolated clusters\n\n   Ask: \"Process all \u002F connect orphans only \u002F promote seeds only \u002F select\n   specific items?\" Wait for user response before any writes.\n\n## Distinction from ztl:review-triage\n\nztl:review-triage focuses on the **work queue**: actionable items (tasks, stale\nnotes, drafts needing updates). ztl:garden-health focuses on **structural vault\nhealth**: orphans, gaps, bridges, and maturity staleness across the full vault.\nWhen the user asks \"what needs attention,\" clarify: work queue items or vault\nstructure?\n\n---\n\nSee `references\u002Fgarden-audit.md` for tool output schemas and remediation option\ndetails.\n",{"name":5,"version":40,"description":41,"disable-model-invocation":42},"1.0.0","Use when the user wants to maintain vault health, garden the knowledge base, check for orphans, find what is stale, audit structural gaps, or see a vault health report. Composes analysis tools into a full health picture before proposing any remediation.\n",true,"develop","fa2801de39a8e8c3a55b0e0ea590781b326e226e","plugin\u002Fskills\u002Fgarden-health","https:\u002F\u002Fgithub.com\u002FThatDevStudio\u002Fztlctl","https:\u002F\u002Fgithub.com\u002FThatDevStudio","thatdev.io","ThatDev","2026-03-22 22:57:17",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":42},[53,56,59],{"tool":54,"command":55},"npx","npx skills add ThatDevStudio\u002Fztlctl --skill garden-health",{"tool":57,"command":58},"bunx","bunx skills add ThatDevStudio\u002Fztlctl --skill garden-health",{"tool":60,"command":61},"pnpm","pnpm dlx skills add ThatDevStudio\u002Fztlctl --skill garden-health","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FThatDevStudio\u002Fztlctl\u002Fblob\u002Fdevelop\u002Fplugin\u002Fskills\u002Fgarden-health\u002FSKILL.md",[64],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fgarden-audit.md","REFERENCE","参考文档",2747,"https:\u002F\u002Fgithub.com\u002FThatDevStudio\u002Fztlctl\u002Fblob\u002Fdevelop\u002Fplugin\u002Fskills\u002Fgarden-health\u002Freferences\u002Fgarden-audit.md",[71,87,104,121,139,153],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":35},"01M6CSNCEFP7TMHJH1RYE6HB6F","vault-methodology","Use when working in a ztlctl vault — creating notes, organizing knowledge, tagging, linking, or making decisions about content types and structure. Activates for any knowledge management task.","https:\u002F\u002Fgithub.com\u002FThatDevStudio\u002Fztlctl\u002Fblob\u002Fdevelop\u002Fplugin\u002Fskills\u002Fvault-methodology\u002FSKILL.md",[],[78,26,79,80,81,27,82,83,31,84,85,86],"methodology","vault methodology","notes","content","decisions","management","knowledge management","task","structure",{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":98,"publishedAt":35},"01M6CSNA9DPPRQTVRB3PK39S41","synthesize","Use when the user wants to synthesize scattered notes into a unified artifact, consolidate knowledge on a topic, connect existing notes, find structural gaps, or create a synthesis note. Activates on \"synthesize\", \"consolidate\", \"connect my notes on X\", \"summarize what I know about X\", \"find gaps in X\", or \"create synthesis\".","https:\u002F\u002Fgithub.com\u002FThatDevStudio\u002Fztlctl\u002Fblob\u002Fdevelop\u002Fplugin\u002Fskills\u002Fsynthesize\u002FSKILL.md",[93],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[89,99,80,100,101,27,28,30,31,102,103],"summarize","connect","create","Synthesis","artifact",{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":35},"01M6CSN854VHN73TST01PPVXC7","session","Use when the user wants to start, begin, or open a work session, OR close, end, or finish an active session. Manages the full session lifecycle: pre-flight checks, polaris alignment, session start, and session close with enrichment pipeline.","https:\u002F\u002Fgithub.com\u002FThatDevStudio\u002Fztlctl\u002Fblob\u002Fdevelop\u002Fplugin\u002Fskills\u002Fsession\u002FSKILL.md",[],[106,111,112,31,113,30,114,115,116,117,118,119,120],"finish","work","alignment","work session","session close","start","open","enrichment","pipeline","lifecycle",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":131,"publishedAt":35},"01M6CSN5HMBGRHZBMY2ANS2YKP","session-workflow","Use when starting, running, or closing research sessions. Guides structured knowledge capture workflows: start → capture → synthesize → close.","https:\u002F\u002Fgithub.com\u002FThatDevStudio\u002Fztlctl\u002Fblob\u002Fdevelop\u002Fplugin\u002Fskills\u002Fsession-workflow\u002FSKILL.md",[127,128],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},{"categoryNo":129,"categoryName":130,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000023","Skill与智能体开发",[132,106,133,134,135,136,137,116,27,138,31],"workflow","session workflow","knowledge capture","research","workflows","sessions","capture",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":35},"01M6CSN2YMTDPQ96ZZ9JMS1XT0","review-triage","Use when the user asks to review the work queue, triage pending items, clear the backlog, or find out what needs attention in the vault. Surfaces prioritized actionable items and batch-processes approved updates.","https:\u002F\u002Fgithub.com\u002FThatDevStudio\u002Fztlctl\u002Fblob\u002Fdevelop\u002Fplugin\u002Fskills\u002Freview-triage\u002FSKILL.md",[],[146,147,148,31,149,26,112,28,30,150,151,152],"review","review triage","triage","batch","queue","surfaces","backlog",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":35},"01M6CSN0XZVNHDN002Z4SWSEZM","review-contradictions","Use when the user wants to review conflicting notes, find inconsistencies in the vault, check for contradictions between knowledge claims, or inspect semantically-close notes that may conflict. Runs the per-pair evaluation loop to surface genuine contradictions and dismiss false positives.","https:\u002F\u002Fgithub.com\u002FThatDevStudio\u002Fztlctl\u002Fblob\u002Fdevelop\u002Fplugin\u002Fskills\u002Freview-contradictions\u002FSKILL.md",[],[160,146,80,161,26,27,162,163,28,29,30,31],"review contradictions","Evaluation","loop","pair"]