mustflow 1.15.97

package/templates/default/locales/hi/.mustflow/docs/agent-workflow.md

@@ -0,0 +1,359 @@
+---
+mustflow_doc: docs.agent-workflow
+locale: hi
+canonical: false
+revision: 13
+lifecycle: mustflow-owned
+authority: workflow-policy
+---
+
+# एजेंट कार्यप्रवाह
+
+यह दस्तावेज़ `AGENTS.md` में दिए गए संक्षिप्त राउटर का विस्तार है।
+यह mustflow root के भीतर काम करने वाले एजेंटों के लिए डिफॉल्ट संचालन चक्र परिभाषित करता है।
+
+## आरंभिक दिशा
+
+संपादन आरंभ करने से पहले `AGENTS.md` में सूचीबद्ध फाइलें पढ़ें। स्थापना स्थिति, कॉन्फ़िगर command intents, और सुझाए गए अगले कदमों की त्वरित read-only जांच के लिए `mf doctor` उपयोग करें।
+
+`REPO_MAP.md` को केवल वर्तमान mustflow root के generated navigation map की तरह उपयोग करें। यह संपूर्ण file listing नहीं है और कार्य-संबंधित फाइलें पढ़ने की आवश्यकता का विकल्प नहीं है।
+
+## परियोजना संदर्भ
+
+`.mustflow/context/` में एजेंटों के लिए task-specific परियोजना संदर्भ होता है।
+यह सामान्य documentation archive नहीं है।
+
+- `.mustflow/context/INDEX.md` केवल तब पढ़ें जब कार्य के लिए परियोजना, उत्पाद, डोमेन, UI, बैकएंड, डेटा, सुरक्षा, या संचालन संदर्भ आवश्यक हो।
+- केवल index द्वारा चुनी गई संदर्भ फाइलें पढ़ें।
+- संदर्भ फाइलों को direct user instructions, current code, tests, command contracts, और configured policies की तुलना में द्वितीयक मानें।
+- अनुपस्थित परियोजना लक्ष्य, non-goals, API promises, डेटा नियम, या design tokens का अनुमान न लगाएं।
+- यदि `DESIGN.md` मौजूद हो, तो UI कार्य के लिए उसे वैकल्पिक external visual-design anchor की तरह लें। उसके design tokens को `.mustflow/context/` में कॉपी न करें।
+- यदि संदर्भ का टकराव current files या commands से हो, तो टकराव रिपोर्ट करें और अधिक प्रामाणिक स्रोत को प्राथमिकता दें।
+
+## Skill सक्रियण
+
+Skills task procedures हैं, autonomous tools नहीं। skill सक्रिय करने का अर्थ है संबंधित
+`.mustflow/skills/<name>/SKILL.md` पढ़ना और current command contract के भीतर उसकी procedure
+का पालन करना।
+
+task start और first edit से पहले:
+
+1. `.mustflow/skills/INDEX.md` पढ़ें।
+2. current task को listed scenarios से मिलाएं।
+3. उस scope को edit करने से पहले हर matching `SKILL.md` पढ़ें।
+4. यदि कोई skill लागू नहीं होती, तो `AGENTS.md` और `.mustflow/config/commands.toml`
+   के अंतर्गत सबसे छोटा safe change करें।
+
+यदि नई evidence task type बदल दे तो बाद में भी skill सक्रिय करें। उदाहरण के लिए configured
+command fail हो तो failure triage, test contract बदले तो test maintenance, और documentation
+या workflow बदले तो docs update सक्रिय होता है।
+
+जब multiple skills लागू हों, तो हर affected scope के लिए सबसे specific skill का पालन करें और
+केवल declared command intents को मिलाएं। Skills raw shell commands, long-running processes,
+या task scope के बाहर writes को authorize नहीं करतीं।
+
+Skill use हो, या कोई plausible skill जानबूझकर skip की जाए, तो अगले user update या final
+report में skill name और selection reason संक्षेप में बताएं। Skill selection record करने के लिए
+versioned worklog न बनाएं।
+
+## इनपुट स्थिरता
+
+उपयोगकर्ता निर्देश, स्थानीय फाइलें, command contracts, और generated reports को अलग-अलग स्रोत मानें।
+इन स्रोतों को आपस में न मिलाएं।
+
+- direct user instructions सर्वोच्च प्राथमिकता रखते हैं।
+- संपादित फाइलों के निकटतम `AGENTS.md` को व्यापक parent नियमों पर प्राथमिकता दें।
+- `.mustflow/config/preferences.toml` में defaults होते हैं, अनिवार्य requirements नहीं।
+- `REPO_MAP.md`, `.mustflow/cache/**`, और `.mustflow/state/**` जैसी generated files stale हो सकती हैं।
+- compacted summaries स्थिति के derived representations हैं। current code, configuration, command records, और current user instructions उनसे ऊपर हैं।
+
+जब generated file stale लगे, तो हाथ से संपादित करने के बजाय संबंधित `mf` command से refresh करें।
+
+## प्रभावी नियम मार्ग
+
+सभी निर्देशों को एक priority list में न मिलाएं। conflict को rule type के आधार पर resolve करें:
+
+- User goal: current direct user instructions task तय करते हैं, जब तक वे unsafe न हों।
+- Host safety: host approval, sandbox, और execution gates अधिक सख्त हों तो बाध्यकारी रहते हैं।
+- Repository work rules: सबसे निकट का `AGENTS.md` और `.mustflow/config/*.toml` उपयोग करें।
+- Command execution: `.mustflow/config/commands.toml` project command contract है।
+- Verification evidence: `mf run` receipts और current files direct host shell output से अधिक भरोसेमंद हैं।
+- Context और preferences: `.mustflow/context/*`, `preferences.toml`, और generated maps lower-authority defaults हैं।
+- Session और cache state: host summaries, `.mustflow/cache/**`, और `.mustflow/state/**` current files या current user instructions से ऊपर नहीं होते।
+
+Allowed action sets intersection से छोटे होते हैं। denied actions, approval requirements, privacy rules,
+और destructive-command rules जुड़ते जाते हैं। अगर effective rule स्पष्ट न हो, तो अनुमान लगाने के बजाय
+रुकें और conflict report करें।
+
+## निर्देश पुनर्पाठ
+
+लंबे सत्रों में निर्देशों से भटकाव हो सकता है। निर्देश refresh को project-file counter नहीं, अनिवार्य checkpoint मानें।
+
+mustflow निर्देशों को इन बिंदुओं पर refresh करें:
+
+- session start
+- new task start
+- first edit से पहले
+- command execution से पहले, जब current task और command intent के पास पहले से fresh command refresh न हो
+- `AGENTS.md` या `.mustflow/**` संपादित करने के बाद
+- root बदलने या nested repository में जाने के बाद
+- context compaction या summarization के बाद
+- final report से पहले
+- configured turn, tool-call, या output-size threshold के बाद
+
+refresh स्तर तय करने के लिए `.mustflow/config/mustflow.toml` में `[refresh]` उपयोग करें:
+
+- `light`: `AGENTS.md` और `.mustflow/docs/agent-workflow.md` दोबारा पढ़ें
+- `command`: `AGENTS.md` और `.mustflow/config/commands.toml` दोबारा पढ़ें
+- `skill`: `AGENTS.md` और `.mustflow/skills/INDEX.md` दोबारा पढ़ें
+- `full`: mustflow की पूरी reading sequence दोबारा पढ़ें
+
+`before_command_run` current command intent के लिए freshness checkpoint है। अगर command contract नहीं बदला, तो हर repeated command से पहले सभी files दोबारा पढ़ना जरूरी नहीं है।
+
+repository में turn counters, message counts, या session activity न लिखें। यदि agent host refresh state ट्रैक करता है, तो उसे versioned project documents के बाहर local cache या host-managed state में रखें। skills refresh behavior बता सकती हैं, लेकिन वे भरोसेमंद lifecycle hooks नहीं हैं।
+
+## संदर्भ संपीड़न
+
+`compaction` default data collection feature नहीं है। यह future harnesses या hosts के लिए safety policy है। Default template इसे disabled रखता है और केवल safety rules declare करता है।
+
+Project में hidden reasoning, secrets, full chat transcripts, full terminal output, raw events, या raw command logs store न करें। अगर future में कोई host summaries बनाता है, तो वे source-linked होनी चाहिए और current files तथा current user instructions से कम authority रखनी चाहिए।
+
+## हार्नेस अनुबंध सीमा
+
+mustflow स्वायत्त agent runtime नहीं है। यह agent harnesses के लिए repository-local contract layer है।
+
+- Brain contract: `AGENTS.md`, यह workflow file, और skill documents अपेक्षित मॉडल व्यवहार परिभाषित करते हैं।
+- Hands contract: `.mustflow/config/commands.toml` और `mf run` सुरक्षित command execution परिभाषित करते हैं।
+- Session contract: run records, bounded checkpoints, और compact handoffs पुनर्प्राप्ति के लिए साक्ष्य देते हैं।
+
+worker folders, persona systems, fleet orchestration, raw event logs, या autonomous loops न बनाएं, जब तक रिपॉजिटरी इन वैकल्पिक सतहों को स्पष्ट रूप से न जोड़े।
+
+## लंबी अवधि कार्य चरण
+
+लंबी अवधि या resumed tasks के लिए इन चरणों को अलग रखें:
+
+1. Plan: task goal, repository rules, command contract, और acceptance criteria पढ़ें।
+2. Work: current unit के लिए सबसे छोटा सुरक्षित बदलाव करें।
+3. Verify: केवल configured oneshot command intents चलाएं, बेहतर है `mf run` के माध्यम से।
+4. Judge: परिणाम को मूल acceptance criteria और run receipts के विरुद्ध मूल्यांकित करें।
+5. Handoff: task अधूरा, अवरुद्ध, या continuation योग्य हो तो compact handoff छोड़ें।
+
+Judge चरण worker की completion claim को पर्याप्त न माने। इसमें task goal, changed files, command contract, और run receipts उपयोग होने चाहिए।
+
+## Git व्यवहार नीति
+
+Git operations जो state या history बदलते हैं, default रूप से denied हैं।
+
+- `git.auto_stage = false`: user request के बिना stage न करें।
+- `git.auto_commit = false`: user request के बिना commit न करें।
+- `git.auto_push = false`: user request के बिना push न करें।
+
+ये values repository preferences हैं, permissions नहीं। ये direct user instructions, `.mustflow/config/commands.toml`, या `.mustflow/config/mustflow.toml` की approval policy से ऊपर नहीं हैं। खास तौर पर, `git.auto_commit = true` push permission नहीं देता, और `git.auto_push = true` को `mf init` से enable नहीं किया जा सकता।
+
+## Version impact नीति
+
+Version impact settings repository preferences हैं। वे version-file edits guide करते हैं, लेकिन
+direct user instructions, host safety rules, या `.mustflow/config/mustflow.toml` के approval gates
+को override नहीं करते।
+
+जब code, templates, schemas, CLI behavior, package metadata, user-visible docs,
+installation output, या tests बदलते हैं, तो `.mustflow/config/preferences.toml` में
+`[release.versioning]` देखें।
+
+- `impact_check = true`: diff package या template version change मांगता है या नहीं, report करें।
+- `suggest_bump = true`: evidence clear हो तो patch, minor, या major suggest करें।
+- `auto_bump = true`: impact clear हो, version source मिल चुका हो, और कोई stricter user, host, या
+  approval rule block न करे तो सही package या template version bump apply करें।
+- `auto_bump = false`: user version bump या release-preparation task न मांगे तो package और
+  template version files unchanged रखें।
+- `require_user_confirmation = true`: version files edit करने से पहले पूछें।
+- `require_user_confirmation = false`: `auto_bump = true` होने पर अलग confirmation step न जोड़ें।
+
+Version change suggest या apply करने से पहले repository का version source of truth खोजें।
+यह न मानें कि केवल `package.json` ही version file है। Repository के languages और frameworks से
+मेल खाते manifests, release documents, और existing update patterns inspect करें, फिर report करें
+कि कौन सी files authoritative हैं और कौन सी derived हैं।
+
+Common version-source candidates:
+
+- JavaScript या TypeScript: `package.json` और package-manager lockfiles जब वे package metadata duplicate करते हों।
+- Python: `pyproject.toml`, `setup.cfg`, `setup.py`, या package `__version__` files।
+- Rust: `Cargo.toml`; `Cargo.lock` तभी देखें जब repo lockfile changes को release metadata मानता हो।
+- Go: पहले release tags और release docs; `go.mod` तभी जब module path या tool metadata relevant हो।
+- Java या Kotlin: `pom.xml`, `build.gradle`, `build.gradle.kts`, या `gradle.properties`।
+- .NET: `*.csproj`, `Directory.Build.props`, या `*.nuspec`।
+- Ruby, PHP, Dart, या Swift: `*.gemspec`, `lib/**/version.rb`, `composer.json`, `pubspec.yaml`, या `Package.swift`।
+- Containers, charts, या apps: `Chart.yaml`, image labels, app manifests, release notes, या deployment metadata।
+- mustflow templates: package metadata, template manifests, documentation examples, और installed versions assert करने वाले tests।
+
+Version change के समय package metadata, template manifest versions, docs examples, और tests को
+`sync_*` preferences के अनुसार synchronized रखें।
+
+## कमांड निष्पादन नीति
+
+`package.json`, `Makefile`, `justfile`, `Taskfile.yml`, या source files से command अनुमान न लगाएं।
+`.mustflow/config/commands.toml` को command contract मानें।
+
+command intent तभी agent उपयोग के लिए पात्र है जब ये सभी सत्य हों:
+
+- `status = "configured"`
+- `lifecycle = "oneshot"`
+- `run_policy = "agent_allowed"`
+- `stdin = "closed"`
+- `timeout_seconds` positive integer हो
+- command `argv` से घोषित हो, या `mode = "shell"` और `cmd` से घोषित हो
+- `cwd` current mustflow root के अंदर रहे
+
+`manual_only` नई configurations में status है। पुराने configs के लिए `run_policy = "manual_only"` पढ़ा जा सकता है, लेकिन नई templates को `status = "manual_only"` उपयोग करना चाहिए।
+
+`mf run <intent>` को प्राथमिकता दें ताकि परियोजना को `.mustflow/state/runs/latest.json` में concise run record मिले।
+
+`mf run` command intents को क्रम से चलाएं। जब कोई दूसरा configured intent अभी चल रहा हो तो
+दूसरा `mf run` शुरू न करें। जिन intents में non-empty `writes` declared हैं वे exclusive
+verification phases हैं; कोई और `mf run` चलाने से पहले उनके समाप्त होने की प्रतीक्षा करें। यह
+खास तौर पर तब जरूरी है जब कोई intent `dist/` जैसी package output फिर से लिखता है, क्योंकि local
+`mf` executable उसी output से load हो सकता है।
+
+Host shells commands चला सकते हैं, लेकिन direct project commands अपने आप mustflow verification नहीं बनते।
+यदि कोई command `mf run` को bypass करती है, तो उसकी output को lower-confidence context मानें, सिवाय इसके
+कि user ने manual override स्पष्ट रूप से approve किया हो और final report में बताया गया हो कि mustflow run receipt नहीं बना।
+
+development servers, watchers, browser launches, interactive prompts, या background processes सीधे न चलाएं। इसके बजाय skipped intent और कारण रिपोर्ट करें।
+
+## संपादन नीति
+
+बदलाव कार्य-सीमा के भीतर रखें। drive-by refactors न करें।
+`.mustflow/config/mustflow.toml` में protected paths न बदलें।
+
+परियोजना की मौजूदा शैली अपनाएं। यदि शैली स्पष्ट न हो, तो `.mustflow/config/preferences.toml` में दिए defaults लागू करें।
+
+## Documentation Review Queue
+
+जब agent user-facing, workflow, template, context, या skill documentation बनाता या बदलता है,
+तो user ने explicitly tracking न करने को न कहा हो तो `mf docs review add <path>` से document
+record करें. Queue `.mustflow/review/docs.toml` में stored होती है और जरूरत होने पर ही बनती है.
+
+Review human, LLM, tool, या external process पूरा कर सकता है. केवल broad reviewer kind और
+free-form identifiers जैसे reviewer id, provider, model, command intent, और summary record करें.
+Specific LLM products की fixed list maintain न करें.
+
+Approved document को default review list से hide करते हुए audit record रखने के लिए
+`mf docs review approve <path> --reviewer-kind <kind> --reviewer-id <id>` use करें. Reviewer
+confidently approve न कर सके तो `needs-human`, और repository intentionally review skip करे तो
+`ignore` use करें.
+
+generated files को tools से refresh करें:
+
+- `REPO_MAP.md` को `mf map --write` से
+- `.mustflow/cache/mustflow.sqlite` को `mf index` से
+- `.mustflow/state/runs/latest.json` को `mf run <intent>` से
+
+## सत्यापन
+
+जांच के लिए configured command intents उपयोग करें। सामान्य intent नाम:
+
+- `mustflow_check`
+- `test`
+- `lint`
+- `build`
+- `docs_validate`
+
+यदि expected intent गायब, disabled, manual-only, या not configured हो, तो replacement न गढ़ें।
+क्या छोड़ा गया और क्यों, यह रिपोर्ट करें।
+
+## सत्यापन चयन नीति
+
+सत्यापन का दायरा चुनने के लिए `.mustflow/config/preferences.toml` में `[verification.selection]` देखें।
+ये preferences command execution permission नहीं देतीं। ये केवल बताती हैं कि कौन से configured command intents पर विचार करना है।
+
+सत्यापन risk के अनुपात में होना चाहिए। बदली हुई surface को ढकने वाले `test_related`,
+`test_fast`, `build`, या docs-specific checks configured हों तो उन्हें broad suites से पहले
+चलाएं। broad full-suite tests cross-cutting behavior, release risk, narrow coverage missing,
+या configured policy की स्पष्ट मांग पर चलाएं। यदि narrow intent सही होता लेकिन `unknown`,
+`manual_only`, या absent है, तो सबसे धीमी suite को चुपचाप normal default मानने के बजाय वह gap
+रिपोर्ट करें।
+
+- `strategy = "risk_based"`: बदले हुए behavior, public surface, command contract और risk area को ढकने वाली सबसे छोटी configured checks को प्राथमिकता दें।
+- `strategy = "targeted"`: user, skill या policy व्यापक coverage न मांगे तो सीधे संबंधित checks को प्राथमिकता दें।
+- `strategy = "full"`: लागू होने वाली पूरी configured verification suite को प्राथमिकता दें।
+- `prefer_related_tests = true`: broad test intent से पहले संकीर्ण और संबंधित test intent खोजें।
+- `skip_docs_only_full_test = true`: docs-only बदलाव में docs validation edited surface ढकता हो तो broad tests छोड़े जा सकते हैं।
+- `skip_translation_only_full_test = true`: translation-only बदलाव में source behavior न बदला हो तो broad tests छोड़े जा सकते हैं।
+- `skip_copy_only_full_test = true`: copy-only बदलाव में behavior, schema, template या command contract न बदला हो तो broad tests छोड़े जा सकते हैं।
+- `report_skipped = true`: final report में छोड़ी गई checks और कारण लिखें।
+
+यदि behavior, security, data, command contracts, release output या generated templates बदलने का evidence हो,
+तो skip preference से risk न छिपाएँ। संबंधित configured intent तक बढ़ाएँ या required intent missing रिपोर्ट करें।
+
+## सत्यापन सख्ती नीति
+
+कार्य पूर्ण दिखाने के लिए validation कमजोर न करें।
+
+एजेंट को यह नहीं करना चाहिए:
+
+- checks pass कराने के लिए failing tests हटाना
+- बिना कारण बताए assertions ढीली करना
+- प्रासंगिक command intents छोड़ना
+- failure से बचने के लिए command intents को केवल `not_applicable` चिह्नित करना
+- implementation के बाद acceptance criteria बदलना
+
+एजेंट tests अपडेट कर सकता है जब intended behavior बदला हो, पुराना test गलत हो, या नया behavior नई coverage मांगता हो। ऐसा बदलाव final report में समझाएं।
+
+## परीक्षण प्रासंगिकता नीति
+
+tests व्यवहार अनुबंध हैं, स्थायी artifacts नहीं।
+
+एजेंट कितनी आसानी से नए tests बनाए, यह तय करने के लिए `.mustflow/config/preferences.toml` के
+`[testing.authoring]` को देखें। Default `new_test_policy = "evidence_required"` का मतलब है
+कि नया test तभी जोड़ा जाए जब behavior contract evidence हो, जैसे बदला public behavior,
+regression risk, configuration rule, schema contract, या security/data path। यह preference केवल
+test authoring behavior guide करती है; यह required verification को कमजोर नहीं करती और valid tests
+हटाने का कारण नहीं बनती।
+
+एजेंट को यह नहीं करना चाहिए:
+
+- केवल पुराने tests की अपेक्षा के कारण हटाया गया व्यवहार फिर लाना
+- जानबूझकर हटाई गई सुविधाओं के tests बचाए रखना
+- validation pass कराने के लिए failing tests हटाना
+- behavior change समझाए बिना assertions ढीली करना
+- tests pass कराने के लिए केवल snapshots अपडेट करना
+
+एजेंट tests अपडेट या हटा सकता है जब tested behavior जानबूझकर हटाया गया हो, public contract बदला हो, test केवल हटे implementation details encode करता हो, coverage किसी मजबूत test से duplicate हो, या snapshot अप्रचलित हो।
+
+जब tests जोड़े, अपडेट, हटाए जाएं, या stale candidates पहचाने जाएं, तब behavior contract, affected tests, run commands, skipped command intents, और remaining test risks रिपोर्ट करें।
+
+## बजट, अनुमोदन, और पृथक्करण
+
+लंबी अवधि सुरक्षा नीति के लिए `.mustflow/config/mustflow.toml` उपयोग करें।
+
+- `[budget]` iterations, wall-clock time, command runs, output volume, और repeated failures सीमित करता है।
+- `[approval]` उन actions की सूची देता है जिनके लिए आगे बढ़ने से पहले मानव अनुमोदन चाहिए।
+- `[isolation]` लंबी अवधि tasks के लिए पसंदीदा worktree या sandbox boundary बताता है।
+
+जब budget limit या approval gate पहुंचे, तो रुकें और report करें। handoff केवल तब उपयोग करें जब यह repository handoff workflow स्पष्ट रूप से enable करे। looping जारी न रखें।
+यदि isolation policy अलग worktree या sandbox मांगती है, तो dirty primary worktree में लंबी अवधि autonomous work न चलाएं।
+
+## विफलता प्रबंधन
+
+जब command विफल हो:
+
+1. मूल command intent नाम सुरक्षित रखें।
+2. exit code और truncated output tail का विश्लेषण करें।
+3. विफलता की सबसे संभावित मूल वजह पहचानें।
+4. असंबंधित फाइलों में बदलाव न करें।
+5. fix के बाद सबसे लक्षित प्रासंगिक सत्यापन फिर चलाएं।
+6. छोड़ी गई जांचें और शेष जोखिम रिपोर्ट करें।
+
+`.mustflow/` में raw full logs, secrets, customer data, या लंबे transcripts संग्रहीत न करें।
+
+## रिपोर्टिंग
+
+final reports में शामिल होना चाहिए:
+
+- बदली हुई फाइलें
+- चलाए गए command intents
+- कारण सहित छोड़े गए command intents
+- सत्यापन परिणाम
+- शेष जोखिम
+
+commit सुझाव केवल तब दें जब `.mustflow/config/preferences.toml` इसकी अनुमति देता हो।

package/templates/default/locales/hi/.mustflow/skills/INDEX.md

@@ -0,0 +1,78 @@
+---
+mustflow_doc: skills.index
+locale: hi
+canonical: false
+revision: 43
+authority: router
+lifecycle: mustflow-owned
+---
+
+# Skills Index
+
+Consult only the skill document relevant to the current task. If no specific skill applies,
+refer to `AGENTS.md` and `.mustflow/config/commands.toml` to implement the most minimal safe change.
+
+## Selection Rules
+
+- At task start and before the first edit, compare the user request and expected changed files with
+  the triggers below.
+- If one or more triggers match, read each `SKILL.md` before editing that scope.
+- When a skill is used, or when a plausible skill is intentionally skipped, leave a concise
+  selection note in the next user-facing update or final report.
+- If a new condition appears during the task, such as a command failure, test contract change, or
+  documentation change, pause and read the newly matching skill before continuing.
+- If no trigger applies, do not invent a skill. Continue with `AGENTS.md`,
+  `.mustflow/docs/agent-workflow.md`, and `.mustflow/config/commands.toml`.
+- Skill documents guide procedure only. They do not authorize command execution outside the declared
+  command intents.
+- Keep the route table compact: each route states the trigger, required input, edit scope, risk,
+  verification intents, and expected output.
+
+| Trigger | Skill Document | Required Input | Edit Scope | Risk | Verification Intents | Expected Output |
+| --- | --- | --- | --- | --- | --- | --- |
+| Generated artifacts, packaged files, binary assets, reports, or downloadable outputs are created, referenced, or reported | `.mustflow/skills/artifact-integrity-check/SKILL.md` | Artifact paths, source or generation path, package rules, and artifact expectations | Artifact references, package metadata, tests, and documentation | unverified or stale artifact claim | `changes_status`, `changes_diff_summary`, `test_release`, `build`, `mustflow_check` | Artifact evidence, inclusion or format checks, skipped checks, and integrity risk |
+| Code changes need review before report | `.mustflow/skills/code-review/SKILL.md` | Diff and task goal | Changed files | behavior and regression | `test`, `test_related`, `test_audit`, `lint` | Findings or no-issue note |
+| Code is being refactored, reorganized, renamed, deduplicated, simplified, or structurally improved while existing behavior should be preserved | `.mustflow/skills/behavior-preserving-refactor/SKILL.md` | Refactoring goal, target area, behavior evidence, local patterns, current changed files, and command contract entries | Small behavior-preserving refactor steps, related tests, and directly synchronized docs or contracts | hidden behavior change, broad cleanup, misleading abstraction, unsafe deduplication, or unverified legacy change | `changes_status`, `changes_diff_summary`, `test_related`, `test`, `docs_validate_fast`, `test_release`, `mustflow_check` | Goal, behavior evidence, structural risks, refactoring ladder, changes made, excluded behavior changes, verification, and remaining risks |
+| Class inheritance, base classes, abstract classes, template methods, protected state, mixins, framework subclasses, or subtype hierarchies are introduced, reviewed, or refactored, especially for behavior reuse or feature variants | `.mustflow/skills/composition-over-inheritance/SKILL.md` | Inheritance surface, reuse goal, change dimensions, local composition patterns, compatibility constraints, current changed files, and command contract entries | Classes, functions, role interfaces, policies, strategies, adapters, decorators, state machines, tests, wrappers, and directly synchronized docs or templates | fragile parent-child coupling, subclass explosion, broken substitutability, hidden protected state, over-composition, or untested behavior-preserving refactor | `changes_status`, `changes_diff_summary`, `test_related`, `test`, `lint`, `build`, `docs_validate_fast`, `test_release`, `mustflow_check` | Inheritance review, keep-or-replace decision, change dimensions, composition pattern, tests, verification, and remaining hierarchy risk |
+| Multiple interchangeable algorithms, policies, calculations, scoring methods, sorting methods, recommendation methods, pricing rules, discount rules, shipping methods, payment methods, notification methods, permission policies, provider choices, feature-flag variants, or repeated branches choose how to do the same kind of work | `.mustflow/skills/strategy-pattern/SKILL.md` | Stable workflow, variants and shared purpose, current branch locations, common input and output shape, selection criteria, local Result, dependency injection, decorator, registry, and test patterns, current changed files, and command contract entries | Strategy function types, interfaces, concrete strategies, selectors, resolvers, registries, decorators, context wiring, tests, and directly synchronized docs or templates | over-abstracted small branch, wrong use-case grouping, context knowing concrete strategies, silent fallback, unsafe user-selected strategy, request-stateful strategy, strategy combination explosion, or untested selector behavior | `changes_status`, `changes_diff_summary`, `test_related`, `test`, `lint`, `build`, `docs_validate_fast`, `test_release`, `mustflow_check` | Strategy classification, shared contract, strategy registry, selector or resolver, default and unsupported-key behavior, tests, verification, and remaining strategy risk |
+| State-changing user or system intents, command data objects, command handlers, command buses, idempotency, authorization, transactions, outbox events, audit logs, retries, concurrency, long-running jobs, or external side effects need one traceable execution unit | `.mustflow/skills/command-pattern/SKILL.md` | User or system intent, source boundary, payload, actor and context, affected resources, local Result, repository, gateway, unit-of-work, outbox, idempotency, audit, retry, and test patterns | Command payloads, command context, handlers, command bus wiring when justified, idempotency, outbox, audit, retry, transaction, controller or worker adapters, tests, and directly synchronized docs or templates | command ceremony for reads, giant handler, hidden domain policy, unsafe duplicate side effect, transaction and external-call coupling, missing audit trail, retry without idempotency, or untested command boundary | `changes_status`, `changes_diff_summary`, `test_related`, `test`, `lint`, `build`, `docs_validate_fast`, `test_release`, `mustflow_check` | Command classification, payload and context shape, handler dependencies, domain delegation, transaction, outbox, idempotency, retry, audit, concurrency choices, tests, verification, and remaining command safety risk |
+| Controllers, handlers, command handlers, workers, services, or UI events need one stable high-level entry point over a complex subsystem, repeated multi-step workflow, multiple dependencies, external services, storage, queues, caches, transactions, idempotency, retries, logging, or normalized results | `.mustflow/skills/facade-pattern/SKILL.md` | Caller surface, high-level operation, repeated internal sequence, leaked subsystem details, dependencies, expected response and errors, authorization, idempotency, retry, transaction, observability, security, performance, local Result, port, adapter, command, and test patterns | Facade request, context, response, and error types, injected collaborators, orchestration, mappers, error normalizers, idempotency, transactions, retries, events, cache invalidation, logging, tests, and directly synchronized docs or templates | pass-through wrapper, god service, hidden domain policy, public internal steps, SDK or ORM leakage, facade-to-facade coupling, request-stateful facade, unsafe retry, external call inside transaction, or untested subsystem orchestration | `changes_status`, `changes_diff_summary`, `test_related`, `test`, `lint`, `build`, `docs_validate_fast`, `test_release`, `mustflow_check` | Facade classification, caller simplification, request and context shape, normalized result, injected dependencies, delegated domain rules, transaction/idempotency/retry/logging choices, tests, verification, and remaining facade risk |
+| Business decisions, validation, authorization, pricing, eligibility, state transitions, domain events, effect descriptions, or calculations are mixed with databases, HTTP handlers, repositories, SDK calls, files, queues, logs, metrics, clocks, randomness, environment reads, payments, emails, or framework request/response objects | `.mustflow/skills/pure-core-imperative-shell/SKILL.md` | Business action, decision facts, side effects, current boundary shape, local result/event/effect patterns, behavior evidence, changed files, and command contract entries | Core decision functions, shell orchestration, mappers, result/error types, events, effect descriptions, tests, and directly synchronized docs or templates | business rules hidden in I/O, non-deterministic core, mock-heavy tests, stale decisions, duplicate side effects, transaction/external-call coupling, or over-layered trivial CRUD | `changes_status`, `changes_diff_summary`, `test_related`, `test`, `lint`, `build`, `docs_validate_fast`, `test_release`, `mustflow_check` | Decision isolated, explicit core input and output, shell responsibilities, events or effects, typed business failures, tests, verification, and remaining mixed-logic risk |
+| Domain objects have lifecycle state, status fields, phase or step fields, allowed actions depend on state, transitions are scattered, external results change state, duplicate events are possible, or state changes need transition tables, guards, effects, history, idempotency, or concurrency control | `.mustflow/skills/state-machine-pattern/SKILL.md` | Entity, state field, state list, event list, terminal states, current state-changing code, guards, context facts, effects, history, idempotency, concurrency risks, local Result and outbox patterns, and command contract entries | State unions, event unions, transition tables, guard functions, pure transition functions, dispatch shell, outbox, transition logs, idempotency records, available-action helpers, tests, and directly synchronized docs or templates | direct state assignment, hidden invalid transition, silent no-op, impure guard, external effect before commit, duplicate webhook damage, state explosion, stale concurrent transition, UI/server rule drift, or untested lifecycle | `changes_status`, `changes_diff_summary`, `test_related`, `test`, `lint`, `build`, `docs_validate_fast`, `test_release`, `mustflow_check` | Lifecycle classification, states and events, transition table, guards and context facts, effects and history, idempotency and concurrency choices, direct assignment cleanup, tests, verification, and remaining state-machine risk |
+| Expected failures, meaningful absence, null or undefined returns, thrown business errors, boolean success flags, raw string errors, repository lookups, validation, parsing, external adapter errors, or boundary error mapping need explicit value-based handling | `.mustflow/skills/result-option/SKILL.md` | Operation semantics, absence and failure cases, local Result/Option/error conventions, layer ownership, public response rules, sensitive data constraints, changed files, and command contract entries | Result and Option helpers, function signatures, typed errors, boundary mappers, repository/service/controller contracts, tests, and directly synchronized docs or templates | hidden null, swallowed error, thrown business failure, ambiguous boolean result, provider error leakage, public error-shape drift, or over-wrapped total function | `changes_status`, `changes_diff_summary`, `test_related`, `test`, `lint`, `build`, `docs_validate_fast`, `test_release`, `mustflow_check` | Return shape decision, error codes and categories, absence handling, boundary conversions, preserved throw paths, tests, verification, and remaining exception or null risk |
+| Repeated null, undefined, None, or nil checks, optional dependencies, disabled integrations, null loggers, null analytics, null caches, optional notifications, no-op collaborators, identity processors, or safe neutral implementations are introduced or refactored | `.mustflow/skills/null-object-pattern/SKILL.md` | Optional collaborator, interface, absence semantics, caller branch needs, neutral output, required side effects, security, money, data, and audit risks, assembly location, local Result, Option, dependency injection, strategy, and test patterns | Interfaces, null, no-op, disabled, identity, empty, deny-all, or failing implementations, assembly wiring, non-null dependency types, tests, and directly synchronized docs or templates | hidden required failure, fake success, authorization bypass, dropped persistence, skipped audit, swallowed initialization error, stateful null object, or caller still nullable | `changes_status`, `changes_diff_summary`, `test_related`, `test`, `lint`, `build`, `docs_validate_fast`, `test_release`, `mustflow_check` | Absence classification, null object decision, neutral implementation, assembly selection, nullable caller cleanup, tests, verification, and remaining hidden-failure risk |
+| User requirements, acceptance criteria, issue reports, bug reports, product notes, compatibility promises, or examples must be preserved as regression coverage before or during implementation | `.mustflow/skills/requirement-regression-guard/SKILL.md` | Requirement source, observable behavior, existing tests or fixtures, implementation scope, changed files, and command contract entries | Focused tests, fixtures, examples, schemas, docs, and implementation changes directly tied to the requirement | untested requirement, invented acceptance criteria, weakened tests, hidden behavior drift, or unverifiable implementation claim | `changes_status`, `changes_diff_summary`, `test_related`, `test`, `test_audit`, `docs_validate_fast`, `test_release`, `mustflow_check` | Requirement sources, coverage map, guards added or reused, implementation changes, deferred requirements, verification, and remaining regression risk |
+| Multiple AI workers, subagents, external agents, parallel task runners, or worktree-based worker roles are planned or used for one repository task | `.mustflow/skills/multi-agent-work-coordination/SKILL.md` | Task goal, worker roles, write permissions, file ownership, workspace isolation, credential boundary, merge owner, and command contract entries | Coordination plan, worker instructions, ownership boundaries, merge notes, and directly synchronized tests or docs | same-file races, conflicting instructions, leaked credentials, shared auth cache, untrusted worker output, merge drift, or unverified parallel result | `changes_status`, `changes_diff_summary`, `test_related`, `test`, `docs_validate_fast`, `test_release`, `mustflow_check` | Worker limit, role map, write ownership, isolation and credential boundaries, merge owner, verification, skipped checks, and remaining coordination risk |
+| An unfamiliar codebase area needs an evidence-based map before planning, implementation, or reporting | `.mustflow/skills/codebase-orientation/SKILL.md` | User request, target area, relevant instructions, and current source, test, schema, template, configuration, or documentation files | Read-only orientation notes and any smallest follow-up edit chosen from inspected evidence | stale documentation, wrong ownership boundary, or invented architecture claim | `changes_status`, `changes_diff_summary`, `mustflow_check` | Scope inspected, entrypoints, flow map, ownership boundaries, verification options, risks, unknowns, and smallest safe next step |
+| Repository improvement, audit, prioritization, stabilization, polish, onboarding, contributor-readiness, production-readiness, or iterative improvement is requested without a single predetermined edit | `.mustflow/skills/repo-improvement-loop/SKILL.md` | User goal, improvement mode, repository evidence, candidate risks, current changed files, and command contract entries | Repository diagnosis, ranked candidates, and at most one scoped improvement cycle unless the user explicitly requests analysis-only | idea spam, ungrounded prioritization, autonomous loop drift, broad rewrite, or unverified improvement claim | `changes_status`, `changes_diff_summary`, `docs_validate_fast`, `test_release`, `mustflow_check` | Mode, evidence inspected, scored candidates, selected improvement, files changed or analysis-only note, verification, next improvement question, and stop reason |
+| A dense plan, suggestion, code explanation, review result, flow map, or decision set would be easier to inspect as a safe static HTML review artifact | `.mustflow/skills/visual-review-artifact/SKILL.md` | User request, artifact goal, target audience, source evidence, output path, and relevant command contract entries | Temporary `.mustflow/state/artifacts/**` output or explicitly requested versioned HTML artifact, plus direct references, docs, or package metadata | unsafe HTML behavior, prompt injection, unverified artifact claim, or mistaken approval authority | `changes_status`, `changes_diff_summary`, `docs_validate_fast`, `test_release`, `mustflow_check` | Artifact kind and path, source evidence, review-only boundary, local interactions, verification, skipped checks, and remaining decision risk |
+| Changed files need risk classification and verification selection | `.mustflow/skills/diff-risk-review/SKILL.md` | Changed-file list, diff summary, and task goal | Changed surfaces and verification report | under- or over-verification | `changes_status`, `changes_diff_summary`, `test`, `test_related`, `test_audit`, `lint`, `build`, `docs_validate`, `mustflow_check` | Risk level, verification choice, rollback notes |
+| Declared behavior must stay aligned across code, schemas, templates, tests, and docs | `.mustflow/skills/contract-sync-check/SKILL.md` | Changed files, intended behavior, source of truth, derived surfaces, and command contract entries | Contract source and required synchronized surfaces | contract drift | `changes_status`, `changes_diff_summary`, `docs_validate_fast`, `test_release`, `mustflow_check` | Contract source, synchronized surfaces, deferred surfaces, verification, and drift risk |
+| Dates, versions, counts, durations, limits, metrics, benchmarks, prices, percentages, or other numeric facts are created, edited, or reported | `.mustflow/skills/date-number-audit/SKILL.md` | Date or numeric fact, source of truth, dependent surfaces, precision expectation, and command contract entries | Numeric statements, metadata, tests, docs, templates, and reports | invented, stale, or mismatched numeric claim | `changes_status`, `changes_diff_summary`, `docs_validate_fast`, `test_release`, `mustflow_check` | Audited values, source of truth, synchronized surfaces, skipped checks, and remaining numeric risk |
+| Packages, runtimes, tools, commands, services, or platform capabilities are assumed, added, invoked, or documented | `.mustflow/skills/dependency-reality-check/SKILL.md` | Dependency or capability, repository declarations, version or capability claim, and command contract entries | Dependency declarations, imports, command metadata, tests, and docs | invented or unavailable dependency | `changes_status`, `changes_diff_summary`, `build`, `test_release`, `mustflow_check` | Dependency status, synchronized surfaces, verification, and remaining dependency risk |
+| External systems, protocols, SDKs, databases, webhooks, queues, files, caches, framework requests or responses, AI models, browser storage, or provider data cross the core boundary or need port/adapter translation, error mapping, retry, idempotency, security, or observability handling | `.mustflow/skills/adapter-boundary/SKILL.md` | External system or protocol, inbound/outbound direction, internal use case, local port/adapter patterns, provider risk, changed files, and command contract entries | Ports, adapters, mappers, controllers, workers, stores, gateways, tests, fixtures, assembly wiring, and directly synchronized docs or templates | provider leakage, pass-through wrapper, unclassified external failure, duplicate side effect, unsafe retry, missing timeout, secret or personal-data leak, or untested integration drift | `changes_status`, `changes_diff_summary`, `test_related`, `test`, `lint`, `build`, `docs_validate_fast`, `test_release`, `mustflow_check` | Boundary classification, internal port, provider containment, validation and mapping, timeout/retry/idempotency handling, security notes, verification, and remaining provider risk |
+| Core or application logic creates, imports, resolves, or hides external dependencies such as databases, SDKs, clocks, random generators, configuration, loggers, framework objects, filesystems, queues, AI clients, or payment/email providers | `.mustflow/skills/dependency-injection/SKILL.md` | Target code area, hidden dependency, intended business capability, layer ownership, local port/adapter patterns, changed files, and command contract entries | Core logic signatures, ports, adapters, assembly roots, tests, and directly synchronized docs or templates | hidden global state, untestable business logic, provider leakage, lifecycle drift, or service-locator coupling | `changes_status`, `changes_diff_summary`, `test_related`, `test`, `lint`, `build`, `docs_validate_fast`, `test_release`, `mustflow_check` | Dependency boundary, direct dependencies found, injection style, ports/adapters, assembly boundary, tests or fakes, verification, and remaining dependency leakage |
+| Git reports CRLF/LF warnings or tracked text files may need line-ending normalization | `.mustflow/skills/line-ending-hygiene/SKILL.md` | Warning text or changed-file evidence, line-ending policy, changed-file status, and command contract entries | Line-ending policy files, tracked text files, command metadata, tests, and reports | silent working-tree rewrite or policy drift | `line_endings_check`, `changes_status`, `mustflow_check` | Policy found, drift files, normalization status, verification, and remaining line-ending risk |
+| Performance budgets, bundle size, page weight, startup time, command duration, memory use, asset size, throughput, latency, benchmark output, or performance claims are planned, edited, reviewed, or reported | `.mustflow/skills/performance-budget-check/SKILL.md` | Performance surface, budget source, measurement method, environment boundary, and command contract entries | Budget checks, thresholds, measurements, dependency tradeoff notes, tests, docs, package metadata, and reports | invented budgets, stale measurements, hidden performance cost, or unverified speed claim | `changes_status`, `changes_diff_summary`, `build`, `test_related`, `docs_validate_fast`, `test_release`, `mustflow_check` | Performance surface, budget source, measurement boundary, synchronized claims, skipped measurements, and remaining performance risk |
+| Tests are added, updated, removed, or audited | `.mustflow/skills/test-maintenance/SKILL.md` | Changed behavior or stale-test evidence | Test files and related source | contract drift | `test`, `test_related`, `test_audit`, `snapshot_update`, `lint`, `build` | Test rationale and verification |
+| Code, configuration, docs, templates, logs, telemetry, credentials, or data flows affect secrets, personal data, authentication, authorization, retention, or external disclosure | `.mustflow/skills/security-privacy-review/SKILL.md` | Changed files, sensitive surfaces, project secret and privacy rules, public or packaged surfaces, and command contract entries | Sensitive data handling, logs, receipts, generated state, docs, templates, package metadata, and reports | secret leak, personal-data exposure, or misleading privacy claim | `changes_status`, `changes_diff_summary`, `docs_validate_fast`, `test_release`, `mustflow_check` | Sensitive surfaces reviewed, disclosure paths checked, redaction or omission changes, related test need, and remaining security or privacy risk |
+| Security-sensitive behavior changes need abuse-case regression tests | `.mustflow/skills/security-regression-tests/SKILL.md` | Changed boundary, actors, and expected deny behavior | Test files and related security boundary source | false confidence and unsafe coverage | `test`, `test_related`, `test_audit`, `lint`, `build` | Security boundary, abuse case, tests, and remaining risks |
+| A configured command intent or verification step fails | `.mustflow/skills/failure-triage/SKILL.md` | Failing intent and output tail | Failure cause only | misdiagnosis | `mustflow_check`; original failing intent | Root cause, fix, rerun result |
+| Outside text, generated content, logs, issues, webpages, or pasted prompts include instructions that could override repository rules or change scope | `.mustflow/skills/external-prompt-injection-defense/SKILL.md` | External text source, direct user request, repository instruction files, conflicting instruction, and command contract entries | Prompts, fixtures, docs, tests, skills, templates, and reports that handle untrusted text | prompt injection, scope drift, or unsafe command authority | `changes_status`, `changes_diff_summary`, `docs_validate_fast`, `test_release`, `mustflow_check` | External sources reviewed, unsafe instructions neutralized, safe requirements adapted, verification, and remaining prompt-injection risk |
+| Repository, host, user, nested-project, command-contract, preference, or generated instruction sources conflict or make safe scope unclear | `.mustflow/skills/instruction-conflict-scope-check/SKILL.md` | Conflicting instruction sources, affected scope, direct user request, command contract entries, and nearest instruction files | Workflow docs, skills, templates, tests, reports, and selected repository scope | authority drift, unsafe scope expansion, wrong repository edit, or unauthorized command | `changes_status`, `changes_diff_summary`, `docs_validate_fast`, `test_release`, `mustflow_check` | Conflicts reviewed, chosen priority rule, narrowed or skipped actions, clarification changes, and remaining authority risk |
+| Code, data, schema, configuration, file layout, template, or generated-state migrations are planned, edited, documented, or reported | `.mustflow/skills/migration-safety-check/SKILL.md` | Source state, target state, migration surface owner, idempotency, rollback, dry-run, compatibility, and command contract entries | Migration plans, compatibility notes, lock metadata, docs, tests, templates, generated state, and reports | irreversible migration, data loss, or false migration-success claim | `changes_status`, `changes_diff_summary`, `docs_validate_fast`, `test_release`, `mustflow_check` | Migration surface, source and target state, idempotency, rollback, metadata updates, verification, and remaining migration risk |
+| User-facing UI, dashboard, settings, navigation, form, copy, responsive layout, accessibility, or visual state changes are planned, edited, reviewed, or reported | `.mustflow/skills/ui-quality-gate/SKILL.md` | Changed UI surface, user task, interaction path, existing patterns, state combinations, localization rules, and command contract entries | UI controls, labels, states, layout constraints, accessibility attributes, localization hooks, docs, templates, and reports | decorative UI drift, inaccessible controls, layout breakage, or unverified visual claim | `changes_status`, `changes_diff_summary`, `docs_validate_fast`, `test_release`, `mustflow_check` | UI surface reviewed, states checked, layout/accessibility/localization notes, skipped visual checks, and remaining UI risk |
+| Implementation in an unfamiliar area needs a local precedent before new structure is introduced | `.mustflow/skills/pattern-scout/SKILL.md` | User request, intended file area, nearby examples, and current changed files | Pattern evidence and files needed to follow it | invented parallel structure | `changes_status`, `changes_diff_summary`, `mustflow_check` | Local pattern, applied alignment, intentional deviations, and verification |
+| New feature, module, folder layout, architecture, scaffold, refactor, routing, data model, or external service integration may require hidden structure decisions before coding | `.mustflow/skills/structure-discovery-gate/SKILL.md` | User request, intended capability, hidden assumptions, named technologies or services, and relevant local patterns | Questions, assumptions, proposed file boundaries, and the smallest resulting implementation | brittle structure, vendor-name leakage, over-questioning, or speculative abstraction | `changes_status`, `changes_diff_summary`, `docs_validate_fast`, `test_release`, `mustflow_check` | Blocking questions, assumptions, proposed files and responsibilities, dependency direction, local pattern, verification, and remaining structure risk |
+| A bug or confusing failure needs a fix before the smallest reproduction is clear | `.mustflow/skills/repro-first-debug/SKILL.md` | Symptom, expected behavior, observed output, and likely changed files | Reproduction notes, focused test, and likely cause | speculative fix or over-testing | `test_related`, `test_fast`, `mustflow_check` | Reproduction evidence, minimal fix, verification, and remaining risk |
+| Claims depend on current, external, dated, versioned, or otherwise drift-prone sources | `.mustflow/skills/source-freshness-check/SKILL.md` | Stale-sensitive claim, source text or page, date or version context, and source policy | Source wording, documentation, and freshness report | stale or unverifiable claim | `changes_status`, `docs_validate_fast`, `mustflow_check` | Checked source boundary, wording changes, skipped refreshes, and stale-source risk |
+| `.mustflow/context/PROJECT.md` needs cautious project context | `.mustflow/skills/project-context-authoring/SKILL.md` | Supported project facts | `.mustflow/context/PROJECT.md` | authority drift | `mustflow_check` | Updated cautious context |
+| Skill procedures or routes are created or maintained | `.mustflow/skills/skill-authoring/SKILL.md` | Repeated task evidence | `.mustflow/skills/**` | overlap and command drift | `mustflow_check`, `docs_validate` | Skill route and procedure changes |
+| `README.md` is created, restructured, or substantially rewritten | `.mustflow/skills/readme-authoring/SKILL.md` | User request, existing README if any, repository evidence, nearest instructions, and command contracts | `README.md` and directly linked public docs | invented project claims, marketing drift, or loss of human-authored intent | `docs_validate_fast`, `mustflow_check` | Evidence-based README changes, preserved or deferred sections, verification notes |
+| Documentation review queue entries need prose cleanup | `.mustflow/skills/docs-prose-review/SKILL.md` | Review queue entry or selected document path, review comment if present, target language, reviewer metadata | Selected documentation file and review ledger entry | meaning drift or stale queue state | `docs_validate`, `mustflow_check` | Prose changes, recorded review status, verification notes |
+| Web image assets are added, converted, resized, or replaced | `.mustflow/skills/web-asset-optimization/SKILL.md` | Image asset request and target path | Web image assets | asset quality and size | `asset_optimize`, `build` | Optimized asset notes |
+| Documentation changes affect public or workflow docs | `.mustflow/skills/docs-update/SKILL.md` | Changed behavior or field | Relevant docs only | stale public docs | `docs_validate_fast`, `docs_validate`, `mustflow_check` | Doc changes and skipped checks |
+
+When introducing a new skill, link it here and define the specific trigger and route fields.
+Avoid including raw shell commands in skill documents; instead, reference the command intent
+names as defined in `.mustflow/config/commands.toml`.