[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GSN0QKPD1QNW0W59HVRV66":3,"skill-same:01M6GSN0QKPD1QNW0W59HVRV66":76},{"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":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":14,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":50,"install":51,"resources":63},"01M6GSN0QKPD1QNW0W59HVRV66","meditate",null,"Audit and evolve the brain vault - prune outdated content, discover cross-cutting principles, review skills for structural encoding opportunities. Triggers on \"meditate\", \"audit the brain\", \"prune brain\", \"review skills\", \"consolidate notes\", \"prune notes\".","japurcell\u002Fskills","japurcell","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F10947458?v=4","01M6GSJK1YAG95R6VHF47V30KY","Adam Purcell","01M6GSJK6817NVR5FVDMFFNJ6H",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdefault\u002Fbrain-install\u002Fassets\u002Fskills\u002Fmeditate\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"audit","snapshot","script","review skills","python","for","prune","encoding","evolve","brain","principles","vault","notes","consolidate","review","true","triggers","structural","discover","2026-11-10 10:12:30",false,"---\nname: meditate\ndescription: Audit and evolve the brain vault - prune outdated content, discover cross-cutting principles, review skills for structural encoding opportunities. Triggers on \"meditate\", \"audit the brain\", \"prune brain\", \"review skills\", \"consolidate notes\", \"prune notes\".\ndisable-model-invocation: true\ncompatibility: Requires Python 3.12+ for the bundled snapshot script.\n---\n\n# Meditate\n\n## Autonomous Session Mode\n\nWhen running non-interactively:\n\n- Apply all high-confidence changes autonomously. For ambiguous or risky changes (brain file deletions, principle rewrites), file a todo instead.\n- Commit only when the user authorizes it; follow the repository commit workflow.\n\n**Quality bar:** A note earns its place by being **high-signal** (The agent would reliably get this wrong without it), **high-frequency** (comes up in most sessions or most tasks of a type), or **high-impact** (getting it wrong causes significant damage or wasted work). Everything else is noise. A lean, precise brain outperforms a comprehensive but bloated one.\n\n## Process\n\nTrack progress with the available planning tools or a short checklist.\n\n### 1. Build snapshots\n\nUse Python 3.12+ to create a temporary directory and run the bundled helper. Replace `\u003Cskill-path>` with this skill's directory:\n\n```python\nfrom pathlib import Path\nimport subprocess\nimport sys\nimport tempfile\n\ntemporary = Path(tempfile.mkdtemp(prefix=\"meditate-\"))\nfor directory, name in [(\"brain\", \"brain-snapshot.md\"),\n                        (\".agents\u002Fskills\", \"skills-snapshot.md\")]:\n    subprocess.run([sys.executable, \"\u003Cskill-path>\u002Fscripts\u002Fsnapshot.py\",\n                    directory, str(temporary \u002F name)], check=True)\nprint(temporary)\n```\n\nFiles are delimited with `=== path\u002Fto\u002Ffile.md ===` headers. Retain the printed directory path and pass actual snapshot paths to reviewers. Keep it until the review finishes.\n\n### 2. Auditor (blocking - its report feeds step 3)\n\nUse an available general analysis subagent, or perform a bounded local review when delegation is unavailable. Read [agent prompts](references\u002Fagent-prompts.md) for the auditor and reviewer specifications. Inputs: brain snapshot, auto-memory path when present, AGENTS.md path.\n\nAudits brain notes, AGENTS.md, and auto-memory for staleness, redundancy, low-value content, verbosity, and orphans. Returns a categorized report.\n\n**Early-exit gate:** If the auditor finds fewer than 3 actionable items, skip step 3 and go directly to step 4.\n\n### 3. Reviewer (after auditor completes)\n\nUse one available general analysis subagent, or continue locally when delegation is unavailable. Use the reviewer specification from the agent prompts. Inputs: brain snapshot, skills snapshot, auditor report, `brain\u002Fprinciples.md`.\n\nCombines three concerns in a single pass:\n\n- **Synthesis**: Proposes missing Markdown links, flags principle tensions, suggests clarifications.\n- **Distillation**: Identifies recurring patterns that reveal unstated principles. New principles must be (1) independent, (2) evidenced by 2+ notes, (3) actionable.\n- **Skill review**: Cross-references skills against brain principles. Finds contradictions, missed structural enforcement, redundant instructions. Audits description frontmatters for context bloat.\n\n### 4. Review reports\n\nPresent the user with a consolidated summary using the report template from the agent prompts.\n\n### 5. Route skill-specific learnings\n\nCheck all reports for findings that belong in skill files, not `brain\u002F`. Update the skill's SKILL.md or references\u002F directly. Read the skill first to avoid duplication.\n\n### 6. Apply changes\n\nApply all changes directly. The user reviews the diff.\n\n- **Outdated notes**: Update or delete\n- **Redundant notes**: Merge into the stronger note, delete the weaker\n- **Low-value notes**: Delete\n- **Verbose notes**: Condense in place\n- **New connections**: Add file-relative Markdown links\n- **Tensions**: Reword to clarify boundaries\n- **New principles**: Only from the distillation section, only if genuinely independent. Write brain files and update `brain\u002Fprinciples.md`\n- **Merge principles**: Look for principles that are subsets or specific applications of each other - merge the narrower into the broader and pick a name that captures the combined insight\n- **Bloated skill descriptions**: Tighten frontmatter descriptions - cut what the agent can infer, keep only distinctive triggers and purpose\n- **AGENTS.md issues**: Rewrite or delete\n- **Stale memories**: Delete or rewrite\n\n### 7. Housekeep\n\nActivate the `brain` skill to maintain curated navigation and reconcile the root inventory, using manual indexing if hooks are unavailable. Remove only the temporary directory created in step 1 after all reviewers finish, using `shutil.rmtree` in Python with that exact retained path.\n\n## Summary\n\n```\n## Meditate Summary\n- Pruned: [N notes deleted, M condensed, K merged]\n- Extracted: [N new principles, with one-line + evidence count each]\n- Skill review: [N findings, M applied]\n- Housekeep: [state files cleaned]\n```\n","# Meditate\n\n## Autonomous Session Mode\n\nWhen running non-interactively:\n\n- Apply all high-confidence changes autonomously. For ambiguous or risky changes (brain file deletions, principle rewrites), file a todo instead.\n- Commit only when the user authorizes it; follow the repository commit workflow.\n\n**Quality bar:** A note earns its place by being **high-signal** (The agent would reliably get this wrong without it), **high-frequency** (comes up in most sessions or most tasks of a type), or **high-impact** (getting it wrong causes significant damage or wasted work). Everything else is noise. A lean, precise brain outperforms a comprehensive but bloated one.\n\n## Process\n\nTrack progress with the available planning tools or a short checklist.\n\n### 1. Build snapshots\n\nUse Python 3.12+ to create a temporary directory and run the bundled helper. Replace `\u003Cskill-path>` with this skill's directory:\n\n```python\nfrom pathlib import Path\nimport subprocess\nimport sys\nimport tempfile\n\ntemporary = Path(tempfile.mkdtemp(prefix=\"meditate-\"))\nfor directory, name in [(\"brain\", \"brain-snapshot.md\"),\n                        (\".agents\u002Fskills\", \"skills-snapshot.md\")]:\n    subprocess.run([sys.executable, \"\u003Cskill-path>\u002Fscripts\u002Fsnapshot.py\",\n                    directory, str(temporary \u002F name)], check=True)\nprint(temporary)\n```\n\nFiles are delimited with `=== path\u002Fto\u002Ffile.md ===` headers. Retain the printed directory path and pass actual snapshot paths to reviewers. Keep it until the review finishes.\n\n### 2. Auditor (blocking - its report feeds step 3)\n\nUse an available general analysis subagent, or perform a bounded local review when delegation is unavailable. Read [agent prompts](references\u002Fagent-prompts.md) for the auditor and reviewer specifications. Inputs: brain snapshot, auto-memory path when present, AGENTS.md path.\n\nAudits brain notes, AGENTS.md, and auto-memory for staleness, redundancy, low-value content, verbosity, and orphans. Returns a categorized report.\n\n**Early-exit gate:** If the auditor finds fewer than 3 actionable items, skip step 3 and go directly to step 4.\n\n### 3. Reviewer (after auditor completes)\n\nUse one available general analysis subagent, or continue locally when delegation is unavailable. Use the reviewer specification from the agent prompts. Inputs: brain snapshot, skills snapshot, auditor report, `brain\u002Fprinciples.md`.\n\nCombines three concerns in a single pass:\n\n- **Synthesis**: Proposes missing Markdown links, flags principle tensions, suggests clarifications.\n- **Distillation**: Identifies recurring patterns that reveal unstated principles. New principles must be (1) independent, (2) evidenced by 2+ notes, (3) actionable.\n- **Skill review**: Cross-references skills against brain principles. Finds contradictions, missed structural enforcement, redundant instructions. Audits description frontmatters for context bloat.\n\n### 4. Review reports\n\nPresent the user with a consolidated summary using the report template from the agent prompts.\n\n### 5. Route skill-specific learnings\n\nCheck all reports for findings that belong in skill files, not `brain\u002F`. Update the skill's SKILL.md or references\u002F directly. Read the skill first to avoid duplication.\n\n### 6. Apply changes\n\nApply all changes directly. The user reviews the diff.\n\n- **Outdated notes**: Update or delete\n- **Redundant notes**: Merge into the stronger note, delete the weaker\n- **Low-value notes**: Delete\n- **Verbose notes**: Condense in place\n- **New connections**: Add file-relative Markdown links\n- **Tensions**: Reword to clarify boundaries\n- **New principles**: Only from the distillation section, only if genuinely independent. Write brain files and update `brain\u002Fprinciples.md`\n- **Merge principles**: Look for principles that are subsets or specific applications of each other - merge the narrower into the broader and pick a name that captures the combined insight\n- **Bloated skill descriptions**: Tighten frontmatter descriptions - cut what the agent can infer, keep only distinctive triggers and purpose\n- **AGENTS.md issues**: Rewrite or delete\n- **Stale memories**: Delete or rewrite\n\n### 7. Housekeep\n\nActivate the `brain` skill to maintain curated navigation and reconcile the root inventory, using manual indexing if hooks are unavailable. Remove only the temporary directory created in step 1 after all reviewers finish, using `shutil.rmtree` in Python with that exact retained path.\n\n## Summary\n\n```\n## Meditate Summary\n- Pruned: [N notes deleted, M condensed, K merged]\n- Extracted: [N new principles, with one-line + evidence count each]\n- Skill review: [N findings, M applied]\n- Housekeep: [state files cleaned]\n```\n",{"name":5,"description":7,"compatibility":43,"disable-model-invocation":44},"Requires Python 3.12+ for the bundled snapshot script.",true,"main","2ce71d590264b43342c52d3011b0097c5ece7e21","skills\u002Fdefault\u002Fbrain-install\u002Fassets\u002Fskills\u002Fmeditate","https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills","https:\u002F\u002Fgithub.com\u002Fjapurcell","2026-11-11 08:59:34",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":44},[53,56,59],{"tool":54,"command":55},"npx","npx skills add japurcell\u002Fskills --skill meditate",{"tool":57,"command":58},"bunx","bunx skills add japurcell\u002Fskills --skill meditate",{"tool":60,"command":61},"pnpm","pnpm dlx skills add japurcell\u002Fskills --skill meditate","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdefault\u002Fbrain-install\u002Fassets\u002Fskills\u002Fmeditate\u002FSKILL.md",[64,70],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fagent-prompts.md","REFERENCE","参考文档",4932,"https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdefault\u002Fbrain-install\u002Fassets\u002Fskills\u002Fmeditate\u002Freferences\u002Fagent-prompts.md",{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"scripts\u002Fsnapshot.py","SCRIPT","脚本",1107,"https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdefault\u002Fbrain-install\u002Fassets\u002Fskills\u002Fmeditate\u002Fscripts\u002Fsnapshot.py",[77,107,129,156,179,200],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":88,"publishedAt":38},"01M6PT0ZTYCN4DHK3SXWS79WSY","spec-create","Create or revise a portable behavioral SPEC for a feature or whole product. Use when specifying a new idea, documenting an existing system for reimplementation, or defining a change while preserving compatibility. Implementation planning is a separate task.","https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdefault\u002Fspec-create\u002FSKILL.md",[83],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000031","产品经理","PROFESSION","适用职业",[89,90,91,92,93,24,94,95,96,97,98,99,100,101,102,103,104,105,106],"create","spec","spec create","feature","planning","system","use","Existing","task","output","change","product","implementation","revise","compatibility","behavioral","idea","path",{"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":114,"publishedAt":38},"01M6GSVHQ4MY4R4SMS8RY6324Q","prd-ralph","Complete at most one eligible unfinished PRD task, verify it, log progress, and optionally create one scoped commit.","https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdefault\u002Fprd-ralph\u002FSKILL.md",[113],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},[115,116,117,89,118,119,120,121,122,123,97,124,125,126,127,128,106],"prd ralph","ralph","prd","progress","verify","at","complete","commit","it","log","scoped","false","file","id",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":138,"publishedAt":38},"01M6GSYMGHE2FEGEFKD926EJH8","fsdp-style-guide","Mandatory for all UI\u002FUX design, implementation, review, audit, or visual regression tasks. Always use for any work that affects user-facing appearance, behavior, accessibility, branding, layout, navigation, forms, dialogs, alerts, tables, or visual design.","https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fforest-service\u002Ffsdp-style-guide\u002FSKILL.md",[135],{"categoryNo":136,"categoryName":137,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000032","设计师",[139,140,141,142,143,144,145,146,95,147,148,33,149,150,151,152,153,19,154,155,24],"fsdp style guide","style guide","FSDP","style","guide","visual regression","regression","design","visual","tasks","visual design","alerts","work","branding","layout","ux","behavior",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":38},"01M6GSYHEQARNM7WN0RJA7K7T2","agency-priorities","Provide self-contained USDA strategic goals and Forest Service priorities for agency briefings, proposals, and work-plan alignment. Use when explaining agency direction or evaluating how a project contributes to USDA and Forest Service priorities.","https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fforest-service\u002Fagency-priorities\u002FSKILL.md",[],[163,164,165,166,167,151,168,169,170,171,172,173,174,175,95,24,176,177,178],"agency priorities","priorities","agency","self","alignment","plan","goals","proposals","direction","how","project","strategic","service","when","briefings","self-contained",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":188,"publishedAt":38},"01M6GSY9VVN8RSJ5QYM540ZJ1D","accomplishment-report","Create a concise Forest Service executive accomplishment report when all work in an ExecPlan is completed, or update its existing report. Use at ExecPlan closeout and when asked to report completed work, agency alignment, and estimated AI-assisted versus human-only time and cost savings.","https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fforest-service\u002Faccomplishment-report\u002FSKILL.md",[185],{"categoryNo":186,"categoryName":187,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000034","行政与办公人员",[189,190,167,191,89,151,192,193,194,195,120,165,196,175,95,197,198,199,96,176],"report","accomplishment report","cost","concise","human","time","update","only","closeout","savings","execplan",{"skillNo":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":214,"publishedAt":38},"01M6GSY7J8ZMCE319P8Y6JZ432","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdefault\u002Fwriting-for-agents\u002FSKILL.md",[206,211],{"categoryNo":207,"categoryName":208,"taxonomyType":209,"taxonomyTypeDesc":210},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":212,"categoryName":213,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000036","内容创作者",[215,216,24,95,217,218,176],"writing","writing for agents","documents","editing"]