{"id":"3ef360c2-372a-41ca-92b0-11c2bc33ceab","shortId":"mVkTmG","kind":"skill","title":"optflow","tagline":"Discover and deliver repository optimization work end to end: identify performance/reliability/maintainability/security/dx/cost optimization points, prioritize by impact-effort-risk, then execute fixes step by step with continuous testing and explicit commit policy (`final_only`,","description":"# Optflow\n\n## Overview\n\nUse this skill to discover repository optimization opportunities and execute selected optimizations end to end:\n- Discover optimization points first (performance, reliability, maintainability, security, cost, DX).\n- Prioritize by impact/effort/risk.\n- Execute in strict sequence with validation and explicit commit policy.\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- Ask to find optimization opportunities in a repository/library.\n- Ask for optimization roadmap + implementation.\n- Require test-first optimization delivery and commit (final or per step).\n- Require behavior-driven delivery (BDD) or acceptance scenarios.\n\n## Workflow\n\n### 0. Discover Optimization Backlog\n\n- Scan the repository before planning changes.\n- Classify findings into: performance, reliability, maintainability, security, developer experience, and cost.\n- For each finding, record:\n  - symptom and evidence (file/path/metric)\n  - expected impact\n  - effort estimate\n  - risk level\n- Build a prioritized backlog using impact/effort/risk.\n- Explicitly mark low-confidence findings as hypotheses.\n\n### 1. Define Ready Criteria (DoR)\n\n> See shared delivery base: [`references/delivery-base.md`](./references/delivery-base.md)\n\nAdditional for optflow:\n- If implementation is requested and commit style is not explicitly specified, use `per_step` (default).\n- If user says \"per step optimize and test then commit\", use `per_step`.\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 Layer When Needed\n\nUse BDD if user requests it, or if requirements are unclear.\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\n- Treat one planned step as one feature boundary whenever possible.\n- If `commit_policy = per_step` (default for implementation):\n  - Stage only files for current step/feature.\n  - Run step-level checks first.\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\n\n> See shared delivery base: [`references/delivery-base.md`](./references/delivery-base.md)\n\nPer-step mandatory loop (when `commit_policy = per_step`):\n1. Implement current feature step.\n2. Run mapped step checks (at least one automated command).\n3. If checks pass, commit this step immediately.\n4. Move to next feature step.\n\n### 7. Commit and Handoff\n\n> See shared delivery base: [`references/delivery-base.md`](./references/delivery-base.md)\n\n- `per_step`: each step must already be committed before next step starts.\n\n## Output Templates\n\n### Optimization Backlog Template\n\n```text\nFinding:\nCategory: <performance|reliability|maintainability|security|dx|cost>\nEvidence: <file/metric/log>\nImpact: <high|medium|low>\nEffort: <high|medium|low>\nRisk: <high|medium|low>\nPriority score: <...>\nDecision: <implement now|defer>\n```\n\n### Optimization Plan Template\n\n```text\nSelected Findings:\n1. <finding>\n2. <finding>\n\nExecution Steps:\n1. <step> (done condition: <...>)\n2. <step> (done condition: <...>)\n\nExpected Gains:\n- <metric or qualitative gain>\n```\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 move to the next plan step before committing when `commit_policy = per_step`.\n- Do not merge multiple completed feature steps into one commit 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":["optflow","claude","arsenal","majiayu000","agent-skills","ai-agents","ai-coding-assistant","automation","claude-code","code-review","developer-tools","devops"],"capabilities":["skill","source-majiayu000","skill-optflow","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/optflow","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 (4,156 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":"2026-05-01T07:01:14.986Z","embedding":null,"createdAt":"2026-04-18T22:24:17.489Z","updatedAt":"2026-05-01T07:01:14.986Z","lastSeenAt":"2026-05-01T07:01:14.986Z","tsv":"'/references/bdd-guide.md':273 '/references/delivery-base.md':195,238,284,340,351,400 '0':136 '1':185,362,453,457 '2':227,367,454,460 '3':239,377 '4':274,385 '5':326 '6':341 '7':391 'accept':133 'add':76,240 'addit':196 'alreadi':406 'ambigu':86 'appli':327 'ask':95,101,109 'autom':375 'backlog':139,174,416 'backward':330 'base':193,236,282,338,349,398 'bdd':77,131,241,246,257 'behavior':78,128 'behavior-driven':127 'boundari':292 'build':171,228 'categori':420 'chang':145 'check':313,319,371,379 'checklist':261 'claim':525 'classifi':146 'command':376 'commit':32,74,121,204,223,296,315,323,358,381,392,408,502,504,517,519,544 'compat':331,526,532 'complet':229,479,512 'concret':550 'condit':459,462 'confid':181 'continu':28 'cost':61,156,426 'criteria':188 'cue':88 'current':307,364 'decis':443 'default':213,300 'defer':446,484 'defin':186 'deliv':4 'deliveri':119,130,192,235,281,337,348,397 'develop':153 'dirti':541 'discov':2,42,53,137 'done':458,461 'dor':189 'driven':129 'dx':62,425 'edit':232 'effort':19,167,433 'end':8,10,50,52 'estim':168 'evid':163,427,552 'execut':22,47,66,275,455 'exist':540 'expect':165,463,474 'experi':154 'explicit':31,73,177,208,529 'featur':291,365,389,513 'file':305,542 'file/metric/log':428 'file/path/metric':164 'final':34,122 'find':103,147,159,182,419,452 'first':56,117,314 'fix':23 'gain':464 'guardrail':465 'hand':547 'handoff':394 'hash':324 'high':430,434,438 'hypothes':184 'identifi':11 'immedi':316,384 'impact':18,166,429 'impact-effort-risk':17 'impact/effort/risk':65,176 'implement':113,200,302,363,444,472 'includ':536 'layer':242,266 'least':373 'leav':477 'level':170,312 'lite':258 'loop':356 'low':180,432,436,440 'low-confid':179 'maintain':59,151,423 'mandatori':355 'map':267,325,369 'mark':178 'matrix':345 'medium':431,435,439 'merg':510 'mode':332 'move':386,495 'multipl':511 'must':405 'need':244 'next':388,410,498 'no-backward-compat':328 'one':97,286,290,374,516 'opportun':45,105 'optflow':1,36,198 'optim':6,13,44,49,54,104,111,118,138,219,415,447 'outlin':263 'output':413 'overview':37 'partial':478 'pass':320,380 'per':124,211,217,225,298,353,360,401,506,521 'per-step':352 'perform':57,149,421 'performance/reliability/maintainability/security/dx/cost':12 'plan':144,230,287,448,470,480,499 'point':14,55 'polici':33,75,297,359,505,520 'possibl':294 'pre':539 'pre-exist':538 'priorit':15,63,173 'prioriti':441 'qualiti':260 'readi':187 'record':160,321 'refer':271 'references/bdd-guide.md':272 'references/delivery-base.md':194,237,283,339,350,399 'reliabl':58,150,422 'repositori':5,43,142 'repository/library':108 'request':81,202,249,334,530 'requir':84,114,126,253,485 'risk':20,169,437 'roadmap':112 'run':309,368,491 'say':216 'scan':140 'scenario':134,259,262 'score':442 'secur':60,152,424 'see':190,233,268,279,335,346,395 'select':48,451 'sequenc':69 'share':191,234,270,280,336,347,396 'skill':40,91 'skill-optflow' 'source-majiayu000' 'spec':79 'specifi':209 'stage':303 'start':412 'step':24,26,125,212,218,226,276,278,288,299,311,318,322,354,361,366,370,383,390,402,404,411,456,481,500,507,514,522 'step-level':310 'step/feature':308 'stop':468 'strict':68 'style':205 'symptom':161 'templat':414,417,449 'test':29,116,221,265,344,486 'test-first':115 'text':418,450 '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' 'treat':285 'trigger':87,89 'unclear':255 'unrel':537 'use':38,175,210,224,245 'user':94,215,248,528 'valid':71,342,551 'whenev':293 'without':549 'work':7,533 'workflow':135","prices":[{"id":"0f6cb584-557a-43f3-8ee5-003cf14b4f33","listingId":"3ef360c2-372a-41ca-92b0-11c2bc33ceab","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":"2026-04-18T22:24:17.489Z"}],"sources":[{"listingId":"3ef360c2-372a-41ca-92b0-11c2bc33ceab","source":"github","sourceId":"majiayu000/claude-arsenal/optflow","sourceUrl":"https://github.com/majiayu000/claude-arsenal/tree/main/skills/optflow","isPrimary":false,"firstSeenAt":"2026-04-18T22:24:17.489Z","lastSeenAt":"2026-05-01T07:01:14.986Z"}],"details":{"listingId":"3ef360c2-372a-41ca-92b0-11c2bc33ceab","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"majiayu000","slug":"optflow","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":"53118f3fdc671f6cbf19ddbf1081e1ac06b280f4","skill_md_path":"skills/optflow/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/majiayu000/claude-arsenal/tree/main/skills/optflow"},"layout":"multi","source":"github","category":"claude-arsenal","frontmatter":{"name":"optflow","description":"Discover and deliver repository optimization work end to end: identify performance/reliability/maintainability/security/dx/cost optimization points, prioritize by impact-effort-risk, then execute fixes step by step with continuous testing and explicit commit policy (`final_only`, `per_step`, `milestone`). Default to `per_step` for implementation work so each feature is tested then committed before the next feature. Supports optional BDD (Given/When/Then)."},"skills_sh_url":"https://skills.sh/majiayu000/claude-arsenal/optflow"},"updatedAt":"2026-05-01T07:01:14.986Z"}}