[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71CBDCF49RWNC14B0C5JRB6":3,"skill-same:01M71CBDCF49RWNC14B0C5JRB6":69},{"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":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":6,"ownerHtmlUrl":52,"ownerBlogUrl":6,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M71CBDCF49RWNC14B0C5JRB6","pilot-feedback",null,"Capture and compound pilot-user feedback (good + negative) into a ledger; ingest a pilot's git branch for passive signal; report polarity+tag patterns for improvement routing.","nexuslinkproductions\u002Fyuri-os","nexuslinkproductions","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F273246263?v=4","01M718YX9NZRCW50B59B8ZVDKN","Marcel Spatz","01M718YXAQ7530F4B1VKN6SFQV",2,"MIT","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fpilot-feedback\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36],"pilot feedback","feedback","user","ledger","patterns","passive","capture","git","report","compound","routing","git branch","ingest","good","signal","for","improvement","branch","2026-11-10 10:12:30",false,"---\nname: pilot-feedback\ndescription: Capture and compound pilot-user feedback (good + negative) into a ledger; ingest a pilot's git branch for passive signal; report polarity+tag patterns for improvement routing.\ntriggers:\n  - pilot feedback\n  - user feedback\n  - ingest rene\n  - ingest dad branch\n  - compounding feedback\n---\n\n# pilot-feedback\n\nThe compounding loop that turns real pilot-user usage (René today, Marcel next) into structured\nimprovement signal. **Both good and negative feedback are captured** — negative feedback is the\nhigh-value ΔU\u002Fsurprise signal (it points at what's broken\u002Fwrong\u002Frejected); positive feedback\nconfirms what to keep + compound.\n\n## When to invoke\n\n- After fetching a pilot's branch (`git fetch`, review their recent commits) → `ingest-git`.\n- When the operator says \"good\"\u002F\"bad\" about a session\u002Foutput\u002Ffeature → `add` explicit.\n- Periodically (or before a design pass) → `report` to see where the friction concentrates.\n\n## The mechanism (capability: `pilot-feedback-capture`)\n\nScript: `node _SYSTEM\u002FScripts\u002Fpilot-feedback.mjs \u003Ccmd>`\nLedger: `_SYSTEM\u002Fstate\u002Fpilot-feedback.jsonl` (append-only JSONL via `_SYSTEM\u002Flib\u002Fjsonl.mjs`).\n\n| command | what it does |\n|---|---|\n| `add --pilot \u003Cname> --polarity good\\|bad\\|neutral [--source explicit\\|commit\\|session] [--tag \u003Carea>] [--note \"...\"]` | record one explicit feedback event |\n| `ingest-git --pilot \u003Cname> --branch \u003Cref> [--since 1d] [--author \u003Cname>]` | parse a pilot's branch commits; classify each subject → good\u002Fbad + tag; record signal-bearing ones (neutral skipped) |\n| `report [--pilot \u003Cname>]` | aggregate by polarity + tag, print recent 5 |\n\n### Tags (auto-classified)\n`voice` · `file-io` · `safety` · `memory` · `launcher` · `persona` · `tool` · `automation` · `other`\n\n### Polarity heuristic (commit subjects)\n- **bad** = the prior state was wrong\u002Frejected: `replac…\u002Freject\u002Fbroken\u002Fwrong\u002Ffix\u002Frollback\u002Frevert\u002Fcrash\u002Fhang\u002Ffail\u002Fmissing\u002Fdead`\n- **good** = addition\u002Fbuild\u002Fenable: `add\u002Fnew\u002Fimprove\u002Fship\u002Ffeature\u002Fenable\u002Fwire\u002Fscaffold\u002Flaunch\u002Fbuilds`\n- A commit with BOTH (e.g., \"Kokoro replaces robotic SAPI\") → **bad** (it's a rejection of the prior).\n\n## How it compounds\n\n1. **Capture** — `ingest-git` after every pilot fetch + `add` for in-session explicit feedback.\n2. **Report** — before a design\u002Fbuild pass, run `report` to see where friction concentrates (high `bad` count in a tag = priority fix).\n3. **Route** — negative feedback in a tag feeds the corresponding roadmap phase (e.g., `voice` bad-count → A0 voice quality; `memory` → A3 NEURO_CORE). Negative feedback = the ΔU\u002Fsurprise that NEURO_CORE weights heavily (write_strength = |ΔU| × precision).\n4. **Synthesize** (periodic, GLM lane) — a higher-level pass over the ledger produces improvement proposals → memory proposals → skill updates. (Future wiring; the deterministic `report` is the v1.)\n\n## Worked example (2026-07-05, René's branch)\n\nManual review of `origin\u002Frene` surfaced: robotic TTS rejected (bad\u002Fvoice), PDF\u002FWord\u002FExcel text\nextraction added (good→fix, bad\u002Ffile-io on the prior raw-bytes), folder-scoped safety (good\u002Fsafety),\nlocal FTS5 second-brain (good\u002Fmemory), one-word launcher (good\u002Flauncher). That manual review is\nexactly what `ingest-git` automates:\n\n```bash\nnode _SYSTEM\u002FScripts\u002Fpilot-feedback.mjs ingest-git --pilot rene --branch origin\u002Frene --since 1d --author \"René\"\nnode _SYSTEM\u002FScripts\u002Fpilot-feedback.mjs report --pilot rene\n```\n\n## Session Notes\n- 2026-07-05: built v1 (add + ingest-git + report + hermetic tests 5\u002F5). Ledger at `_SYSTEM\u002Fstate\u002Fpilot-feedback.jsonl`. Feeds A0–A5 priority via the negative-feedback signal. Next: GLM synthesis pass for cross-session pattern extraction.\n","# pilot-feedback\n\nThe compounding loop that turns real pilot-user usage (René today, Marcel next) into structured\nimprovement signal. **Both good and negative feedback are captured** — negative feedback is the\nhigh-value ΔU\u002Fsurprise signal (it points at what's broken\u002Fwrong\u002Frejected); positive feedback\nconfirms what to keep + compound.\n\n## When to invoke\n\n- After fetching a pilot's branch (`git fetch`, review their recent commits) → `ingest-git`.\n- When the operator says \"good\"\u002F\"bad\" about a session\u002Foutput\u002Ffeature → `add` explicit.\n- Periodically (or before a design pass) → `report` to see where the friction concentrates.\n\n## The mechanism (capability: `pilot-feedback-capture`)\n\nScript: `node _SYSTEM\u002FScripts\u002Fpilot-feedback.mjs \u003Ccmd>`\nLedger: `_SYSTEM\u002Fstate\u002Fpilot-feedback.jsonl` (append-only JSONL via `_SYSTEM\u002Flib\u002Fjsonl.mjs`).\n\n| command | what it does |\n|---|---|\n| `add --pilot \u003Cname> --polarity good\\|bad\\|neutral [--source explicit\\|commit\\|session] [--tag \u003Carea>] [--note \"...\"]` | record one explicit feedback event |\n| `ingest-git --pilot \u003Cname> --branch \u003Cref> [--since 1d] [--author \u003Cname>]` | parse a pilot's branch commits; classify each subject → good\u002Fbad + tag; record signal-bearing ones (neutral skipped) |\n| `report [--pilot \u003Cname>]` | aggregate by polarity + tag, print recent 5 |\n\n### Tags (auto-classified)\n`voice` · `file-io` · `safety` · `memory` · `launcher` · `persona` · `tool` · `automation` · `other`\n\n### Polarity heuristic (commit subjects)\n- **bad** = the prior state was wrong\u002Frejected: `replac…\u002Freject\u002Fbroken\u002Fwrong\u002Ffix\u002Frollback\u002Frevert\u002Fcrash\u002Fhang\u002Ffail\u002Fmissing\u002Fdead`\n- **good** = addition\u002Fbuild\u002Fenable: `add\u002Fnew\u002Fimprove\u002Fship\u002Ffeature\u002Fenable\u002Fwire\u002Fscaffold\u002Flaunch\u002Fbuilds`\n- A commit with BOTH (e.g., \"Kokoro replaces robotic SAPI\") → **bad** (it's a rejection of the prior).\n\n## How it compounds\n\n1. **Capture** — `ingest-git` after every pilot fetch + `add` for in-session explicit feedback.\n2. **Report** — before a design\u002Fbuild pass, run `report` to see where friction concentrates (high `bad` count in a tag = priority fix).\n3. **Route** — negative feedback in a tag feeds the corresponding roadmap phase (e.g., `voice` bad-count → A0 voice quality; `memory` → A3 NEURO_CORE). Negative feedback = the ΔU\u002Fsurprise that NEURO_CORE weights heavily (write_strength = |ΔU| × precision).\n4. **Synthesize** (periodic, GLM lane) — a higher-level pass over the ledger produces improvement proposals → memory proposals → skill updates. (Future wiring; the deterministic `report` is the v1.)\n\n## Worked example (2026-07-05, René's branch)\n\nManual review of `origin\u002Frene` surfaced: robotic TTS rejected (bad\u002Fvoice), PDF\u002FWord\u002FExcel text\nextraction added (good→fix, bad\u002Ffile-io on the prior raw-bytes), folder-scoped safety (good\u002Fsafety),\nlocal FTS5 second-brain (good\u002Fmemory), one-word launcher (good\u002Flauncher). That manual review is\nexactly what `ingest-git` automates:\n\n```bash\nnode _SYSTEM\u002FScripts\u002Fpilot-feedback.mjs ingest-git --pilot rene --branch origin\u002Frene --since 1d --author \"René\"\nnode _SYSTEM\u002FScripts\u002Fpilot-feedback.mjs report --pilot rene\n```\n\n## Session Notes\n- 2026-07-05: built v1 (add + ingest-git + report + hermetic tests 5\u002F5). Ledger at `_SYSTEM\u002Fstate\u002Fpilot-feedback.jsonl`. Feeds A0–A5 priority via the negative-feedback signal. Next: GLM synthesis pass for cross-session pattern extraction.\n",{"name":5,"triggers":42,"description":7},[19,43,44,45,46],"user feedback","ingest rene","ingest dad branch","compounding feedback","main","4c6d8d65f3d6096e2fc25b0845e481dda73c2794","skills\u002Fpilot-feedback",0,"https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions","Building deterministic AI governance and continuity systems. Workflow architect + visual storyteller","2026-11-14 03:05:17",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add nexuslinkproductions\u002Fyuri-os --skill pilot-feedback",{"tool":61,"command":62},"bunx","bunx skills add nexuslinkproductions\u002Fyuri-os --skill pilot-feedback",{"tool":64,"command":65},"pnpm","pnpm dlx skills add nexuslinkproductions\u002Fyuri-os --skill pilot-feedback","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fpilot-feedback\u002FSKILL.md",true,[],[70,93,116,146,175,193],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":37},"01M71CG1AME5WC0A79AE65WT0X","zoom-out","Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fzoom-out\u002FSKILL.md",[],[77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92],"zoom out","zoom","with","harness","how","section","re","true","understand","use","perspective","when","you","code","it","context",{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":37},"01M71CFY9ATD0BAXV6B14HFG7C","yuri-shura","6-perspective adversarial review for high-stakes turns (architecture decisions, refactor planning, deployment review) — fans out architect, adversary (7-vector attack), maintainer, ops, product, and security perspectives in parallel, then consolidates. Use when user says 'review this decision', '\u002Fshura', 'adversarial review', 'what could go wrong', 'architecture review', or 'deployment review'.","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fyuri-shura\u002FSKILL.md",[],[100,101,80,102,103,34,104,105,106,107,108,86,109,88,110,111,112,113,114,115],"yuri shura","parallel","architecture review","planning","deployment","vector","strategic review","decision","strategic","ops","workflow","decisions","architecture","review","perspectives","adversarial",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":127,"publishedAt":37},"01M71CFTTYW1HA2MNX38EV1GJ5","yuri-sales-intelligence","Unified sales and outreach skill generating cold outreach openers, social selling sequences, objection rebuttals, and ad creative for any paid platform — multi-persona aware, adapting tone and offer frame to buyer type. Use when user says 'write a cold email', 'outreach sequence', 'objection handling', 'ad copy', or 'sales pitch'.","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fyuri-sales-intelligence\u002FSKILL.md",[122],{"categoryNo":123,"categoryName":124,"taxonomyType":125,"taxonomyTypeDesc":126},"01JBSEEDCAT000000000000005","邮件与沟通","SCENARIO","使用场景",[128,129,130,131,132,133,134,135,136,88,137,138,139,140,141,142,143,34,144,145],"intelligence","sales intelligence","yuri sales intelligence","sales","cold","paid","social","persona","pitch","cold email","ad creative","write","sequences","sequence","platform","email","cold outreach","frame",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":160,"publishedAt":37},"01M71CFQMBFTFADJNGP0Z2WCYK","yuri-code-intelligence","Unified code quality intelligence layer that diagnoses code smells (Long Method, Feature Envy, design pattern issues), prescribes targeted Fowler refactoring techniques, and reviews code for security, performance, and clarity. Use when user says 'review this code', 'refactor this', 'what's wrong with this method', 'code smells', or 'clean this up'.","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fyuri-code-intelligence\u002FSKILL.md",[152,155],{"categoryNo":153,"categoryName":154,"taxonomyType":125,"taxonomyTypeDesc":126},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":156,"categoryName":157,"taxonomyType":158,"taxonomyTypeDesc":159},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[161,90,162,128,80,163,164,165,34,166,167,168,169,170,171,172,173,174,86,88],"yuri code intelligence","code intelligence","reviews","code quality","feature","performance","code review","long","up","issues","clean","techniques","improve","design",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":181,"publishedAt":37},"01M71CFP32RT6GD3GKNHCJP8VP","yuri-adw","Invoke when user asks to run the ADW loop \u002F agentic engineering loop \u002F software factory workflow.","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fyuri-adw\u002FSKILL.md",[],[182,183,184,185,186,187,188,189,190,88,191,110,192,21],"yuri adw","run","engineering loop","software factory","software","agentic engineering","factory","loop","invoke","engineering","agentic",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":197,"categories":198,"keywords":211,"publishedAt":37},"01M71CFK4VPEKY6A73237P7RSN","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-skills\u002FSKILL.md",[199,202,205,208],{"categoryNo":200,"categoryName":201,"taxonomyType":125,"taxonomyTypeDesc":126},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":203,"categoryName":204,"taxonomyType":125,"taxonomyTypeDesc":126},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":206,"categoryName":207,"taxonomyType":125,"taxonomyTypeDesc":126},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":209,"categoryName":210,"taxonomyType":158,"taxonomyTypeDesc":159},"01JBSEEDCAT000000000000036","内容创作者",[212,213,214,88,110,215,80,216,104,86,217],"writing","writing skills","new","work","editing","Existing"]