{"id":"03d0f8f3-236d-4560-8bc8-9909f9c11a52","shortId":"qYJkYz","kind":"skill","title":"fixflow","tagline":"Execute coding tasks with a strict delivery workflow: build a full plan, implement one step at a time, run tests continuously, and commit by default after each step (`per_step`). Support explicit commit policy overrides (`final_only`, `milestone`) and optional BDD (Given/When/The","description":"# Fixflow\n\n## Overview\n\nUse this skill to deliver end-to-end engineering work in one run:\n- Plan fully.\n- Execute in strict sequence.\n- Validate continuously.\n- Use explicit commit policy (`per_step` default; `final_only`/`milestone` when requested).\n- Add BDD behavior specs when requested or when requirements are ambiguous.\n\n## Trigger Cues\n\nTrigger this skill when the user asks for one or more of:\n- Full plan + sequential execution.\n- No backward compatibility.\n- Test everything before handoff.\n- Commit after completion or commit before each next step.\n- Behavior-driven delivery (BDD) or acceptance scenarios.\n\n## Workflow\n\n### 1. Define Ready Criteria (DoR)\n\n> See shared delivery base: [`references/delivery-base.md`](./references/delivery-base.md)\n\n### 2. Build Complete Plan Before Editing\n\n> See shared delivery base: [`references/delivery-base.md`](./references/delivery-base.md)\n\n### 3. Add BDD/TDD Layer When Needed\n\nUse BDD if user requests it, or if requirements are unclear.\n\n#### 3.0 TDD Mode (RED -> GREEN -> IMPROVE)\n\nWhen user requests TDD or test-driven delivery:\n\n1. **RED** — Write a failing test first\n   - Extract testable behavior from requirements\n   - Write minimal test case asserting expected behavior\n   - Run test, confirm it fails (red)\n   - If test passes unexpectedly -> requirement already met or test is wrong\n\n2. **GREEN** — Write minimal implementation\n   - Write just enough code to make the test pass\n   - No extra improvements, no \"while I'm here\" changes\n   - Run test, confirm it passes (green)\n\n3. **IMPROVE** — Refactor under green tests\n   - Eliminate duplication, improve naming, simplify logic\n   - Run tests after each refactor to confirm no regression\n   - Refactoring must not change external behavior\n\nCoverage target: 80% line coverage for new code, 100% for critical paths.\n\nTrigger cues for TDD mode:\n- User says \"TDD\", \"test-driven\", \"test first\"\n- User says \"write tests before code\"\n- Requirements are well-defined with clear inputs/outputs\n\nFor BDD Lite, Scenario Quality Checklist, Scenario Outline, and Test Layer mapping, see the shared reference:\n\n> [`references/bdd-guide.md`](./references/bdd-guide.md)\n\n\n### 4. Execute Step by Step\n\n> See shared delivery base: [`references/delivery-base.md`](./references/delivery-base.md)\n\nFor `per_step` (default):\n  - Stage only files for current step.\n  - Run step-level checks.\n  - Commit immediately after step checks pass.\n  - Record step -> commit hash mapping.\n\n### 5. Apply No-Backward-Compatibility Mode (When Requested)\n\n> See shared delivery base: [`references/delivery-base.md`](./references/delivery-base.md)\n\n### 6. Validate with Test Matrix (Verification Loop)\n\n> See shared delivery base: [`references/delivery-base.md`](./references/delivery-base.md)\n\n### 7. Commit and Handoff\n\n> See shared delivery base: [`references/delivery-base.md`](./references/delivery-base.md)\n\n## Guardrails\n\n- Do not stop at planning when implementation is expected.\n- Do not leave partially completed plan steps.\n- Do not defer required testing when it can be run now.\n- Do not default to `final_only`; use `per_step` unless user explicitly asks otherwise.\n- Do not move to the next plan step before committing when `commit_policy = per_step`.\n- Do not claim compatibility if user explicitly requested no compatibility work.\n- Do not include unrelated pre-existing dirty files in commits.\n- Do not hand off without concrete validation evidence.","tags":["fixflow","claude","arsenal","majiayu000","agent-skills","ai-agents","ai-coding-assistant","automation","claude-code","code-review","developer-tools","devops"],"capabilities":["skill","source-majiayu000","skill-fixflow","topic-agent-skills","topic-ai-agents","topic-ai-coding-assistant","topic-automation","topic-claude","topic-claude-code","topic-code-review","topic-developer-tools","topic-devops","topic-productivity","topic-prompt-engineering","topic-python"],"categories":["claude-arsenal"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/majiayu000/claude-arsenal/fixflow","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add majiayu000/claude-arsenal","source_repo":"https://github.com/majiayu000/claude-arsenal","install_from":"skills.sh"}},"qualityScore":"0.464","qualityRationale":"deterministic score 0.46 from registry signals: · indexed on github topic:agent-skills · 29 github stars · SKILL.md body (3,447 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-01T07:01:13.833Z","embedding":null,"createdAt":"2026-04-18T22:24:09.470Z","updatedAt":"2026-05-01T07:01:13.833Z","lastSeenAt":"2026-05-01T07:01:13.833Z","tsv":"'/references/bdd-guide.md':337 '/references/delivery-base.md':144,156,348,389,402,412 '1':134,189 '100':289 '2':145,225 '3':157,254 '3.0':174 '4':338 '5':375 '6':390 '7':403 '80':283 'accept':131 'add':80,158 'alreadi':219 'ambigu':90 'appli':376 'ask':99,453 'assert':205 'backward':110,379 'base':142,154,346,387,400,410 'bdd':42,81,129,164,321 'bdd/tdd':159 'behavior':82,126,198,207,280 'behavior-driven':125 'build':10,146 'case':204 'chang':247,278 'check':363,368 'checklist':325 'claim':472 'clear':318 'code':3,233,288,311 'commit':24,34,70,116,120,364,372,404,464,466,491 'compat':111,380,473,479 'complet':118,147,427 'concret':497 'confirm':210,250,272 'continu':22,67 'coverag':281,285 'criteria':137 'critic':291 'cue':92,294 'current':357 'default':26,74,352,443 'defer':432 'defin':135,316 'deliv':50 'deliveri':8,128,141,153,188,345,386,399,409 'dirti':488 'dor':138 'driven':127,187,303 'duplic':261 'edit':150 'elimin':260 'end':52,54 'end-to-end':51 'engin':55 'enough':232 'everyth':113 'evid':499 'execut':2,62,108,339 'exist':487 'expect':206,422 'explicit':33,69,452,476 'extern':279 'extra':240 'extract':196 'fail':193,212 'file':355,489 'final':37,75,445 'first':195,305 'fixflow':1,44 'full':12,105 'fulli':61 'given/when/the':43 'green':178,226,253,258 'guardrail':413 'hand':494 'handoff':115,406 'hash':373 'immedi':365 'implement':14,229,420 'improv':179,241,255,262 'includ':483 'inputs/outputs':319 'layer':160,330 'leav':425 'level':362 'line':284 'lite':322 'logic':265 'loop':396 'm':245 'make':235 'map':331,374 'matrix':394 'met':220 'mileston':39,77 'minim':202,228 'mode':176,297,381 'move':457 'must':276 'name':263 'need':162 'new':287 'next':123,460 'no-backward-compat':377 'one':15,58,101 'option':41 'otherwis':454 'outlin':327 'overrid':36 'overview':45 'partial':426 'pass':216,238,252,369 'path':292 'per':30,72,350,448,468 'plan':13,60,106,148,418,428,461 'polici':35,71,467 'pre':486 'pre-exist':485 'qualiti':324 'readi':136 'record':370 'red':177,190,213 'refactor':256,270,275 'refer':335 'references/bdd-guide.md':336 'references/delivery-base.md':143,155,347,388,401,411 'regress':274 'request':79,85,167,182,383,477 'requir':88,171,200,218,312,433 'run':20,59,208,248,266,359,439 'say':299,307 'scenario':132,323,326 'see':139,151,332,343,384,397,407 'sequenc':65 'sequenti':107 'share':140,152,334,344,385,398,408 'simplifi':264 'skill':48,95 'skill-fixflow' 'source-majiayu000' 'spec':83 'stage':353 'step':16,29,31,73,124,340,342,351,358,361,367,371,429,449,462,469 'step-level':360 'stop':416 'strict':7,64 'support':32 'target':282 'task':4 'tdd':175,183,296,300 'test':21,112,186,194,203,209,215,222,237,249,259,267,302,304,309,329,393,434 'test-driven':185,301 'testabl':197 'time':19 'topic-agent-skills' 'topic-ai-agents' 'topic-ai-coding-assistant' 'topic-automation' 'topic-claude' 'topic-claude-code' 'topic-code-review' 'topic-developer-tools' 'topic-devops' 'topic-productivity' 'topic-prompt-engineering' 'topic-python' 'trigger':91,93,293 'unclear':173 'unexpect':217 'unless':450 'unrel':484 'use':46,68,163,447 'user':98,166,181,298,306,451,475 'valid':66,391,498 'verif':395 'well':315 'well-defin':314 'without':496 'work':56,480 'workflow':9,133 'write':191,201,227,230,308 'wrong':224","prices":[{"id":"3f739624-46ec-46ae-90cd-a24ac5dbfc3d","listingId":"03d0f8f3-236d-4560-8bc8-9909f9c11a52","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"majiayu000","category":"claude-arsenal","install_from":"skills.sh"},"createdAt":"2026-04-18T22:24:09.470Z"}],"sources":[{"listingId":"03d0f8f3-236d-4560-8bc8-9909f9c11a52","source":"github","sourceId":"majiayu000/claude-arsenal/fixflow","sourceUrl":"https://github.com/majiayu000/claude-arsenal/tree/main/skills/fixflow","isPrimary":false,"firstSeenAt":"2026-04-18T22:24:09.470Z","lastSeenAt":"2026-05-01T07:01:13.833Z"}],"details":{"listingId":"03d0f8f3-236d-4560-8bc8-9909f9c11a52","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"majiayu000","slug":"fixflow","github":{"repo":"majiayu000/claude-arsenal","stars":29,"topics":["agent-skills","ai-agents","ai-coding-assistant","automation","claude","claude-code","code-review","developer-tools","devops","productivity","prompt-engineering","python","software-development","typescript","workflows"],"license":"mit","html_url":"https://github.com/majiayu000/claude-arsenal","pushed_at":"2026-04-29T04:12:22Z","description":"52 production-ready Claude Code skills and 7 specialized agents for software development, DevOps, product workflows, and automation.","skill_md_sha":"86d66c76df279167a69d8dff58dff479546f304f","skill_md_path":"skills/fixflow/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/majiayu000/claude-arsenal/tree/main/skills/fixflow"},"layout":"multi","source":"github","category":"claude-arsenal","frontmatter":{"name":"fixflow","description":"Execute coding tasks with a strict delivery workflow: build a full plan, implement one step at a time, run tests continuously, and commit by default after each step (`per_step`). Support explicit commit policy overrides (`final_only`, `milestone`) and optional BDD (Given/When/Then) when users ask for behavior-driven delivery or requirements are unclear."},"skills_sh_url":"https://skills.sh/majiayu000/claude-arsenal/fixflow"},"updatedAt":"2026-05-01T07:01:13.833Z"}}