[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DSSVZX782JRDY02M7GGAT6":3,"skill-same:01M6DSSVZX782JRDY02M7GGAT6":81},{"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":30,"linkOnly":31,"markdownContent":32,"markdownBody":33,"frontMatter":34,"refName":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":40,"ownerHtmlUrl":41,"ownerBlogUrl":42,"ownerDescription":6,"updatedAt":43,"install":44,"resources":57},"01M6DSSVZX782JRDY02M7GGAT6","doctor",null,"Run environment and workspace diagnostics, auto-fix what it can, and report blockers. Use at session start or when something seems broken.","kiloloop\u002Foacp-skills","kiloloop","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F264514437?v=4","01M6DSS1K2JKZD3YRMXRH54968","Kiloloop","01M6DSS1SMM810F7327W2YX7ZZ",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fkiloloop\u002Foacp-skills\u002Fblob\u002Fmain\u002Fskills\u002Fdoctor\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29],"diagnostics","run","report","start","workspace","broken","fix","environment","session","use","auto","2026-11-10 10:12:30",false,"---\nname: doctor\ndescription: Run environment and workspace diagnostics, auto-fix what it can, and report blockers. Use at session start or when something seems broken.\n---\n\n# \u002Fdoctor — Environment & Workspace Diagnostics\n\nRun `oacp doctor` to check environment health, workspace structure, inbox state, YAML schemas, autonomy configs, agent status, and signing trust roots. Auto-fixes safe issues and reports blockers that need human intervention.\n\n## Arguments\n\n```\n\u002Fdoctor [--project \u003Cname>]\n```\n\n- `--project \u003Cname>` — Which project to check. Auto-detected from `.oacp` project marker (may be a symlink to `workspace.json`) if omitted.\n\n## Instructions\n\nWhen the user runs `\u002Fdoctor`, do the following:\n\n### 1. Pre-flight: verify oacp CLI\n\nBefore anything else, check that the CLI is available:\n\n```bash\ncommand -v oacp >\u002Fdev\u002Fnull 2>&1 || echo \"NOT_FOUND\"\n```\n\nIf not found, report immediately: \"oacp CLI not found. Install: `pip install 'oacp-cli[crypto]'`\" and stop. (The `[crypto]` extra enables the signing\u002Ftrust checks; the base install runs everything else.)\n\n### 2. Resolve project name\n\nIf `--project` was provided, use it directly. Otherwise auto-detect:\n\n```bash\nPROJECT=$(python3 -c \"import json; print(json.load(open('.oacp'))['project_name'])\" 2>\u002Fdev\u002Fnull || echo \"\")\n```\n\nIf empty, ask the user which project to check. If the user only wants environment checks (no project), run without `--project`.\n\n### 3. Run oacp doctor with --fix\n\nRun the doctor command with `--fix` and `--json` for structured parsing:\n\n```bash\noacp doctor --project \"${PROJECT}\" --fix --json 2>&1\n```\n\nIf `--project` was not resolved, run without it and without `--fix` (fixes require a workspace target):\n\n```bash\noacp doctor --json 2>&1\n```\n\nCapture both stdout (JSON) and the exit code. Exit code 1 means errors were found — this is expected, not a failure.\n\nIf the output is not valid JSON, the CLI may have crashed. Show the raw output to the user and report: \"oacp doctor returned invalid output. Check CLI installation.\"\n\n### 4. Parse the JSON output\n\nThe JSON output has this structure:\n\n```json\n{\n  \"has_errors\": false,\n  \"fixed\": [\n    \"Created claude\u002Fstatus.yaml\",\n    \"Updated codex\u002Fstatus.yaml timestamp\"\n  ],\n  \"categories\": [\n    {\n      \"name\": \"Environment\",\n      \"worst_severity\": \"ok\",\n      \"results\": [\n        {\n          \"name\": \"git\",\n          \"severity\": \"ok\",\n          \"message\": \"git — git version 2.x.x\"\n        },\n        {\n          \"name\": \"pyyaml\",\n          \"severity\": \"warn\",\n          \"message\": \"pyyaml — not importable\",\n          \"fix_hint\": \"Install: pip install pyyaml\"\n        }\n      ]\n    }\n  ]\n}\n```\n\nSeverity levels:\n\n- `ok` — passed (or auto-fixed), no action needed\n- `warn` — non-blocking issue, should be addressed\n- `error` — blocking issue, must be fixed\n- `skip` — check was skipped (missing dependency)\n\nThe `--fix` flag auto-fixes these safe issues:\n\n| Issue | Fix applied |\n|-------|------------|\n| Missing inbox directory | Creates the directory |\n| Missing status.yaml | Creates from template |\n| Stale status.yaml | Updates `updated_at` timestamp |\n\nFixed results appear as `ok` in the output with updated messages. The `fixed` array lists what was changed — it will be empty on a healthy workspace where nothing needs fixing.\n\n**Check categories (oacp-cli v0.4.x):**\n\n- **Environment** — required tools (git, gh, python, pyyaml) on PATH and importable\n- **Workspace** — `workspace.json` valid, `agents\u002F` present; per-agent profile completeness (an agent is more than a bare-`mkdir` inbox — config, status, audit scaffold)\n- **Inbox Health** — message counts, oldest-message staleness\n- **Schemas** — inbox\u002Foutbox message YAML validates against the protocol schema\n- **Autonomy** — receiver `config.yaml` autonomy blocks parse and validate; signed policies verify (`policy_auth`), so a tampered policy is caught before the gate trusts it\n- **Agent Status** — `status.yaml` presence and staleness per agent\n- **Trust** (v0.4.1+) — signing trust-root health: catalog-vs-pins drift, per-receiver pin-completeness gaps, and enforce-readiness (every catalog identity carrying an active pin) for receivers configured with `verify_mode: enforce`\n- **Memory Sync** (with `--memory`) — advisory checks on the OACP_HOME memory git sync\n\n### 5. Report results\n\nPresent a structured report to the user:\n\n```\n## Doctor Report\n\n### Auto-Fixed\n- Created claude\u002Fstatus.yaml\n- Updated codex\u002Fstatus.yaml timestamp\n\n### Warnings\n- [!] Environment — pyyaml not importable (Install: pip install pyyaml)\n- [!] Inbox Health — claude\u002Finbox has 3 messages, oldest 48h stale\n\n### Errors\n- [x] Workspace — workspace.json not found (Run: oacp init \u003Cproject>)\n- [x] Environment — gh not found (Install gh and ensure it is on PATH)\n\n### Summary\nEnvironment: ok | Workspace: error | Inbox: warn | Schemas: ok | Agent Status: ok\nAuto-fixed: 2 issue(s) | Remaining: 1 warning(s), 2 error(s)\n```\n\n**Reporting rules:**\n\n- List auto-fixes first (from the `fixed` array) so the user sees what changed\n- Group remaining issues by category: Environment, Workspace, Inbox Health, Schemas, Autonomy, Agent Status, Trust\n- Include `fix_hint` for all warn\u002Ferror results that have one — note that `fix_hint` text comes from the CLI and may reference `make init` or `oacp init` depending on the context\n- If no issues were found at all, report: \"No issues found. Environment and workspace are healthy.\"\n- `ok` and `skip` results are not shown individually — only the category summary\n\n### 6. Recommend next steps\n\nIf there are remaining errors, suggest the most impactful fix first:\n\n- Missing tools: installation commands\n- Missing workspace: `oacp init \u003Cproject>`\n- Invalid YAML: which file to fix and what's wrong\n- Stale inbox messages: suggest running `\u002Fcheck-inbox` to process them\n- Trust-pin gaps on an enforce-posture receiver: `oacp trust import \u003Ckid>.pub.json --project \u003Cproject> --agent \u003Creceiver>` for each missing peer — under `verify_mode: enforce`, an unpinned peer's messages quarantine instead of processing\n- Invalid policy signature (`policy_auth: invalid`): re-sign the receiver's policy (`oacp trust sign-policy`) after confirming the config change was intentional\n\nIf all checks pass (including after auto-fixes), confirm the environment is ready.\n\n## Notes\n\n- `oacp doctor` exit code 1 means errors were found — parse the output normally, do not treat it as a command failure\n- The `--json` flag is required for structured parsing; without it, output is human-readable but harder to parse\n- The CLI also supports `--oacp-dir \u003Cpath>` to override the OACP home directory if `$OACP_HOME` is not set\n- For recurring health checks, pair with `\u002Fcheck-inbox` at session start: run `\u002Fdoctor` first to verify the environment, then `\u002Fcheck-inbox` to process pending messages\n- Ensure your runtime has filesystem access to `$OACP_HOME` for reading workspace and agent directories\n","# \u002Fdoctor — Environment & Workspace Diagnostics\n\nRun `oacp doctor` to check environment health, workspace structure, inbox state, YAML schemas, autonomy configs, agent status, and signing trust roots. Auto-fixes safe issues and reports blockers that need human intervention.\n\n## Arguments\n\n```\n\u002Fdoctor [--project \u003Cname>]\n```\n\n- `--project \u003Cname>` — Which project to check. Auto-detected from `.oacp` project marker (may be a symlink to `workspace.json`) if omitted.\n\n## Instructions\n\nWhen the user runs `\u002Fdoctor`, do the following:\n\n### 1. Pre-flight: verify oacp CLI\n\nBefore anything else, check that the CLI is available:\n\n```bash\ncommand -v oacp >\u002Fdev\u002Fnull 2>&1 || echo \"NOT_FOUND\"\n```\n\nIf not found, report immediately: \"oacp CLI not found. Install: `pip install 'oacp-cli[crypto]'`\" and stop. (The `[crypto]` extra enables the signing\u002Ftrust checks; the base install runs everything else.)\n\n### 2. Resolve project name\n\nIf `--project` was provided, use it directly. Otherwise auto-detect:\n\n```bash\nPROJECT=$(python3 -c \"import json; print(json.load(open('.oacp'))['project_name'])\" 2>\u002Fdev\u002Fnull || echo \"\")\n```\n\nIf empty, ask the user which project to check. If the user only wants environment checks (no project), run without `--project`.\n\n### 3. Run oacp doctor with --fix\n\nRun the doctor command with `--fix` and `--json` for structured parsing:\n\n```bash\noacp doctor --project \"${PROJECT}\" --fix --json 2>&1\n```\n\nIf `--project` was not resolved, run without it and without `--fix` (fixes require a workspace target):\n\n```bash\noacp doctor --json 2>&1\n```\n\nCapture both stdout (JSON) and the exit code. Exit code 1 means errors were found — this is expected, not a failure.\n\nIf the output is not valid JSON, the CLI may have crashed. Show the raw output to the user and report: \"oacp doctor returned invalid output. Check CLI installation.\"\n\n### 4. Parse the JSON output\n\nThe JSON output has this structure:\n\n```json\n{\n  \"has_errors\": false,\n  \"fixed\": [\n    \"Created claude\u002Fstatus.yaml\",\n    \"Updated codex\u002Fstatus.yaml timestamp\"\n  ],\n  \"categories\": [\n    {\n      \"name\": \"Environment\",\n      \"worst_severity\": \"ok\",\n      \"results\": [\n        {\n          \"name\": \"git\",\n          \"severity\": \"ok\",\n          \"message\": \"git — git version 2.x.x\"\n        },\n        {\n          \"name\": \"pyyaml\",\n          \"severity\": \"warn\",\n          \"message\": \"pyyaml — not importable\",\n          \"fix_hint\": \"Install: pip install pyyaml\"\n        }\n      ]\n    }\n  ]\n}\n```\n\nSeverity levels:\n\n- `ok` — passed (or auto-fixed), no action needed\n- `warn` — non-blocking issue, should be addressed\n- `error` — blocking issue, must be fixed\n- `skip` — check was skipped (missing dependency)\n\nThe `--fix` flag auto-fixes these safe issues:\n\n| Issue | Fix applied |\n|-------|------------|\n| Missing inbox directory | Creates the directory |\n| Missing status.yaml | Creates from template |\n| Stale status.yaml | Updates `updated_at` timestamp |\n\nFixed results appear as `ok` in the output with updated messages. The `fixed` array lists what was changed — it will be empty on a healthy workspace where nothing needs fixing.\n\n**Check categories (oacp-cli v0.4.x):**\n\n- **Environment** — required tools (git, gh, python, pyyaml) on PATH and importable\n- **Workspace** — `workspace.json` valid, `agents\u002F` present; per-agent profile completeness (an agent is more than a bare-`mkdir` inbox — config, status, audit scaffold)\n- **Inbox Health** — message counts, oldest-message staleness\n- **Schemas** — inbox\u002Foutbox message YAML validates against the protocol schema\n- **Autonomy** — receiver `config.yaml` autonomy blocks parse and validate; signed policies verify (`policy_auth`), so a tampered policy is caught before the gate trusts it\n- **Agent Status** — `status.yaml` presence and staleness per agent\n- **Trust** (v0.4.1+) — signing trust-root health: catalog-vs-pins drift, per-receiver pin-completeness gaps, and enforce-readiness (every catalog identity carrying an active pin) for receivers configured with `verify_mode: enforce`\n- **Memory Sync** (with `--memory`) — advisory checks on the OACP_HOME memory git sync\n\n### 5. Report results\n\nPresent a structured report to the user:\n\n```\n## Doctor Report\n\n### Auto-Fixed\n- Created claude\u002Fstatus.yaml\n- Updated codex\u002Fstatus.yaml timestamp\n\n### Warnings\n- [!] Environment — pyyaml not importable (Install: pip install pyyaml)\n- [!] Inbox Health — claude\u002Finbox has 3 messages, oldest 48h stale\n\n### Errors\n- [x] Workspace — workspace.json not found (Run: oacp init \u003Cproject>)\n- [x] Environment — gh not found (Install gh and ensure it is on PATH)\n\n### Summary\nEnvironment: ok | Workspace: error | Inbox: warn | Schemas: ok | Agent Status: ok\nAuto-fixed: 2 issue(s) | Remaining: 1 warning(s), 2 error(s)\n```\n\n**Reporting rules:**\n\n- List auto-fixes first (from the `fixed` array) so the user sees what changed\n- Group remaining issues by category: Environment, Workspace, Inbox Health, Schemas, Autonomy, Agent Status, Trust\n- Include `fix_hint` for all warn\u002Ferror results that have one — note that `fix_hint` text comes from the CLI and may reference `make init` or `oacp init` depending on the context\n- If no issues were found at all, report: \"No issues found. Environment and workspace are healthy.\"\n- `ok` and `skip` results are not shown individually — only the category summary\n\n### 6. Recommend next steps\n\nIf there are remaining errors, suggest the most impactful fix first:\n\n- Missing tools: installation commands\n- Missing workspace: `oacp init \u003Cproject>`\n- Invalid YAML: which file to fix and what's wrong\n- Stale inbox messages: suggest running `\u002Fcheck-inbox` to process them\n- Trust-pin gaps on an enforce-posture receiver: `oacp trust import \u003Ckid>.pub.json --project \u003Cproject> --agent \u003Creceiver>` for each missing peer — under `verify_mode: enforce`, an unpinned peer's messages quarantine instead of processing\n- Invalid policy signature (`policy_auth: invalid`): re-sign the receiver's policy (`oacp trust sign-policy`) after confirming the config change was intentional\n\nIf all checks pass (including after auto-fixes), confirm the environment is ready.\n\n## Notes\n\n- `oacp doctor` exit code 1 means errors were found — parse the output normally, do not treat it as a command failure\n- The `--json` flag is required for structured parsing; without it, output is human-readable but harder to parse\n- The CLI also supports `--oacp-dir \u003Cpath>` to override the OACP home directory if `$OACP_HOME` is not set\n- For recurring health checks, pair with `\u002Fcheck-inbox` at session start: run `\u002Fdoctor` first to verify the environment, then `\u002Fcheck-inbox` to process pending messages\n- Ensure your runtime has filesystem access to `$OACP_HOME` for reading workspace and agent directories\n",{"name":5,"description":7},"main","ea78d5cce0208a15b59f6f2c49e729ba71a3c5af","skills\u002Fdoctor",1,"https:\u002F\u002Fgithub.com\u002Fkiloloop\u002Foacp-skills","https:\u002F\u002Foacp.dev\u002Fskills\u002F","https:\u002F\u002Fgithub.com\u002Fkiloloop","https:\u002F\u002Fkiloloop.com","2026-10-31 14:39:52",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add kiloloop\u002Foacp-skills --skill doctor",{"tool":50,"command":51},"bunx","bunx skills add kiloloop\u002Foacp-skills --skill doctor",{"tool":53,"command":54},"pnpm","pnpm dlx skills add kiloloop\u002Foacp-skills --skill doctor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkiloloop\u002Foacp-skills\u002Fblob\u002Fmain\u002Fskills\u002Fdoctor\u002FSKILL.md",true,[58,64,68,73,77],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"index.json","REFERENCE","参考文档",549,"https:\u002F\u002Fgithub.com\u002FDCx7C5\u002Fai-marketplace\u002Fblob\u002Fmain\u002Fskills\u002Flinux-net-rsync-exposure-detect\u002Findex.json",{"path":65,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":66,"sourceHtmlUrl":67},"README.md",2551,"https:\u002F\u002Fgithub.com\u002Fkiloloop\u002Foacp-skills\u002Fblob\u002Fmain\u002Fskills\u002Fdoctor\u002FREADME.md",{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":14,"sourceHtmlUrl":72},"shared\u002F.gitkeep","OTHER","其他","https:\u002F\u002Fgithub.com\u002Fkiloloop\u002Foacp-skills\u002Fblob\u002Fmain\u002Fskills\u002Fdoctor\u002Fshared\u002F.gitkeep",{"path":74,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":75,"sourceHtmlUrl":76},"shared\u002FINTENT.md",3102,"https:\u002F\u002Fgithub.com\u002Fkiloloop\u002Foacp-skills\u002Fblob\u002Fmain\u002Fskills\u002Fdoctor\u002Fshared\u002FINTENT.md",{"path":78,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":79,"sourceHtmlUrl":80},"skill.yaml",293,"https:\u002F\u002Fgithub.com\u002Fkiloloop\u002Foacp-skills\u002Fblob\u002Fmain\u002Fskills\u002Fdoctor\u002Fskill.yaml",[82,93,98,123,129,138],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":30},"01M6DSWR7WDRG7C3D31R4QKW5T","\u003Cskill-name>","\u003Cone-line description>","https:\u002F\u002Fgithub.com\u002Fkiloloop\u002Foacp-skills\u002Fblob\u002Fmain\u002Ftemplate\u002Fcodex\u002FSKILL.md",[],[89,90,91,92],"skill name","name","\u003Cskill name>","line",{"skillNo":94,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":30},"01M6DSWMRPCHQH4HJJF3MATTXZ","https:\u002F\u002Fgithub.com\u002Fkiloloop\u002Foacp-skills\u002Fblob\u002Fmain\u002Ftemplate\u002Fclaude\u002FSKILL.md",[],[89,90,91,92],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":30},"01M6DSWH83XKNGJSKX2XWQCRKJ","wrap-up","End-of-session cleanup for Codex — inspect stale artifacts, run debrief, write significant org-memory events, run a delta-first self-improve pass, then publish bounded approved memory and repository changes.","https:\u002F\u002Fgithub.com\u002Fkiloloop\u002Foacp-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwrap-up\u002Fcodex\u002FSKILL.md",[],[105,106,107,20,108,109,110,111,112,113,114,115,27,116,117,118,119,120,121,122],"wrap up","up","wrap","memory","cleanup","artifacts","repository","publish","first","improve","write","stale","session cleanup","delta","self","end","debrief","codex",{"skillNo":124,"name":125,"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":126,"categories":127,"keywords":128,"publishedAt":30},"01M6DSWEQBS2CE6F2H8T3VQNZY","claude","https:\u002F\u002Fgithub.com\u002Fkiloloop\u002Foacp-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwrap-up\u002Fclaude\u002FSKILL.md",[],[],{"skillNo":130,"name":100,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":30},"01M6DSW99EPXDVAG8GHR785CC5","End-of-session cleanup, debrief, org-memory events, self-improve, commit, and push in one command.","https:\u002F\u002Fgithub.com\u002Fkiloloop\u002Foacp-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwrap-up\u002FSKILL.md",[],[105,106,107,119,108,135,109,136,114,137,27,117,120,121],"commit","push","command",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":30},"01M6DSW4FRNRKRQ0TRMZAYNMKZ","self-improve","Audit and improve Codex operating guidance: skills, curated project memory, AGENTS.md, and relevant configuration. Use for explicit self-improve requests, routine wrap-up drift checks, stale or conflicting guidance, or an approved cleanup. Route release-wide OACP migrations and context-budget audits to audit-oacp-skills. Do not hand-edit generated Codex memories or installed plugin\u002Fsystem artifacts.","https:\u002F\u002Fgithub.com\u002Fkiloloop\u002Foacp-skills\u002Fblob\u002Fmain\u002Fskills\u002Fself-improve\u002Fcodex\u002FSKILL.md",[],[145,119,114,146,109,147,148,149,150,151,152,153,106,154,155,156,157,158,159,108],"self improve","project","release","audit","Budget","system","edit","context","generated","do","route","drift","memories","operating","oacp"]