[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M780VQZYBVESTGFVBHPYD92C":3,"skill-same:01M780VQZYBVESTGFVBHPYD92C":97},{"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":72,"commitSha":73,"skillDirectory":74,"forksCount":14,"repositoryHtmlUrl":75,"repositoryHomepageUrl":6,"ownerHtmlUrl":76,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":77,"install":78,"resources":90},"01M780VQZYBVESTGFVBHPYD92C","eiirp",null,"Everything In Its Right Place. The universal post-work organizer. After\nany significant work session, EIIRP runs a 7-phase audit: (1) inventory\nevery output, (2) walk taxonomy to decide where each lands, (3) check\nschema-pack consistency against the brain's actual shape, (4) file\nenriched brain pages, (5) audit the skill graph for DRY+MECE, (6) verify\nresolvability, (7) report. Named after the Radiohead song. Nothing\nproduced during significant work lives only in chat — knowledge becomes\npermanent, patterns become reusable.","moonstachain\u002Fgbrain-yuanli","moonstachain","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F20961570?v=4","01M780RGGTEZZFR5F5PP9BY2RP","HAY2045","01M780RGHMKRKAX5KHNJN779EV",0,"MIT","https:\u002F\u002Fgithub.com\u002Fmoonstachain\u002Fgbrain-yuanli\u002Fblob\u002Fmain\u002Fskills\u002Feiirp\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: eiirp\nversion: 1.0.0\nprompt_version: 1\ndescription: |\n  Everything In Its Right Place. The universal post-work organizer. After\n  any significant work session, EIIRP runs a 7-phase audit: (1) inventory\n  every output, (2) walk taxonomy to decide where each lands, (3) check\n  schema-pack consistency against the brain's actual shape, (4) file\n  enriched brain pages, (5) audit the skill graph for DRY+MECE, (6) verify\n  resolvability, (7) report. Named after the Radiohead song. Nothing\n  produced during significant work lives only in chat — knowledge becomes\n  permanent, patterns become reusable.\ntriggers:\n  - \"everything in its right place\"\n  - \"eiirp\"\n  - \"store this research\"\n  - \"put this in the brain\"\n  - \"file this properly\"\n  - \"where does this research go\"\n  - \"make this permanent\"\n  - \"archive this research\"\n  - \"archive this research thread\"\n  - \"brain this\"\n  - \"file all of this\"\n  - \"organize all of this\"\n  - \"organize all of this work\"\n  - \"make this re-doable\"\n  - \"DRY this up\"\n  - \"check everything is in the right place\"\ntools:\n  - search\n  - query\n  - get_page\n  - put_page\n  - add_link\n  - add_timeline_entry\nmutating: true\nwrites_pages: true\n# EIIRP files across the full canonical set — the actual destination\n# per page is decided by brain-taxonomist consulting the active schema\n# pack via `gbrain schema show --json`. List the gbrain-recommended set\n# of canonical directories here so the filing-audit gate passes; on\n# brains with custom packs, the routing surface is broader and routes\n# through loadActivePack at write time.\nwrites_to:\n  - people\u002F\n  - companies\u002F\n  - deals\u002F\n  - meetings\u002F\n  - concepts\u002F\n  - projects\u002F\n  - civic\u002F\n  - writing\u002F\n  - analysis\u002F\n  - guides\u002F\nfiling_exempt: true\ndistinct_from:\n  - name: brain-taxonomist\n    reason: \"brain-taxonomist classifies individual pages at write time (the filing GATE). EIIRP orchestrates the full post-work LIFECYCLE — inventory + taxonomy + schema + skillify + verify.\"\n  - name: ingest\n    reason: \"ingest handles NEW content from external URLs\u002Fmedia. EIIRP handles COMPLETED research that needs to be decomposed and filed across multiple brain locations.\"\n  - name: skillify\n    reason: \"skillify is the meta-skill for turning a feature into a tested skill. EIIRP calls skillify when Phase 5 identifies a reusable pattern.\"\n---\n\n# EIIRP — Everything In Its Right Place\n\n> *\"Everything in its right place\"* — Radiohead, Kid A\n\n## Contract\n\nAfter any significant work, EIIRP organizes ALL outputs across two domains:\n\n**Knowledge domain (brain):**\n1. Every piece of knowledge lands in the correct brain location.\n2. All sources are cited and linked.\n3. The active schema pack is updated if a new content type emerged.\n4. Entity pages created\u002Fupdated with cross-links.\n\n**Capability domain (skills):**\n5. Every reusable pattern becomes a composable skill.\n6. Existing skills are audited for DRY violations.\n7. Skill graph is MECE — no gaps, no overlaps, no ambiguous routing.\n\n**The meta-guarantee:** Nothing produced during significant work lives only in chat.\nKnowledge → brain. Patterns → skills. Everything in its right place.\n\n## When to Use\n\n- After completing a deep research thread.\n- After building something new (code, pipeline, workflow).\n- After a multi-source analysis that produced significant findings.\n- When the user says \"EIIRP\", \"organize this\", \"DRY this up\", \"make this re-doable\".\n- When a work session produced both knowledge AND new capabilities.\n- When you notice skill overlap, duplication, or gaps.\n\n## Phase 1: INVENTORY — What did we produce?\n\nScan the current session\u002Fthread and identify ALL outputs across both domains.\n\n### Knowledge outputs\n```\n□ Primary findings (the synthesis)\n□ Source documents (URLs, PDFs, articles, tweets)\n□ Entity mentions (people, companies, organizations, places)\n□ Concepts\u002Fframeworks (reusable mental models)\n□ Data artifacts (structured data, timelines, statistics)\n```\n\n### Capability outputs\n```\n□ New skills created or modified\n□ Scripts\u002Fcode written (should they be in lib\u002F or scripts\u002F?)\n□ Methodology used (search patterns, source chains, verification steps)\n□ Workflows that could be automated (cron, pipeline, webhook)\n□ Patterns that will recur (→ candidate for skillification)\n```\n\nProduce a manifest:\n\n```markdown\n## EIIRP Manifest\n- Topic: [topic]\n- Date: [date]\n- Knowledge outputs: [count] (sources, entities, concepts)\n- Capability outputs: [count] (skills, scripts, patterns)\n- Reusable methodology: [yes\u002Fno — describe if yes]\n```\n\n## Phase 2: TAXONOMY — Where does each piece go?\n\n**Read the active schema pack first** (the single source of truth for\nfiling decisions in v0.39+):\n\n```bash\ngbrain schema show --json\n```\n\nThe pack's `page_types[]` lists every directory the brain accepts plus\nthe primitive each maps to. Walk it for each output and pick the directory\nwhose `path_prefixes` matches the content's primary subject.\n\nIf `brain-taxonomist` is installed, INVOKE IT for ambiguous cases. It runs\nthe same decision protocol against the active pack and gives you a single\nrecommended filing path with reasoning.\n\nOutput: a filing plan table:\n\n```\n| Content | Brain path | Action |\n|---------|-----------|--------|\n| Primary research | reference\u002F...\u002Fpage.md | CREATE |\n| Person X | people\u002Fx-slug.md | CREATE |\n| Person Y | people\u002Fy-slug.md | UPDATE (already exists) |\n| ... | ... | ... |\n```\n\n## Phase 3: SCHEMA CHECK — Does the active pack cover this content?\n\nThis is where EIIRP closes the schema-derivation loop. If the work\nproduced content that doesn't fit any existing `page_types`, propose\nadding a new type via the v0.39 cathedral:\n\n```bash\n# What's emerging in the brain that the active pack doesn't cover?\ngbrain schema detect --json\n\n# LLM-refined suggestions (heuristic when no API key set).\ngbrain schema suggest --json\n\n# Review what's pending; promote or ignore each candidate.\ngbrain schema review-candidates --json\ngbrain schema review-candidates --apply \u003Cprefix-or-type-name>\n```\n\n**Confidence floor (codex finding #9):** when `gbrain schema suggest`\nreturns confidence \u003C 0.6 on a proposed type, DO NOT auto-apply. Surface\nthe suggestion to the user and let them choose. The schema-cathedral\nships the primitives; EIIRP enforces the human-in-the-loop gate.\n\nIf schema needs change:\n- Propose the addition to the user before running `review-candidates --apply`.\n- Document the change in the commit message of the next sync.\n- The schema-pack engine writes the delta to\n  `~\u002F.gbrain\u002Fschema-pack-deltas\u002F` — review and merge into the active\n  pack via `gbrain schema edit` (or hand-edit the YAML).\n\n## Phase 4: FILE — Create enriched brain pages\n\nFor each item in the filing plan:\n\n### 4a. Primary research page\nUse the brain page template. MUST include:\n- Proper frontmatter (`type`, `title`, `date`, `tags`, sources)\n- **State** section — current status\u002Fkey findings\n- **Sources** section — every source with URL, author, date, language\n- **Timeline** section — chronological development\n- **Entity links** — backlinks to all related brain pages\n- **See Also** — related concepts, reference pages\n\n### 4b. Entity pages (people, companies)\nFor each entity mentioned:\n- Check if a brain page exists (`gbrain search \"\u003Cname>\"` or `gbrain get_page people\u002F\u003Cslug>`).\n- If exists: update State, append Timeline entry citing this research.\n- If not: create with enrichment.\n\n### 4c. Commit and verify\nAfter ALL pages are written, run `gbrain sync` (or commit + push in the\nbrain repo). Verify every link resolves.\n\n## Phase 5: SKILL GRAPH AUDIT — DRY + MECE on capabilities\n\nThis phase operates on the SKILL graph, not just the research.\n\n### 5a. New pattern identification\n\nAsk: did this work reveal REPEATABLE patterns that will recur?\n\n**Indicators of a reusable pattern:**\n- You used a specific sequence of searches across multiple sources.\n- You followed a specific verification\u002Fcross-referencing methodology.\n- You wrote code that could be parameterized for different inputs.\n- The output format is generalizable.\n- The user is likely to ask for similar work on a different topic.\n\n**For each identified pattern:**\n1. Identify the composable pieces (DRY, MECE):\n   - Shared logic → `lib\u002F` (not copy-pasted into skills)\n   - Search methodology → skill or lib function\n   - Output template → brain template or skill phase\n   - Filing logic → already covered by brain-taxonomist + active pack\n2. DRY check via the v0.19 resolver:\n   ```bash\n   gbrain check-resolvable\n   ```\n   Look for overlapping triggers or unreachable skills.\n\n### 5b. Existing skill audit\nFor ALL skills used or touched during this work, check:\n1. Were any skills BYPASSED? (did you do something manually that a skill should handle?)\n2. Are there skills that OVERLAP with what you just did? (merge candidates)\n3. Is shared code copy-pasted between skills? (extract to `lib\u002F`)\n\n**The MECE question:** If someone asked for this exact work again tomorrow on a different topic, which skills would they invoke? Is the path clear and unambiguous? If not, fix the routing.\n\n### 5c. Present the plan\n```\n## Skill Graph Changes\n\n### New skills to create\n1. **[skill-name]** — [what it does]\n   - DRY check: [clean \u002F overlaps with X]\n   - Recommendation: [create \u002F merge into X]\n\n### Existing skills to update\n1. **[skill-name]** — [what changed, why]\n\n### Code to extract to lib\u002F\n1. **lib\u002F[name].ts** — [what it does, which skills use it]\n\n### Skills to merge or deprecate\n1. **[skill-A] + [skill-B]** → [merged-skill] — [why]\n```\n\nOn approval: invoke `\u002Fskillify` for each new\u002Fmodified skill.\n\n## Phase 6: CHECK_RESOLVABLE — Verify everything routes\n\nAfter all filing and skillification:\n\n```bash\ngbrain check-resolvable                         # routing-table reachability\ngbrain doctor --json                            # health surface\ngbrain search \"\u003Ctopic keywords>\"                # brain pages findable\ngbrain orphans                                  # any pages without inbound links?\n```\n\nConfirm:\n- [ ] All brain pages have proper frontmatter against active schema pack\n- [ ] All entity pages are cross-linked\n- [ ] Any new skills have routing entries in `skills\u002FRESOLVER.md`\n- [ ] No DRY violations (no duplicated logic across skills)\n- [ ] No MECE violations (no ambiguous routing between skills)\n- [ ] Active schema pack updated if new content types emerged\n- [ ] `gbrain doctor` reports `schema_pack_consistency: ok`\n\n## Phase 7: REPORT — Summary\n\n```markdown\n## EIIRP Complete: [Topic]\n\n### Brain pages created\u002Fupdated\n- [path] — [description]\n- ...\n\n### Entity pages\n- [path] — [created\u002Fupdated]\n- ...\n\n### Schema changes\n- [none \u002F description of changes + which pack delta file]\n\n### Skills identified\n- [skill-name] — [status: created \u002F merged \u002F deferred]\n- ...\n\n### Resolver status\n- DRY check: [clean]\n- MECE audit: [clean]\n- Active pack: [name] v[version]\n- schema_pack_consistency: [ok \u002F warn — pct untyped]\n```\n\n## Output Format\n\nEIIRP produces a single Phase 7 report block. Plain markdown:\n\n```markdown\n## EIIRP Complete: [topic]\n\n### Brain pages created\u002Fupdated\n- [path] — [description]\n\n### Entity pages\n- [path] — [created|updated]\n\n### Schema changes\n- [none | description of changes + which pack delta file]\n\n### Skills identified\n- [skill-name] — [status: created|merged|deferred]\n\n### Resolver status\n- DRY check: [clean|N violations]\n- MECE audit: [clean|N overlaps]\n- Active pack: [name] v[version]\n- schema_pack_consistency: [ok|warn — N% untyped]\n```\n\nAlways machine-readable: stable section headers + bullet-per-item. The\nreport doubles as a sync checkpoint for downstream skills (skillpack-check\nreads it; doctor cross-references the pack version).\n\n## Anti-Patterns\n\n- **Hardcoding directory tables in EIIRP's logic.** Every filing decision\n  reads `gbrain schema show --json`. Users on `gbrain-recommended` AND\n  custom packs MUST get the right behavior automatically. Pinned by D9\n  from \u002Fplan-eng-review.\n- **Auto-applying low-confidence schema suggestions.** Confidence \u003C 0.6\n  from `gbrain schema suggest` is \"manual review required\" per codex\n  finding #9. EIIRP surfaces it; the user accepts.\n- **Skipping Phase 5 SKILL GRAPH AUDIT because \"this was a one-off.\"**\n  If the work took >10 minutes, the methodology is probably reusable.\n  Audit anyway; defer the skillify decision to the user.\n- **Filing synthesis output by topic alone.** Synthesis pages tied to a\n  single source + reader are sui generis; they file under\n  `media\u002F\u003Cformat>\u002F\u003Cslug>-personalized.md`. See _brain-filing-rules.md\n  \"Sanctioned exception\" section.\n- **Treating non-English sources as secondary citations.** Multilingual\n  sources are first-class.\n\n## Hard Rules\n\n### Knowledge domain\n- **Never leave research only in chat.** If it took >10 minutes to produce, it gets a brain page.\n- **Every source gets a citation.** No \"according to reports\" without a URL.\n- **Entity pages get updated, not just created.** If a brain page exists, UPDATE it.\n- **Schema changes require confirmation.** The active pack is load-bearing.\n- **Multilingual sources are first-class.** Never treat non-English sources as secondary.\n\n### Capability domain\n- **DRY is sacred.** If the same logic appears in two skills, extract it to `lib\u002F`.\n- **MECE is sacred.** Every trigger phrase routes to exactly one skill.\n- **Composability over monoliths.** Small skills that compose > one giant skill that does everything.\n- **Skillify only what recurs.** One-off work doesn't need a skill. Patterns that repeat 2+ times do.\n\n### Meta\n- **EIIRP is idempotent.** Running it twice on the same work should produce no changes the second time.\n- **EIIRP consumes the active schema pack as data.** Never hard-code directory tables in EIIRP's logic — read from `gbrain schema show --json` so users who picked `gbrain-recommended` OR custom packs get the right behavior automatically.\n\n## Changelog\n\n### v1.0.0 — gbrain v0.39.0.0\n- Initial port from upstream OpenClaw. Genericized — no references to\n  private fork names per CLAUDE.md privacy rules.\n- Phase 3 SCHEMA CHECK rewritten to consume the v0.39 cathedral CLI\n  (`detect | suggest | review-candidates`) instead of a private\n  `brain\u002Fschema.md`.\n- Phase 5 SKILL GRAPH AUDIT calls `gbrain check-resolvable` instead of\n  upstream `scripts\u002Fskill-dry-check.mjs`.\n- Phase 6 verification uses `gbrain doctor`'s schema_pack_consistency\n  check (T7) for the persistent surface.\n","# EIIRP — Everything In Its Right Place\n\n> *\"Everything in its right place\"* — Radiohead, Kid A\n\n## Contract\n\nAfter any significant work, EIIRP organizes ALL outputs across two domains:\n\n**Knowledge domain (brain):**\n1. Every piece of knowledge lands in the correct brain location.\n2. All sources are cited and linked.\n3. The active schema pack is updated if a new content type emerged.\n4. Entity pages created\u002Fupdated with cross-links.\n\n**Capability domain (skills):**\n5. Every reusable pattern becomes a composable skill.\n6. Existing skills are audited for DRY violations.\n7. Skill graph is MECE — no gaps, no overlaps, no ambiguous routing.\n\n**The meta-guarantee:** Nothing produced during significant work lives only in chat.\nKnowledge → brain. Patterns → skills. Everything in its right place.\n\n## When to Use\n\n- After completing a deep research thread.\n- After building something new (code, pipeline, workflow).\n- After a multi-source analysis that produced significant findings.\n- When the user says \"EIIRP\", \"organize this\", \"DRY this up\", \"make this re-doable\".\n- When a work session produced both knowledge AND new capabilities.\n- When you notice skill overlap, duplication, or gaps.\n\n## Phase 1: INVENTORY — What did we produce?\n\nScan the current session\u002Fthread and identify ALL outputs across both domains.\n\n### Knowledge outputs\n```\n□ Primary findings (the synthesis)\n□ Source documents (URLs, PDFs, articles, tweets)\n□ Entity mentions (people, companies, organizations, places)\n□ Concepts\u002Fframeworks (reusable mental models)\n□ Data artifacts (structured data, timelines, statistics)\n```\n\n### Capability outputs\n```\n□ New skills created or modified\n□ Scripts\u002Fcode written (should they be in lib\u002F or scripts\u002F?)\n□ Methodology used (search patterns, source chains, verification steps)\n□ Workflows that could be automated (cron, pipeline, webhook)\n□ Patterns that will recur (→ candidate for skillification)\n```\n\nProduce a manifest:\n\n```markdown\n## EIIRP Manifest\n- Topic: [topic]\n- Date: [date]\n- Knowledge outputs: [count] (sources, entities, concepts)\n- Capability outputs: [count] (skills, scripts, patterns)\n- Reusable methodology: [yes\u002Fno — describe if yes]\n```\n\n## Phase 2: TAXONOMY — Where does each piece go?\n\n**Read the active schema pack first** (the single source of truth for\nfiling decisions in v0.39+):\n\n```bash\ngbrain schema show --json\n```\n\nThe pack's `page_types[]` lists every directory the brain accepts plus\nthe primitive each maps to. Walk it for each output and pick the directory\nwhose `path_prefixes` matches the content's primary subject.\n\nIf `brain-taxonomist` is installed, INVOKE IT for ambiguous cases. It runs\nthe same decision protocol against the active pack and gives you a single\nrecommended filing path with reasoning.\n\nOutput: a filing plan table:\n\n```\n| Content | Brain path | Action |\n|---------|-----------|--------|\n| Primary research | reference\u002F...\u002Fpage.md | CREATE |\n| Person X | people\u002Fx-slug.md | CREATE |\n| Person Y | people\u002Fy-slug.md | UPDATE (already exists) |\n| ... | ... | ... |\n```\n\n## Phase 3: SCHEMA CHECK — Does the active pack cover this content?\n\nThis is where EIIRP closes the schema-derivation loop. If the work\nproduced content that doesn't fit any existing `page_types`, propose\nadding a new type via the v0.39 cathedral:\n\n```bash\n# What's emerging in the brain that the active pack doesn't cover?\ngbrain schema detect --json\n\n# LLM-refined suggestions (heuristic when no API key set).\ngbrain schema suggest --json\n\n# Review what's pending; promote or ignore each candidate.\ngbrain schema review-candidates --json\ngbrain schema review-candidates --apply \u003Cprefix-or-type-name>\n```\n\n**Confidence floor (codex finding #9):** when `gbrain schema suggest`\nreturns confidence \u003C 0.6 on a proposed type, DO NOT auto-apply. Surface\nthe suggestion to the user and let them choose. The schema-cathedral\nships the primitives; EIIRP enforces the human-in-the-loop gate.\n\nIf schema needs change:\n- Propose the addition to the user before running `review-candidates --apply`.\n- Document the change in the commit message of the next sync.\n- The schema-pack engine writes the delta to\n  `~\u002F.gbrain\u002Fschema-pack-deltas\u002F` — review and merge into the active\n  pack via `gbrain schema edit` (or hand-edit the YAML).\n\n## Phase 4: FILE — Create enriched brain pages\n\nFor each item in the filing plan:\n\n### 4a. Primary research page\nUse the brain page template. MUST include:\n- Proper frontmatter (`type`, `title`, `date`, `tags`, sources)\n- **State** section — current status\u002Fkey findings\n- **Sources** section — every source with URL, author, date, language\n- **Timeline** section — chronological development\n- **Entity links** — backlinks to all related brain pages\n- **See Also** — related concepts, reference pages\n\n### 4b. Entity pages (people, companies)\nFor each entity mentioned:\n- Check if a brain page exists (`gbrain search \"\u003Cname>\"` or `gbrain get_page people\u002F\u003Cslug>`).\n- If exists: update State, append Timeline entry citing this research.\n- If not: create with enrichment.\n\n### 4c. Commit and verify\nAfter ALL pages are written, run `gbrain sync` (or commit + push in the\nbrain repo). Verify every link resolves.\n\n## Phase 5: SKILL GRAPH AUDIT — DRY + MECE on capabilities\n\nThis phase operates on the SKILL graph, not just the research.\n\n### 5a. New pattern identification\n\nAsk: did this work reveal REPEATABLE patterns that will recur?\n\n**Indicators of a reusable pattern:**\n- You used a specific sequence of searches across multiple sources.\n- You followed a specific verification\u002Fcross-referencing methodology.\n- You wrote code that could be parameterized for different inputs.\n- The output format is generalizable.\n- The user is likely to ask for similar work on a different topic.\n\n**For each identified pattern:**\n1. Identify the composable pieces (DRY, MECE):\n   - Shared logic → `lib\u002F` (not copy-pasted into skills)\n   - Search methodology → skill or lib function\n   - Output template → brain template or skill phase\n   - Filing logic → already covered by brain-taxonomist + active pack\n2. DRY check via the v0.19 resolver:\n   ```bash\n   gbrain check-resolvable\n   ```\n   Look for overlapping triggers or unreachable skills.\n\n### 5b. Existing skill audit\nFor ALL skills used or touched during this work, check:\n1. Were any skills BYPASSED? (did you do something manually that a skill should handle?)\n2. Are there skills that OVERLAP with what you just did? (merge candidates)\n3. Is shared code copy-pasted between skills? (extract to `lib\u002F`)\n\n**The MECE question:** If someone asked for this exact work again tomorrow on a different topic, which skills would they invoke? Is the path clear and unambiguous? If not, fix the routing.\n\n### 5c. Present the plan\n```\n## Skill Graph Changes\n\n### New skills to create\n1. **[skill-name]** — [what it does]\n   - DRY check: [clean \u002F overlaps with X]\n   - Recommendation: [create \u002F merge into X]\n\n### Existing skills to update\n1. **[skill-name]** — [what changed, why]\n\n### Code to extract to lib\u002F\n1. **lib\u002F[name].ts** — [what it does, which skills use it]\n\n### Skills to merge or deprecate\n1. **[skill-A] + [skill-B]** → [merged-skill] — [why]\n```\n\nOn approval: invoke `\u002Fskillify` for each new\u002Fmodified skill.\n\n## Phase 6: CHECK_RESOLVABLE — Verify everything routes\n\nAfter all filing and skillification:\n\n```bash\ngbrain check-resolvable                         # routing-table reachability\ngbrain doctor --json                            # health surface\ngbrain search \"\u003Ctopic keywords>\"                # brain pages findable\ngbrain orphans                                  # any pages without inbound links?\n```\n\nConfirm:\n- [ ] All brain pages have proper frontmatter against active schema pack\n- [ ] All entity pages are cross-linked\n- [ ] Any new skills have routing entries in `skills\u002FRESOLVER.md`\n- [ ] No DRY violations (no duplicated logic across skills)\n- [ ] No MECE violations (no ambiguous routing between skills)\n- [ ] Active schema pack updated if new content types emerged\n- [ ] `gbrain doctor` reports `schema_pack_consistency: ok`\n\n## Phase 7: REPORT — Summary\n\n```markdown\n## EIIRP Complete: [Topic]\n\n### Brain pages created\u002Fupdated\n- [path] — [description]\n- ...\n\n### Entity pages\n- [path] — [created\u002Fupdated]\n- ...\n\n### Schema changes\n- [none \u002F description of changes + which pack delta file]\n\n### Skills identified\n- [skill-name] — [status: created \u002F merged \u002F deferred]\n- ...\n\n### Resolver status\n- DRY check: [clean]\n- MECE audit: [clean]\n- Active pack: [name] v[version]\n- schema_pack_consistency: [ok \u002F warn — pct untyped]\n```\n\n## Output Format\n\nEIIRP produces a single Phase 7 report block. Plain markdown:\n\n```markdown\n## EIIRP Complete: [topic]\n\n### Brain pages created\u002Fupdated\n- [path] — [description]\n\n### Entity pages\n- [path] — [created|updated]\n\n### Schema changes\n- [none | description of changes + which pack delta file]\n\n### Skills identified\n- [skill-name] — [status: created|merged|deferred]\n\n### Resolver status\n- DRY check: [clean|N violations]\n- MECE audit: [clean|N overlaps]\n- Active pack: [name] v[version]\n- schema_pack_consistency: [ok|warn — N% untyped]\n```\n\nAlways machine-readable: stable section headers + bullet-per-item. The\nreport doubles as a sync checkpoint for downstream skills (skillpack-check\nreads it; doctor cross-references the pack version).\n\n## Anti-Patterns\n\n- **Hardcoding directory tables in EIIRP's logic.** Every filing decision\n  reads `gbrain schema show --json`. Users on `gbrain-recommended` AND\n  custom packs MUST get the right behavior automatically. Pinned by D9\n  from \u002Fplan-eng-review.\n- **Auto-applying low-confidence schema suggestions.** Confidence \u003C 0.6\n  from `gbrain schema suggest` is \"manual review required\" per codex\n  finding #9. EIIRP surfaces it; the user accepts.\n- **Skipping Phase 5 SKILL GRAPH AUDIT because \"this was a one-off.\"**\n  If the work took >10 minutes, the methodology is probably reusable.\n  Audit anyway; defer the skillify decision to the user.\n- **Filing synthesis output by topic alone.** Synthesis pages tied to a\n  single source + reader are sui generis; they file under\n  `media\u002F\u003Cformat>\u002F\u003Cslug>-personalized.md`. See _brain-filing-rules.md\n  \"Sanctioned exception\" section.\n- **Treating non-English sources as secondary citations.** Multilingual\n  sources are first-class.\n\n## Hard Rules\n\n### Knowledge domain\n- **Never leave research only in chat.** If it took >10 minutes to produce, it gets a brain page.\n- **Every source gets a citation.** No \"according to reports\" without a URL.\n- **Entity pages get updated, not just created.** If a brain page exists, UPDATE it.\n- **Schema changes require confirmation.** The active pack is load-bearing.\n- **Multilingual sources are first-class.** Never treat non-English sources as secondary.\n\n### Capability domain\n- **DRY is sacred.** If the same logic appears in two skills, extract it to `lib\u002F`.\n- **MECE is sacred.** Every trigger phrase routes to exactly one skill.\n- **Composability over monoliths.** Small skills that compose > one giant skill that does everything.\n- **Skillify only what recurs.** One-off work doesn't need a skill. Patterns that repeat 2+ times do.\n\n### Meta\n- **EIIRP is idempotent.** Running it twice on the same work should produce no changes the second time.\n- **EIIRP consumes the active schema pack as data.** Never hard-code directory tables in EIIRP's logic — read from `gbrain schema show --json` so users who picked `gbrain-recommended` OR custom packs get the right behavior automatically.\n\n## Changelog\n\n### v1.0.0 — gbrain v0.39.0.0\n- Initial port from upstream OpenClaw. Genericized — no references to\n  private fork names per CLAUDE.md privacy rules.\n- Phase 3 SCHEMA CHECK rewritten to consume the v0.39 cathedral CLI\n  (`detect | suggest | review-candidates`) instead of a private\n  `brain\u002Fschema.md`.\n- Phase 5 SKILL GRAPH AUDIT calls `gbrain check-resolvable` instead of\n  upstream `scripts\u002Fskill-dry-check.mjs`.\n- Phase 6 verification uses `gbrain doctor`'s schema_pack_consistency\n  check (T7) for the persistent surface.\n",{"name":5,"tools":24,"version":31,"mutating":32,"triggers":33,"writes_to":49,"description":60,"writes_pages":32,"distinct_from":61,"filing_exempt":32,"prompt_version":71},[25,26,27,28,29,30],"search","query","get_page","put_page","add_link","add_timeline_entry","1.0.0",true,[34,5,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"everything in its right place","store this research","put this in the brain","file this properly","where does this research go","make this permanent","archive this research","archive this research thread","brain this","file all of this","organize all of this","organize all of this work","make this re-doable","DRY this up","check everything is in the right place",[50,51,52,53,54,55,56,57,58,59],"people\u002F","companies\u002F","deals\u002F","meetings\u002F","concepts\u002F","projects\u002F","civic\u002F","writing\u002F","analysis\u002F","guides\u002F","Everything In Its Right Place. The universal post-work organizer. After\nany significant work session, EIIRP runs a 7-phase audit: (1) inventory\nevery output, (2) walk taxonomy to decide where each lands, (3) check\nschema-pack consistency against the brain's actual shape, (4) file\nenriched brain pages, (5) audit the skill graph for DRY+MECE, (6) verify\nresolvability, (7) report. Named after the Radiohead song. Nothing\nproduced during significant work lives only in chat — knowledge becomes\npermanent, patterns become reusable.\n",[62,65,68],{"name":63,"reason":64},"brain-taxonomist","brain-taxonomist classifies individual pages at write time (the filing GATE). EIIRP orchestrates the full post-work LIFECYCLE — inventory + taxonomy + schema + skillify + verify.",{"name":66,"reason":67},"ingest","ingest handles NEW content from external URLs\u002Fmedia. EIIRP handles COMPLETED research that needs to be decomposed and filed across multiple brain locations.",{"name":69,"reason":70},"skillify","skillify is the meta-skill for turning a feature into a tested skill. EIIRP calls skillify when Phase 5 identifies a reusable pattern.",1,"main","8a1ba5bf6fb27ae3c622d36b4287f8a96555c805","skills\u002Feiirp","https:\u002F\u002Fgithub.com\u002Fmoonstachain\u002Fgbrain-yuanli","https:\u002F\u002Fgithub.com\u002Fmoonstachain","2026-09-16 09:55:03",{"source":8,"skillName":5,"commands":79,"prompt":89,"zipAvailable":32},[80,83,86],{"tool":81,"command":82},"npx","npx skills add moonstachain\u002Fgbrain-yuanli --skill eiirp",{"tool":84,"command":85},"bunx","bunx skills add moonstachain\u002Fgbrain-yuanli --skill eiirp",{"tool":87,"command":88},"pnpm","pnpm dlx skills add moonstachain\u002Fgbrain-yuanli --skill eiirp","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmoonstachain\u002Fgbrain-yuanli\u002Fblob\u002Fmain\u002Fskills\u002Feiirp\u002FSKILL.md",[91],{"path":92,"resourceType":93,"resourceTypeDesc":94,"sizeBytes":95,"sourceHtmlUrl":96},"routing-eval.jsonl","OTHER","其他",779,"https:\u002F\u002Fgithub.com\u002Fmoonstachain\u002Fgbrain-yuanli\u002Fblob\u002Fmain\u002Fskills\u002Feiirp\u002Frouting-eval.jsonl",[98,104,110,117,124,130],{"skillNo":99,"name":100,"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":101,"categories":102,"keywords":103,"publishedAt":19},"01M7813JZE1PE2C5VYE92ENW0K","query-helper","https:\u002F\u002Fgithub.com\u002Fmoonstachain\u002Fgbrain-yuanli\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fskill-catalog\u002Fskills\u002Fquery-helper\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"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":107,"categories":108,"keywords":109,"publishedAt":19},"01M7813J1CEF860359MM2X0E9F","broken","https:\u002F\u002Fgithub.com\u002Fmoonstachain\u002Fgbrain-yuanli\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fskill-catalog\u002Fskills\u002Fbroken\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":19},"01M7813EM189HRGPS6JMYWGDBY","brain-ops","Read, enrich, and write brain pages with source attribution.","https:\u002F\u002Fgithub.com\u002Fmoonstachain\u002Fgbrain-yuanli\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fskill-catalog\u002Fskills\u002Fbrain-ops\u002FSKILL.md",[],[],{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":19},"01M7813BNHV1F88ZSEZC7FVE30","signal-detector","Always-on ambient signal capture for the OpenClaw reference fixture.","https:\u002F\u002Fgithub.com\u002Fmoonstachain\u002Fgbrain-yuanli\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fopenclaw-reference-minimal\u002Fskills\u002Fsignal-detector\u002FSKILL.md",[],[],{"skillNo":125,"name":26,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":19},"01M78138QAK5AM8ZJV3DEYZZZN","Look up brain pages in the OpenClaw reference fixture.","https:\u002F\u002Fgithub.com\u002Fmoonstachain\u002Fgbrain-yuanli\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fopenclaw-reference-minimal\u002Fskills\u002Fquery\u002FSKILL.md",[],[],{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":136,"publishedAt":19},"01M78135RC63M8RZNK0TTHRBTS","context-now","ALWAYS-ON time-sensitivity discipline for the OpenClaw reference fixture.","https:\u002F\u002Fgithub.com\u002Fmoonstachain\u002Fgbrain-yuanli\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fopenclaw-reference-minimal\u002Fskills\u002Fcontext-now\u002FSKILL.md",[],[]]