[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ERZ8WMFAXBX3YNGP24RTJB":3,"skill-same:01M7ERZ8WMFAXBX3YNGP24RTJB":54},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":14,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7ERZ8WMFAXBX3YNGP24RTJB","reflect",null,"Review a long session through independent lenses and propose edits to existing skills, packs or checks, applied only after they pass skill-tdd. Use at the end of a long or rocky session, or when the user asks to reflect on what the skills got wrong.","Ventorius\u002Fven-stack","Ventorius","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F5689509?v=4","01M7ERRDPQ5YXCNXJZWEKQNP50","Sebastian Basznianin","01M7ERRDQ9S0ZD9YMH1RN1WVP7",0,"MIT","https:\u002F\u002Fgithub.com\u002FVentorius\u002Fven-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fven\u002Fskills\u002Freflect\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: reflect\ndescription: Review a long session through independent lenses and propose edits to existing skills, packs or checks, applied only after they pass skill-tdd. Use at the end of a long or rocky session, or when the user asks to reflect on what the skills got wrong.\nmetadata:\n  layer: L3\n  source: cursor\u002Fplugins@1e5c90a:pstack\u002Fskills\u002Freflect\u002FSKILL.md\n  license: MIT\n---\n\n# Reflect\n\nMine this session for durable learnings about how the work was done, and turn each one into a concrete change to an existing skill, pack or check. Skip trivial sessions, and sessions where the skills were followed and worked. One-offs are not learnings.\n\nNothing is applied to a skill in this session. Skill edits become proposals that **skill-tdd** applies in a later session, so a skill never edits itself in the session that proposed the change.\n\n## 1. Find the transcript\n\nThe transcript is your agent's log of this session, when it keeps one on disk (Claude Code: the newest `*.jsonl` in `\u003Cconfig dir>\u002Fprojects\u002F\u003Crepo path with every non-alphanumeric character replaced by ->\u002F`, where `\u003Cconfig dir>` is `$CLAUDE_CONFIG_DIR` or `~\u002F.claude`). Confirm it by matching its first user message to this session's opening request. Stay in this repo's project directory; never read other projects' transcripts.\n\nNo match: write a digest instead (the requests, corrections, skills used, check refusals, outcomes).\n\nCount corrections from the decisions log first: `ven-decisions list --step correction` shows what the user objected to this session and earlier. The transcript is the fallback and the source for everything else.\n\n## 2. Run three blind lenses\n\n**delegate** to three reviewers at once, each with the brief in `references\u002Flenses.md` (shared part plus its lens) and the transcript path or digest:\n\n| Lens | Looks for | `model` |\n|---|---|---|\n| judgment | The durable principle behind an incident | `orchestrator_model` |\n| tooling | Commands, paths and context the agent rediscovered or the user had to hand over | `coder_model` |\n| divergent | What the other two miss: second-order effects, skipped proof, skills that never fired | `orchestrator_model` |\n\nReviewers never see each other's output. On the `lean` budget tier, run the judgment lens only.\n\n## 3. Synthesize\n\nJudge every finding yourself against these tests, in order:\n\n1. **Structural.** If a check could enforce it, route it to **ratchet** instead of skill text (apply **encode-lessons-in-structure**, which also sets the promotion threshold).\n2. **Durable.** Still true after paths, versions and code shapes change.\n3. **Decision-changing.** A future agent acts differently, not just reads more.\n4. **Used.** The target skill ran in this session, or should have fired and didn't (then the change is to its description).\n5. **Not already covered.** Read the target skill. Already said clearly: the failure was execution, reject it. Said weakly or buried: propose moving or sharpening that line, not adding another.\n6. **Convergent.** A finding from two lenses ranks highest; a singleton must clear every test on its own.\n7. **Agnostic.** Tech, vendor or domain specifics go to a pack skill, never to core.\n\nA finding about the repo rather than about how to work goes to **compound**.\n\n## 4. Present and propose\n\nShow the result and wait for the user to pick rows:\n\n```markdown\n## Accepted\n| Problem | Proposed change | Target (skill and section, or description) |\n## Checks\n| Rule | Rung | Original mistake it must catch |\n## Rejected\n- \u003Cfinding> — \u003Cstructural | durability | decision-changing | not used | already covered | one-off>\n```\n\nFor each picked Accepted row, write a proposal file in the format **skill-tdd** defines. For each picked Checks row, run **ratchet** now (a check is not a skill edit) or queue it as a proposal of kind `check`.\n\n## 5. Summarize\n\n- Proposals written: path and one line each.\n- Checks: added (with path) or queued.\n- Solution entries written.\n- Dropped: one line each, with the reason.\n\n```bash\nven-decisions add --step reflect --decision \"\u003Cn> proposals, \u003Cn> checks, \u003Cn> dropped\" --evidence \"\u003Cproposal paths>\"\n```\n","# Reflect\n\nMine this session for durable learnings about how the work was done, and turn each one into a concrete change to an existing skill, pack or check. Skip trivial sessions, and sessions where the skills were followed and worked. One-offs are not learnings.\n\nNothing is applied to a skill in this session. Skill edits become proposals that **skill-tdd** applies in a later session, so a skill never edits itself in the session that proposed the change.\n\n## 1. Find the transcript\n\nThe transcript is your agent's log of this session, when it keeps one on disk (Claude Code: the newest `*.jsonl` in `\u003Cconfig dir>\u002Fprojects\u002F\u003Crepo path with every non-alphanumeric character replaced by ->\u002F`, where `\u003Cconfig dir>` is `$CLAUDE_CONFIG_DIR` or `~\u002F.claude`). Confirm it by matching its first user message to this session's opening request. Stay in this repo's project directory; never read other projects' transcripts.\n\nNo match: write a digest instead (the requests, corrections, skills used, check refusals, outcomes).\n\nCount corrections from the decisions log first: `ven-decisions list --step correction` shows what the user objected to this session and earlier. The transcript is the fallback and the source for everything else.\n\n## 2. Run three blind lenses\n\n**delegate** to three reviewers at once, each with the brief in `references\u002Flenses.md` (shared part plus its lens) and the transcript path or digest:\n\n| Lens | Looks for | `model` |\n|---|---|---|\n| judgment | The durable principle behind an incident | `orchestrator_model` |\n| tooling | Commands, paths and context the agent rediscovered or the user had to hand over | `coder_model` |\n| divergent | What the other two miss: second-order effects, skipped proof, skills that never fired | `orchestrator_model` |\n\nReviewers never see each other's output. On the `lean` budget tier, run the judgment lens only.\n\n## 3. Synthesize\n\nJudge every finding yourself against these tests, in order:\n\n1. **Structural.** If a check could enforce it, route it to **ratchet** instead of skill text (apply **encode-lessons-in-structure**, which also sets the promotion threshold).\n2. **Durable.** Still true after paths, versions and code shapes change.\n3. **Decision-changing.** A future agent acts differently, not just reads more.\n4. **Used.** The target skill ran in this session, or should have fired and didn't (then the change is to its description).\n5. **Not already covered.** Read the target skill. Already said clearly: the failure was execution, reject it. Said weakly or buried: propose moving or sharpening that line, not adding another.\n6. **Convergent.** A finding from two lenses ranks highest; a singleton must clear every test on its own.\n7. **Agnostic.** Tech, vendor or domain specifics go to a pack skill, never to core.\n\nA finding about the repo rather than about how to work goes to **compound**.\n\n## 4. Present and propose\n\nShow the result and wait for the user to pick rows:\n\n```markdown\n## Accepted\n| Problem | Proposed change | Target (skill and section, or description) |\n## Checks\n| Rule | Rung | Original mistake it must catch |\n## Rejected\n- \u003Cfinding> — \u003Cstructural | durability | decision-changing | not used | already covered | one-off>\n```\n\nFor each picked Accepted row, write a proposal file in the format **skill-tdd** defines. For each picked Checks row, run **ratchet** now (a check is not a skill edit) or queue it as a proposal of kind `check`.\n\n## 5. Summarize\n\n- Proposals written: path and one line each.\n- Checks: added (with path) or queued.\n- Solution entries written.\n- Dropped: one line each, with the reason.\n\n```bash\nven-decisions add --step reflect --decision \"\u003Cn> proposals, \u003Cn> checks, \u003Cn> dropped\" --evidence \"\u003Cproposal paths>\"\n```\n",{"name":5,"metadata":24,"description":7},{"layer":25,"source":26,"license":15},"L3","cursor\u002Fplugins@1e5c90a:pstack\u002Fskills\u002Freflect\u002FSKILL.md","main","e57e3dd5c8aec0fe40658397aee9fd9b1d77bb60","plugins\u002Fven\u002Fskills\u002Freflect","https:\u002F\u002Fgithub.com\u002FVentorius\u002Fven-stack","https:\u002F\u002Fgithub.com\u002FVentorius","Heavy testing believer. Workflow automation fan. Fullstack JS developer.","2026-11-04 04:05:46",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add Ventorius\u002Fven-stack --skill reflect",{"tool":40,"command":41},"bunx","bunx skills add Ventorius\u002Fven-stack --skill reflect",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Ventorius\u002Fven-stack --skill reflect","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVentorius\u002Fven-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fven\u002Fskills\u002Freflect\u002FSKILL.md",true,[48],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Flenses.md","REFERENCE","参考文档",2561,"https:\u002F\u002Fgithub.com\u002FVentorius\u002Fven-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fven\u002Fskills\u002Freflect\u002Freferences\u002Flenses.md",[55,62,69,76,83,90],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7ES1P06ZPAGTT7YS4V6MS32","yeet","Take every local change green through the repo's own checks, slice it into conventional commits, push, and with --pr open a pull request on the code host. Use only when the user explicitly asks to yeet, or to commit and push everything; never on your own initiative.","https:\u002F\u002Fgithub.com\u002FVentorius\u002Fven-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fven\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"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":19},"01M7ES1JHVQEN3YYMRZEBM2E79","write-docs","Write or update documentation from the code: gather facts, pick the shape for the reader, write it plain, and prove every command and path in it. Use when asked to document a repo, module or feature, or to bring stale docs up to date.","https:\u002F\u002Fgithub.com\u002FVentorius\u002Fven-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fven\u002Fskills\u002Fwrite-docs\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":19},"01M7ES1DD3YVMF1MY7D51R6516","why","Find why code is shaped the way it is (design rationale, trade-offs, regressions, odd thresholds) from history, tickets, docs and chat, citing every claim and stating its confidence. Use for 'why does X work this way', 'why did we pick Y', or before changing code whose purpose is unclear.","https:\u002F\u002Fgithub.com\u002FVentorius\u002Fven-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fven\u002Fskills\u002Fwhy\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":19},"01M7ES18XVRZGQ0V1BBZH63Q8W","verify","Prove a change works with the check that matches its type, do the read-back, and log the pass against the exact tree. Use when a change is ready to call done, before review, commit or stopping, and whenever ven-decisions end refuses an unverified tree.","https:\u002F\u002Fgithub.com\u002FVentorius\u002Fven-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fven\u002Fskills\u002Fverify\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":19},"01M7ES15Z3W8QTJH4CRAJ53D2G","unslop","Cut AI writing tells (filler, model vocabulary, metaphor nouns, hedging, formatting tics) from text while keeping every fact. Use when editing or checking any prose before it ships: docs, PR bodies, reports, skill text.","https:\u002F\u002Fgithub.com\u002FVentorius\u002Fven-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fven\u002Fskills\u002Funslop\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":19},"01M7ES12GT9WD9NE2X3M1B29ZZ","type-discipline","Apply when designing types or data shapes, reviewing a signature, or handling outside data, in any language. Make wrong states fail early: in the compiler for typed languages, in validated runtime contracts for untyped ones.","https:\u002F\u002Fgithub.com\u002FVentorius\u002Fven-stack\u002Fblob\u002Fmain\u002Fplugins\u002Fven\u002Fskills\u002Ftype-discipline\u002FSKILL.md",[],[]]