[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M757P5FJ4SY2EXGVK9XXA2GA":3,"skill-same:01M757P5FJ4SY2EXGVK9XXA2GA":53},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":35,"ownerHtmlUrl":36,"ownerBlogUrl":6,"ownerDescription":37,"updatedAt":38,"install":39,"resources":52},"01M757P5FJ4SY2EXGVK9XXA2GA","answer-cache",null,"Agent protocol for mycortex answer cache — inserts a cache-check step between RAG miss and model call. Saves tokens by caching LLM answers with quality gating, semantic dedup, and RLS isolation per profile.","lukemcqueen\u002Fsteadfaste-fleet","lukemcqueen","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F405240?v=4","01M757MHPAGRXTJAT46SKZP98R","Luke McQueen","01M757MHPZ573KP8DT9GB8SBQ7",4,"MIT","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fops\u002Fskills\u002Fanswer-cache\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: answer-cache\nversion: 1.0.0\ncategory: devops\ndescription: >-\n  Agent protocol for mycortex answer cache — inserts a cache-check step\n  between RAG miss and model call. Saves tokens by caching LLM answers\n  with quality gating, semantic dedup, and RLS isolation per profile.\nauthor: Steadfaste Fleet\nlicense: MIT\nplatforms: [linux, macos]\n---\n\n# Answer Cache — Agent Protocol\n\n## Purpose\n\nWhen mycortex (`search`) misses and the model answers from training data, that\nanswer is ephemeral. Next session pays the same token cost. This skill inserts\na cache-check step between RAG miss and model call, so repeated queries hit\nthe local answer cache for 0 tokens.\n\n## Core Flow\n\n```\nQuery -> mycortex search (hit? use it, 0 tokens)\n       -> miss? mycortex answer search (hit? use it, 0 tokens)\n       -> miss? model answers (costs tokens)\n       -> quality gate passes? mycortex answer store -> future hits local\n```\n\n## CLI Commands\n\nAll via the `mycortex` CLI (`~\u002F.steadfaste-fleet\u002Fscripts\u002Fmycortex`):\n\n### Store an answer\n\n```bash\nmycortex answer store \"\u003Cquery>\" \"\u003Canswer>\" \\\n  --confidence high|medium|low \\\n  --model deepseek\u002Fdeepseek-v4-flash \\\n  --tokens 512 \\\n  --source-scope federated|source_name\n```\n\n- Quality gates auto-skip: time-sensitive queries, refusals, PII\n- Use `--force` to bypass quality gates\n- Use `--update` to overwrite an existing entry for the same query\n- Semantic dedup checks before insert (trigram similarity > 0.6)\n\n### Search cached answers\n\n```bash\nmycortex answer search \"\u003Cquery>\" [--limit 10] [--min-score 0.0] [--json]\n```\n\n- Returns exact matches first, then trigram similarity matches\n- `--min-score 0.5` filters low-confidence semantic matches\n- `--json` for machine-readable output\n\n### View statistics\n\n```bash\nmycortex answer stats [--json]\n```\n\n### Prune stale entries\n\n```bash\nmycortex answer prune [--days 90] [--min-access 0] [--dry-run]\n```\n\n## Agent Protocol\n\n### Step 1: Search mycortex (existing RAG)\n```python\nresult = terminal(\"mycortex search '\u003Cquery>' --limit 5 --json\")\n```\n\n### Step 2: On miss, check the answer cache\n```python\nresult = terminal(\"mycortex answer search '\u003Cquery>' --limit 3 --min-score 0.5 --json\")\n```\n\n### Step 3: Model fallback + auto-store\n```python\n# Only if both searches yield nothing useful\n# After getting the model's answer:\nterminal(\"mycortex answer store '\u003Cquery>' '\u003Canswer>' --confidence medium --tokens \u003CN>\")\n```\n\n### Step 4: Verify the cached answer is used on repeat\n```python\nresult = terminal(\"mycortex answer search '\u003Cquery>' --json\")\n# -> returns the stored answer with 0 token cost\n```\n\n## Quality Gate Rules\n\n| Gate | What it prevents | Bypass |\n|------|-----------------|--------|\n| Time-sensitive | \"current weather\", \"latest news\" — content becomes stale | `--force` |\n| Refusal | LLM \"I cannot help\" patterns — don't cache dead ends | `--force` |\n| PII | Emails, phones, IPs in answers — never cache | `--force` |\n| Semantic dedup | Similar query, same answer — don't duplicate | `--force` |\n\n## Source Scope\n\n- **`federated`** (default) — visible to ALL agents (like federated brain sources)\n- **`\u003Csource_name>`** — visible only to agents with a grant for that source\n  (matches the RLS model: `mycortex.source_grants` controls per-role visibility)\n\n## RLS Isolation\n\nThe same per-profile isolation model applies: each Hermes profile connects as\n`mycortex_reader_\u003Cprofile>` and sees only answers whose `source_scope` is\n`federated` OR whose scope matches a source the profile has a grant for.\n\n## Pruning\n\nThe existing `agent-mycortex-retention` cron handles stale answers:\n- Orphaned answers: archived after 90 days with zero access\n- Active low-use: access_count \u003C 3 after 180 days\n- Manual: `mycortex answer prune --days 90 --min-access 0`\n\n## Test Commands\n\n```bash\nmycortex answer store \"What is the capital of France?\" \"Paris\" \\\n  --confidence high --tokens 5 --force\n\nmycortex answer search \"capital of France\" --json\n\nmycortex answer stats\n\nmycortex answer prune --days 0 --min-access 0 --dry-run\n```\n","# Answer Cache — Agent Protocol\n\n## Purpose\n\nWhen mycortex (`search`) misses and the model answers from training data, that\nanswer is ephemeral. Next session pays the same token cost. This skill inserts\na cache-check step between RAG miss and model call, so repeated queries hit\nthe local answer cache for 0 tokens.\n\n## Core Flow\n\n```\nQuery -> mycortex search (hit? use it, 0 tokens)\n       -> miss? mycortex answer search (hit? use it, 0 tokens)\n       -> miss? model answers (costs tokens)\n       -> quality gate passes? mycortex answer store -> future hits local\n```\n\n## CLI Commands\n\nAll via the `mycortex` CLI (`~\u002F.steadfaste-fleet\u002Fscripts\u002Fmycortex`):\n\n### Store an answer\n\n```bash\nmycortex answer store \"\u003Cquery>\" \"\u003Canswer>\" \\\n  --confidence high|medium|low \\\n  --model deepseek\u002Fdeepseek-v4-flash \\\n  --tokens 512 \\\n  --source-scope federated|source_name\n```\n\n- Quality gates auto-skip: time-sensitive queries, refusals, PII\n- Use `--force` to bypass quality gates\n- Use `--update` to overwrite an existing entry for the same query\n- Semantic dedup checks before insert (trigram similarity > 0.6)\n\n### Search cached answers\n\n```bash\nmycortex answer search \"\u003Cquery>\" [--limit 10] [--min-score 0.0] [--json]\n```\n\n- Returns exact matches first, then trigram similarity matches\n- `--min-score 0.5` filters low-confidence semantic matches\n- `--json` for machine-readable output\n\n### View statistics\n\n```bash\nmycortex answer stats [--json]\n```\n\n### Prune stale entries\n\n```bash\nmycortex answer prune [--days 90] [--min-access 0] [--dry-run]\n```\n\n## Agent Protocol\n\n### Step 1: Search mycortex (existing RAG)\n```python\nresult = terminal(\"mycortex search '\u003Cquery>' --limit 5 --json\")\n```\n\n### Step 2: On miss, check the answer cache\n```python\nresult = terminal(\"mycortex answer search '\u003Cquery>' --limit 3 --min-score 0.5 --json\")\n```\n\n### Step 3: Model fallback + auto-store\n```python\n# Only if both searches yield nothing useful\n# After getting the model's answer:\nterminal(\"mycortex answer store '\u003Cquery>' '\u003Canswer>' --confidence medium --tokens \u003CN>\")\n```\n\n### Step 4: Verify the cached answer is used on repeat\n```python\nresult = terminal(\"mycortex answer search '\u003Cquery>' --json\")\n# -> returns the stored answer with 0 token cost\n```\n\n## Quality Gate Rules\n\n| Gate | What it prevents | Bypass |\n|------|-----------------|--------|\n| Time-sensitive | \"current weather\", \"latest news\" — content becomes stale | `--force` |\n| Refusal | LLM \"I cannot help\" patterns — don't cache dead ends | `--force` |\n| PII | Emails, phones, IPs in answers — never cache | `--force` |\n| Semantic dedup | Similar query, same answer — don't duplicate | `--force` |\n\n## Source Scope\n\n- **`federated`** (default) — visible to ALL agents (like federated brain sources)\n- **`\u003Csource_name>`** — visible only to agents with a grant for that source\n  (matches the RLS model: `mycortex.source_grants` controls per-role visibility)\n\n## RLS Isolation\n\nThe same per-profile isolation model applies: each Hermes profile connects as\n`mycortex_reader_\u003Cprofile>` and sees only answers whose `source_scope` is\n`federated` OR whose scope matches a source the profile has a grant for.\n\n## Pruning\n\nThe existing `agent-mycortex-retention` cron handles stale answers:\n- Orphaned answers: archived after 90 days with zero access\n- Active low-use: access_count \u003C 3 after 180 days\n- Manual: `mycortex answer prune --days 90 --min-access 0`\n\n## Test Commands\n\n```bash\nmycortex answer store \"What is the capital of France?\" \"Paris\" \\\n  --confidence high --tokens 5 --force\n\nmycortex answer search \"capital of France\" --json\n\nmycortex answer stats\n\nmycortex answer prune --days 0 --min-access 0 --dry-run\n```\n",{"name":5,"author":24,"license":15,"version":25,"category":26,"platforms":27,"description":7},"Steadfaste Fleet","1.0.0","devops",[28,29],"linux","macos","main","2e6aa8d15ab0a366c90be54f61bf9c6e97015e83","ops\u002Fskills\u002Fanswer-cache",1,"https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet","steadfaste.com","https:\u002F\u002Fgithub.com\u002Flukemcqueen","AI Architect | Building Hermes Cortex: governed multi-agent AI for autonomous software engineering | Enterprise Tech Consultant","2026-11-14 22:33:34",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add lukemcqueen\u002Fsteadfaste-fleet --skill answer-cache",{"tool":45,"command":46},"bunx","bunx skills add lukemcqueen\u002Fsteadfaste-fleet --skill answer-cache",{"tool":48,"command":49},"pnpm","pnpm dlx skills add lukemcqueen\u002Fsteadfaste-fleet --skill answer-cache","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fops\u002Fskills\u002Fanswer-cache\u002FSKILL.md",true,[],[54,62,69,76,83,90],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":61},"01M7DXY4G8NSVB59K8B6S2AQNP","macbook-linux-maintenance","Legacy MacBook Linux fixes: GPU wedge, reboot hang, thermal.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fmacbook-linux-maintenance\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":61},"01M7DXXYJCXFJ3TGB84ZQ8KFE6","governance-regression-triage","Triage a host's governance issues: what changed.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fgovernance-regression-triage\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":61},"01M7DXXSAP1G8FDRJAMXQGBBMK","enforcement-immutability","Use when enforcement files lose their immutable flag.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fenforcement-immutability\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":61},"01M78SSDQVRYX64Y16X32TC0NS","steadfaste-fleet-repo-deploy","Use when committing to the steadfaste-fleet repo.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fsteadfaste-fleet-repo-deploy\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":61},"01M78SS928F3R2RJAYVW4E30CE","steadfaste-fleet-maintenance","Maintain an installed Steadfaste Fleet instance — update both the upstream Hermes Agent and the fleet repo layer, merge diverged histories, sync skills safely, and troubleshoot common issues. Covers the dual-update workflow (hermes update + fleet-update.sh), encrypted brain data backup, mycortex import, and recovery techniques.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fsteadfaste-fleet-maintenance\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":61},"01M78SP1CHW0T0BWE5ZT6JBPX8","fleet-preflight","DEPRECATED alias — merged into survey-before-action (2026-08-20). Load survey-before-action instead; its \"Repo-Specific Pre-Flight\" section covers git search, Hermes boundary, and deployment verification.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Ffleet-preflight\u002FSKILL.md",[],[]]