[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72TSD53VT09VF3EG67KA68E":3,"skill-same:01M72TSD53VT09VF3EG67KA68E":44},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M72TSD53VT09VF3EG67KA68E","ws-tdd-green",null,"Phase 4 -- write minimal production code to make failing tests pass.","vempio\u002FWhittleSpec","vempio","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F226084226?v=4","01M72TQW11B57V5ZE8MQPKJ5QY","01M72TQW22F5C4SJ317ETCWHFW",4,"MIT","https:\u002F\u002Fgithub.com\u002Fvempio\u002FWhittleSpec\u002Fblob\u002Fmain\u002Fskills\u002Fws.tdd.green\u002FSKILL.md",[],[],"2026-11-10 22:39:42",false,"---\nname: ws-tdd-green\ndescription: Phase 4 -- write minimal production code to make failing tests pass.\n---\n# ws.tdd.green\n\nLoad shared context: `ws.tdd._meta\u002FSKILL.md` — the sibling skill in the same skills directory this skill loaded from (resolves under any clone name, install location, or skills-root override). Also read `ws.tdd._meta\u002Fbdd-workflow.md`.\n\n## Purpose\n\nTransition from test design to production code. Heavy lifting (discovering what to test, designing assertions, validating depth) done in Phases 1-3. This phase writes simplest code making tests pass.\n\nInteraction signal: tells LLM test design is complete and production code may be written. Without explicit transition, LLM blurs test writing and production coding, undermining review gates.\n\n## Prerequisites\n\n- Failing tests from `\u002Fws.tdd.red` (Phase 3), confirmed failing for right reasons\n\n## Process\n\n### 1. Write Minimal Code\n\nImplement production code making failing tests pass. Minimal = enough to pass, no more \u002F no speculative features \u002F no premature abstractions.\n\n### 2. Run Full Suite\n\nRun **entire** test suite, not just new tests. All new tests must pass \u002F all previous tests must still pass \u002F previously passing test now fails = **stop and investigate** (regression, not acceptable side effect).\n\n### 3. BDD Verification Checkpoint\n\nRun BDD suite for feature's tags after unit tests green. **Not optional** when BDD scenarios exist or are expected. Report: \"BDD outer loop: X of Y scenarios pass. Z still `@todo`.\"\n\n- All pass: double loop complete for batch. Note in gate report.\n- Still fail: identify which steps need more production code. Feeds next TDD inner loop.\n- **Still `@todo`** (never got step definitions): flag: \"WARNING: N scenarios still stubs. Route to `\u002Fws.bdd.outline` -> `\u002Fws.bdd.red` before declaring complete.\"\n- No BDD scenarios exist\u002Fexpected: skip, state why.\n\n**Early wiring check** (critical for multi-component tasks): BDD scenarios fail at entry point level (\"unknown subcommand,\" \"function not found\")? Wire component into entry point now -- typically few lines of glue. Scenario stuck at \"subcommand not found\" for entire build = zero integration feedback. Scenario advancing to next failure tells you what to build next. **Do not defer wiring to end.**\n\n### 4. Documentation Update\n\nIf green cycle changed operator-visible behavior (new subcommand\u002Fflags, changed output, new errors), update `docs\u002F\u003Cworkflow>.md` in same cycle. Documentation = deliverable alongside code, not afterthought.\n\n- **New subcommand\u002Fflag**: Quick Reference + Subcommands sections\n- **New error**: Error Catalog with exact message and fix\n- **Changed workflow**: Typical Operator Workflow\n- **New config\u002Fenv var**: Configuration section\n\nNo docs file yet and task spec names one: create from `workflow-doc.md` template in `ws._meta`. Skip for internal plumbing with no operator-visible effect.\n\n### 5. Refactor (if needed)\n\nRefactor while keeping tests green \u002F run suite after each step \u002F breaks test = revert and reconsider \u002F consult user first.\n\n## Anti-Patterns\n\n- **Gold plating**: behavior beyond what tests require\n- **Untested additions**: production code no test exercises\n- **\"While I'm here\"**: fixing\u002Frefactoring unrelated code\n- **Skipping full suite**: running only new tests misses regressions\n- **Deferring docs**: \"I'll write docs later\" = docs won't exist\n- **Building without wiring**: primitive + tests complete, production never calls the primitive. Dominant failure mode -- not a defensible scope boundary. \"The wiring is out of scope \u002F a follow-up task\" is this pattern renamed. If the primitive's purpose is to serve production, wiring is part of the same cycle.\n- **Spec drift out of the green cycle**: new behavior landed in code, `requirements.md` \u002F `umbrella-requirements.md` silent. Treating spec-sync as a later sweep concern rather than a green-phase deliverable is how concurrency protocols, locking behaviors, and contract changes go spec-dark.\n\n## Gate\n\nPresent passing suite with **mandatory checklist**. Every item needs visible evidence (command output, grep result, explicit statement) -- not \"I checked.\"\n\n```\nPOST-GREEN CHECKLIST:\n1. Production wiring: [for each new primitive \u002F method \u002F Protocol \u002F type \u002F\n   config knob introduced, grep production code (NOT tests) for call sites\n   or type-annotated uses. Zero hits = DEAD CODE, task not complete.\n   \"Will be wired later \u002F out of scope\" does NOT satisfy this -- building\n   without wiring is the dominant failure mode, not a scope boundary.]\n   New element: \u003Cname> -> Wired at: \u003Cfile:line> (or DEAD CODE -- STOP)\n2. Test honesty: Did any new test pass immediately (never red)?\n   [yes\u002Fno -- if yes, list which; backfill or genuine?]\n3. BDD status: [N active, M @todo, K green out of total]\n   \"Can't run\" requires verified evidence, not assumption.\n4. Regressions: [N existing tests pass, 0 failures]\n5. Documentation: [no operator-visible changes \u002F updated \u003Cfile>]\n6. Spec sync: [for each new user-visible behavior or protocol this cycle\n   introduced, name the requirements.md \u002F umbrella-requirements.md AC\n   covering it with line number. No spec for this work: state \"no spec\"\n   and why. Spec exists but lacks coverage for the new behavior: STOP --\n   update spec before declaring green. Spec-sync is a green-phase\n   deliverable, not a later-sweep rescue.]\n```\n\n**If any item cannot be completed honestly, say so.** \"I didn't check\" beats fabricated answer. Checklist exists because LLM has bias toward declaring green prematurely -- particularly on items 1 (wiring) and 6 (spec sync).\n\nWait for confirmation before proceeding.\n\n## Completion\n\nAll tests pass and human confirms -> follow batch processing flow (see `ws.tdd._meta`):\n\n1. **More outlines waiting?** Return to `\u002Fws.tdd.red` for the next red batch.\n2. **Outlines exhausted, ideas waiting?** Return to `\u002Fws.tdd.outline` for the next outline batch.\n3. **Unit ideas exhausted, BDD still red?** Continue TDD inner loop -- derive unit test ideas from failing BDD steps.\n4. **Both exhausted \u002F green?** TDD cycle complete. Via `\u002Fws.4-run`: return to ws.4-run flow. Standalone: stop or `\u002Fws.tdd.idea` if new needs emerged.\n","# ws.tdd.green\n\nLoad shared context: `ws.tdd._meta\u002FSKILL.md` — the sibling skill in the same skills directory this skill loaded from (resolves under any clone name, install location, or skills-root override). Also read `ws.tdd._meta\u002Fbdd-workflow.md`.\n\n## Purpose\n\nTransition from test design to production code. Heavy lifting (discovering what to test, designing assertions, validating depth) done in Phases 1-3. This phase writes simplest code making tests pass.\n\nInteraction signal: tells LLM test design is complete and production code may be written. Without explicit transition, LLM blurs test writing and production coding, undermining review gates.\n\n## Prerequisites\n\n- Failing tests from `\u002Fws.tdd.red` (Phase 3), confirmed failing for right reasons\n\n## Process\n\n### 1. Write Minimal Code\n\nImplement production code making failing tests pass. Minimal = enough to pass, no more \u002F no speculative features \u002F no premature abstractions.\n\n### 2. Run Full Suite\n\nRun **entire** test suite, not just new tests. All new tests must pass \u002F all previous tests must still pass \u002F previously passing test now fails = **stop and investigate** (regression, not acceptable side effect).\n\n### 3. BDD Verification Checkpoint\n\nRun BDD suite for feature's tags after unit tests green. **Not optional** when BDD scenarios exist or are expected. Report: \"BDD outer loop: X of Y scenarios pass. Z still `@todo`.\"\n\n- All pass: double loop complete for batch. Note in gate report.\n- Still fail: identify which steps need more production code. Feeds next TDD inner loop.\n- **Still `@todo`** (never got step definitions): flag: \"WARNING: N scenarios still stubs. Route to `\u002Fws.bdd.outline` -> `\u002Fws.bdd.red` before declaring complete.\"\n- No BDD scenarios exist\u002Fexpected: skip, state why.\n\n**Early wiring check** (critical for multi-component tasks): BDD scenarios fail at entry point level (\"unknown subcommand,\" \"function not found\")? Wire component into entry point now -- typically few lines of glue. Scenario stuck at \"subcommand not found\" for entire build = zero integration feedback. Scenario advancing to next failure tells you what to build next. **Do not defer wiring to end.**\n\n### 4. Documentation Update\n\nIf green cycle changed operator-visible behavior (new subcommand\u002Fflags, changed output, new errors), update `docs\u002F\u003Cworkflow>.md` in same cycle. Documentation = deliverable alongside code, not afterthought.\n\n- **New subcommand\u002Fflag**: Quick Reference + Subcommands sections\n- **New error**: Error Catalog with exact message and fix\n- **Changed workflow**: Typical Operator Workflow\n- **New config\u002Fenv var**: Configuration section\n\nNo docs file yet and task spec names one: create from `workflow-doc.md` template in `ws._meta`. Skip for internal plumbing with no operator-visible effect.\n\n### 5. Refactor (if needed)\n\nRefactor while keeping tests green \u002F run suite after each step \u002F breaks test = revert and reconsider \u002F consult user first.\n\n## Anti-Patterns\n\n- **Gold plating**: behavior beyond what tests require\n- **Untested additions**: production code no test exercises\n- **\"While I'm here\"**: fixing\u002Frefactoring unrelated code\n- **Skipping full suite**: running only new tests misses regressions\n- **Deferring docs**: \"I'll write docs later\" = docs won't exist\n- **Building without wiring**: primitive + tests complete, production never calls the primitive. Dominant failure mode -- not a defensible scope boundary. \"The wiring is out of scope \u002F a follow-up task\" is this pattern renamed. If the primitive's purpose is to serve production, wiring is part of the same cycle.\n- **Spec drift out of the green cycle**: new behavior landed in code, `requirements.md` \u002F `umbrella-requirements.md` silent. Treating spec-sync as a later sweep concern rather than a green-phase deliverable is how concurrency protocols, locking behaviors, and contract changes go spec-dark.\n\n## Gate\n\nPresent passing suite with **mandatory checklist**. Every item needs visible evidence (command output, grep result, explicit statement) -- not \"I checked.\"\n\n```\nPOST-GREEN CHECKLIST:\n1. Production wiring: [for each new primitive \u002F method \u002F Protocol \u002F type \u002F\n   config knob introduced, grep production code (NOT tests) for call sites\n   or type-annotated uses. Zero hits = DEAD CODE, task not complete.\n   \"Will be wired later \u002F out of scope\" does NOT satisfy this -- building\n   without wiring is the dominant failure mode, not a scope boundary.]\n   New element: \u003Cname> -> Wired at: \u003Cfile:line> (or DEAD CODE -- STOP)\n2. Test honesty: Did any new test pass immediately (never red)?\n   [yes\u002Fno -- if yes, list which; backfill or genuine?]\n3. BDD status: [N active, M @todo, K green out of total]\n   \"Can't run\" requires verified evidence, not assumption.\n4. Regressions: [N existing tests pass, 0 failures]\n5. Documentation: [no operator-visible changes \u002F updated \u003Cfile>]\n6. Spec sync: [for each new user-visible behavior or protocol this cycle\n   introduced, name the requirements.md \u002F umbrella-requirements.md AC\n   covering it with line number. No spec for this work: state \"no spec\"\n   and why. Spec exists but lacks coverage for the new behavior: STOP --\n   update spec before declaring green. Spec-sync is a green-phase\n   deliverable, not a later-sweep rescue.]\n```\n\n**If any item cannot be completed honestly, say so.** \"I didn't check\" beats fabricated answer. Checklist exists because LLM has bias toward declaring green prematurely -- particularly on items 1 (wiring) and 6 (spec sync).\n\nWait for confirmation before proceeding.\n\n## Completion\n\nAll tests pass and human confirms -> follow batch processing flow (see `ws.tdd._meta`):\n\n1. **More outlines waiting?** Return to `\u002Fws.tdd.red` for the next red batch.\n2. **Outlines exhausted, ideas waiting?** Return to `\u002Fws.tdd.outline` for the next outline batch.\n3. **Unit ideas exhausted, BDD still red?** Continue TDD inner loop -- derive unit test ideas from failing BDD steps.\n4. **Both exhausted \u002F green?** TDD cycle complete. Via `\u002Fws.4-run`: return to ws.4-run flow. Standalone: stop or `\u002Fws.tdd.idea` if new needs emerged.\n",{"name":5,"description":7},"main","1ad262fc695612ff484ee364ff66ab5298bdda58","skills\u002Fws.tdd.green",0,"https:\u002F\u002Fgithub.com\u002Fvempio\u002FWhittleSpec","https:\u002F\u002Fgithub.com\u002Fvempio","2026-10-06 16:08:48",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add vempio\u002FWhittleSpec --skill ws-tdd-green",{"tool":36,"command":37},"bunx","bunx skills add vempio\u002FWhittleSpec --skill ws-tdd-green",{"tool":39,"command":40},"pnpm","pnpm dlx skills add vempio\u002FWhittleSpec --skill ws-tdd-green","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fvempio\u002FWhittleSpec\u002Fblob\u002Fmain\u002Fskills\u002Fws.tdd.green\u002FSKILL.md",true,[],[45,52,59,66,73,80],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":18},"01M72TSQYBBJ3FG1MSMB9B33SZ","ws-tdd-review","Audit existing test code for quality, depth, and adherence to TDD principles.","https:\u002F\u002Fgithub.com\u002Fvempio\u002FWhittleSpec\u002Fblob\u002Fmain\u002Fskills\u002Fws.tdd.review\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M72TSN33MN2J0CW29MBY4WC4","ws-tdd-red","Phase 3 -- implement failing tests, validating assertion quality and depth.","https:\u002F\u002Fgithub.com\u002Fvempio\u002FWhittleSpec\u002Fblob\u002Fmain\u002Fskills\u002Fws.tdd.red\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M72TSJMTHFVC8FW2BGQ0NYD7","ws-tdd-outline","Phase 2 -- tree-level test design, examining intent and approach per test.","https:\u002F\u002Fgithub.com\u002Fvempio\u002FWhittleSpec\u002Fblob\u002Fmain\u002Fskills\u002Fws.tdd.outline\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M72TSFPHD749CY9KRV66T0RH","ws-tdd-idea","Phase 1 -- forest-level test case discovery, mapping the full problem space.","https:\u002F\u002Fgithub.com\u002Fvempio\u002FWhittleSpec\u002Fblob\u002Fmain\u002Fskills\u002Fws.tdd.idea\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M72TS9TXQ9RHYF3VBGR87BF6","ws-tdd-meta","TDD shared context -- phased protocol, quality standards, and standing instructions for all TDD skills.","https:\u002F\u002Fgithub.com\u002Fvempio\u002FWhittleSpec\u002Fblob\u002Fmain\u002Fskills\u002Fws.tdd._meta\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M72TS76RJ3K1HNGQXJ2S09HT","ws-sweep","Completeness sweep -- exhaustively verify nothing was missed after a change.","https:\u002F\u002Fgithub.com\u002Fvempio\u002FWhittleSpec\u002Fblob\u002Fmain\u002Fskills\u002Fws.sweep\u002FSKILL.md",[],[]]