Review & quality
19,178 rows, by stacks then stars
1,766 of these skill files have been read, by 1,273 distinct authors, and what they tell an agent counted. What Review & quality authors agree on, and what they forbid
TommyBez/skillsboard/.agents/skills/review-animations Skill
5★ repoReviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.
The same file is in 1 other repository
TAKEOFF69/codex-skills-kit/skills/git-under-contention Skill
5★ repoOperate Git safely when multiple humans or coding agents may share a repository, checkout, index, branches, or worktrees. Use before staging, committing, pushing, merging, rebasing, creating or removing worktrees, recovering apparently lost edits, handling staged files you did not touch, or preserving unfinished agent work under parallel-session contention.
TAKEOFF69/codex-skills-kit/skills/verify-honestly Skill
5★ repoChoose proportional verification and write evidence-bounded completion claims for coding-agent work. Use before saying work is fixed, done, working, passing, shipped, or deployed; when asked to verify a change; when relying on another agent's findings; or when reporting counts, artifact properties, UI behavior, live data, or production state.
ondata/skills/skills/open-data-quality Skill
no license5★ repoComprehensive open data quality validator for two audiences: data analysts who need to assess whether a dataset is ready to use, and public administrations who want to self-evaluate their published data. Automatically adapts based on input type: (A) local CSV file only — performs file-level structural and content checks; (B) CKAN/open data portal dataset — adds metadata completeness, resource accessibility, URL reachability, and DCAT-AP compliance (supports all national profiles: DCAT-AP 2.x baseline, IT, BE, NL, DE, FR, UK, ES, and others). Always use this skill when the user mentions: data quality, validate dataset, check CSV, open data compliance, metadata audit, CKAN dataset review, "is this data usable?", or whenever a CSV file or CKAN dataset ID/URL is provided for quality assessment. Produces severity-ranked reports (blocker / major / minor) with concrete fixes, quality score, and a plain-language summary for non-technical stakeholders.
The same file is in 1 other repository
christopherlouet/claude-base/.claude/skills/git-worktrees Skill
5★ repoUsing git worktrees for parallel development. Trigger when the user wants to work on multiple branches simultaneously, do parallel dev, or manage worktrees.
christopherlouet/claude-base/.claude/skills/qa-design Skill
5★ repoUI/UX design audit and verification of web best practices, including responsive/mobile-first breakpoints. Trigger when the user wants to audit the design, verify the UI/UX, check responsive behaviour, or improve the user interface.
christopherlouet/claude-base/.claude/skills/qa-review Skill
5★ repoPerform a thorough code review. Use when the user requests a review, wants to verify code quality, or before merging a PR.
christopherlouet/claude-base/.claude/skills/work-commit Skill
5★ repoGenerates clear commit messages following Conventional Commits. Use when the user wants to commit, asks for a commit message, or after completing a modification.
christopherlouet/claude-base/.claude/skills/work-pr Skill
5★ repoCreate a complete and well-documented Pull Request. Use when the user wants to create a PR, submit their changes, or prepare a merge request.
recallnet/codecontext/.claude/skills/context-staged Skill
no license5★ repoCheck all staged files for stale @context annotations before committing. Use as a pre-commit verification step.
recallnet/codecontext/packages/claude-plugin/skills/context-diff Skill
no license5★ repoCheck which @context annotations are affected by recent code changes. Use after editing code to verify context accuracy and flag stale annotations.
recallnet/codecontext/packages/claude-plugin/skills/context-staged Skill
no license5★ repoCheck all staged files for stale @context annotations before committing. Use as a pre-commit verification step.
Bruno-Cunha-Souza/ValarMindSkills/skills/code-review Skill
5★ repoLifecycle code review Go/Rust/TS/Python. Auto-detects toolchain, runs static analysis, emits severity-ranked findings + file:line evidence, diffs, risk tags (SAFE/REVIEW/BREAKING). Covers OWASP Top 10, perf anti-patterns, test quality. Read-only — every finding cites file:line. Triggers: 'review code', 'revisar código', 'auditar código', '/code-review'.
Bruno-Cunha-Souza/ValarMindSkills/skills/code-security-review Skill
5★ repoWeb/API security lifecycle for Go, Next.js, Python, and Bun — design controls, active testing, supply-chain/CI-CD, and LLM/agentic/MCP coverage. Maps to OWASP Web Top 10 2025 + API 2023 + LLM 2025 + Agentic 2026. Triggers: 'security review', 'revisão de segurança', 'auditar segurança', 'pentest', '/code-security-review'.
Bruno-Cunha-Souza/ValarMindSkills/skills/github-commit Skill
5★ repoGenerate Conventional Commit from staged diff. Triggers: 'commit', 'create commit', 'commit message'.
Bruno-Cunha-Souza/ValarMindSkills/skills/github-pr-review Skill
5★ repoStructured GitHub PR review — correctness, security, performance, maintainability. Severity-ranked findings + verdict (Approve/Request Changes/Comment). Non-PR: @code-review. Triggers: 'review PR', 'revisar PR', 'analisar pull request', '/github-pr-review'.
Bruno-Cunha-Souza/ValarMindSkills/skills/ponytail-review Skill
5★ repoOver-engineering review — finds what to DELETE, not what to fix. One line per finding with tags delete/stdlib/native/yagni/shrink and a net-lines score. Three scopes: current diff (default), whole repo ('repo'/'audit'), or 'debt' to harvest ponytail: comments into a ledger. Complements correctness review (@code-review, @github-pr-review) — this lens only hunts complexity. Use when the user says 'review for over-engineering', 'what can we delete', 'is this over-engineered', 'find bloat', 'audit for bloat', 'ponytail debt', 'list the shortcuts', '/ponytail-review'. One-shot report; applies nothing.
Amadeus performance validation
amadeus-dlc/amadeus/.agents/skills/amadeus-performance-validation Skill
5★ repoRun the AI-DLC `performance-validation` stage (operation phase) in isolation, without advancing the main workflow. Packages `/amadeus --stage performance-validation --single`: the engine emits one run-stage directive for performance-validation and its gate, the conductor runs it, then the single-stage run commits a synthetic-id pair and stops. The main workflow's Current Stage is never touched.
Amadeus performance validation
amadeus-dlc/amadeus/.kimi-code/skills/amadeus-performance-validation Skill
5★ repoRun the AI-DLC `performance-validation` stage (operation phase) in isolation, without advancing the main workflow. Packages `/amadeus --stage performance-validation --single`: the engine emits one run-stage directive for performance-validation and its gate, the conductor runs it, then the single-stage run commits a synthetic-id pair and stops. The main workflow's Current Stage is never touched.
Ddd cross aggregate constraints
amadeus-dlc/amadeus/amadeus/spaces/default/knowledge/amadeus-shared/software-design/ddd-cross-aggregate-constraints Skill
5★ repoUse when a use case wants to check another aggregate's state before changing the current aggregate. Helps separate true invariants from policies, detect Saga misuse, reason about CQRS/Event Sourcing lookup limits, and decide whether inconsistent data is acceptable. Trigger for cross-aggregate validation, checking another aggregate, command-side read-model access, reverse lookup constraints, or Saga-based validation.
amadeus-dlc/amadeus/amadeus/spaces/default/knowledge/amadeus-shared/software-design/parse-dont-validate Skill
5★ repoUse when replacing validation that discards information with parsing that returns a typed, validated value. Helps enforce invariants through the type system and reduce shotgun parsing. Trigger for validation refactors, type-safe inputs, invalid-state prevention, reducing `Maybe`/nullable checks, or converting validators into constructors/parsers.
Amadeus performance validation
amadeus-dlc/amadeus/dist/claude/.claude/skills/amadeus-performance-validation Skill
5★ repoRun the AI-DLC `performance-validation` stage (operation phase) in isolation, without advancing the main workflow. Packages `/amadeus --stage performance-validation --single`: the engine emits one run-stage directive for performance-validation and its gate, the conductor runs it, then the single-stage run commits a synthetic-id pair and stops. The main workflow's Current Stage is never touched.
Amadeus performance validation
amadeus-dlc/amadeus/dist/codex/.agents/skills/amadeus-performance-validation Skill
5★ repoRun the AI-DLC `performance-validation` stage (operation phase) in isolation, without advancing the main workflow. Packages `/amadeus --stage performance-validation --single`: the engine emits one run-stage directive for performance-validation and its gate, the conductor runs it, then the single-stage run commits a synthetic-id pair and stops. The main workflow's Current Stage is never touched.
Amadeus performance validation
amadeus-dlc/amadeus/dist/kimi/.kimi-code/skills/amadeus-performance-validation Skill
5★ repoRun the AI-DLC `performance-validation` stage (operation phase) in isolation, without advancing the main workflow. Packages `/amadeus --stage performance-validation --single`: the engine emits one run-stage directive for performance-validation and its gate, the conductor runs it, then the single-stage run commits a synthetic-id pair and stops. The main workflow's Current Stage is never touched.
Amadeus performance validation
amadeus-dlc/amadeus/dist/kiro-ide/.kiro/skills/amadeus-performance-validation Skill
5★ repoRun the AI-DLC `performance-validation` stage (operation phase) in isolation, without advancing the main workflow. Packages `/amadeus --stage performance-validation --single`: the engine emits one run-stage directive for performance-validation and its gate, the conductor runs it, then the single-stage run commits a synthetic-id pair and stops. The main workflow's Current Stage is never touched.
Amadeus performance validation
amadeus-dlc/amadeus/dist/kiro/.kiro/skills/amadeus-performance-validation Skill
5★ repoRun the AI-DLC `performance-validation` stage (operation phase) in isolation, without advancing the main workflow. Packages `/amadeus --stage performance-validation --single`: the engine emits one run-stage directive for performance-validation and its gate, the conductor runs it, then the single-stage run commits a synthetic-id pair and stops. The main workflow's Current Stage is never touched.
IvanCampos/agents/skills/git-search Skill
5★ repoList recent git commits across all repos under ~/Code (excluding .build checkouts). Use when the user asks to show last commits, recent history, or commits across all projects in ~/Code.
colinwilliams91/gaitor-orchestrator-cli/packages/cli/templates/skills/checkpoint-commit Skill
5★ repoCreate a deliberate git checkpoint commit from staged or current working changes using a diff-based, model-written Conventional Commit message. Use when you want a clean commit boundary during intensive agentic iteration.
sergeionlyart/minius_codex_lab/.agents/skills/session-memory-handoff Skill
5★ repoНачни, веди и заверши исследовательскую сессию с Git-операционной памятью: branch/worktree, session note, смысловые commits, CURRENT.md и handoff. Используй для параллельных/долгих задач; не используй для одношаговой задачи без durable state и не делай автоматический push.
Destynova2/cli-code-skills/cli-audit-review Skill
5★ repoScored MR/PR/diff review skill calibrated for strict infrastructure and automation changes. Use for merge-request reviews, pull-request reviews, scored reviewer gates, convention compliance, Ansible roles/collections, Molecule, GitLab CI, semantic-release, packaging, Go/Cobra CLIs, PowerShell, shell/Python helpers, Kubernetes/containers, Terraform/OpenTofu, and operator documentation reviewed through a contract -> validation -> execution -> proof -> docs/release methodology. Produces RMI scoring, gate decisions, and reviewer-style actionable comments. For generic code quality, code smells, clean-code compliance, or tech debt audits, use cli-audit-code instead.
Destynova2/cli-code-skills/cli-audit-sync Skill
5★ repoVerify documentation-code coherence: detect stale references, broken links, terminology drift, outdated diagrams, and non-working examples. Use when the user wants to check if docs match reality, detect doc drift, verify README accuracy, find stale documentation, or says 'is my doc up to date', 'check coherence', 'sync docs', 'doc drift', 'stale docs', 'verify documentation'. Also triggers on 'broken links', 'outdated references', 'docs match code'.
Destynova2/cli-code-skills/cli-forge-plume Skill
5★ repoGhostwrite, rewrite, and audit everyday professional exchanges in the user's voice: emails, replies, chat messages (Slack/Teams/Discord), LinkedIn DMs, client and recruiter answers, follow-ups, thank-yous, refusals, bad-news notes, meeting requests, and short announcements. Enforces zero AI tells (no em-dash reflex, no AI vocabulary, no assistant structure), front-loaded asks, one message = one ask, target-language proofreading with correct diacritics, and calibrated light humor for follow-ups. USE BY DEFAULT — even without a trigger word — whenever creating, editing, rewriting, translating, or auditing ANY text the user will send or publish in their name: message, mail, réponse, annonce, petite annonce, post, commentaire, DM, description produit, texte de formulaire. If the task involves producing or modifying user-facing prose, load this skill first. Also triggers on 'écris un mail', 'réponds à', 'relance', 'relance-le', 'follow up', 'reformule ce message', 'humanize this', 'sounds like AI', 'trop formel', 'make this less formal', 'ghostwrite', or when the user pastes an exchange to answer. Do not use for professional identity content like CV/LinkedIn profiles (cli-forge-profile), commit/PR/release text (cli-git-conventional), or project documentation (cli-forge-doc, cli-forge-readme).
Destynova2/cli-code-skills/cli-git-conventional Skill
5★ repoEnforce Conventional Commits v1.0.0, SemVer 2.0.0, branch naming, commit guard, full-directory AI marker audits, and human ghostwriter style on all git/jj operations. Zero AI markers. Use on 'commit', 'branch', 'tag', 'release', 'changelog', 'semver', 'bump version', 'next version', 'CHANGELOG.md', 'audit markers', 'scan AI files', '/ghost', 'not an AI', or 'I'm not an AI'. Also trigger proactively when the user shares code changes without mentioning commit.
gustavo-meilus/superpipelines/.agents/skills/superpipelines/parity-test-f/reviewer-protocol Skill
5★ repoLoaded by the reviewer agent to supply operating protocol and invariants for findings validation in the parity-test-f pipeline. Not user-invocable.
gustavo-meilus/superpipelines/.claude/skills/superpipelines/parity-test-b/reviewer-protocol Skill
5★ repoLoaded by the reviewer agent of parity-test-b to supply its operating protocol. Not user-invocable.
gustavo-meilus/superpipelines/.superpipelines/skills/superpipelines/parity-test-h/reviewer-protocol Skill
5★ repoLoaded by the run-parity-test-h entry skill to supply operating protocol and invariants for false-positive review of validator findings in the parity-test-h pipeline. Not user-invocable.
gustavo-meilus/superpipelines/.superpipelines/skills/superpipelines/parity-test-h/validator-protocol Skill
5★ repoLoaded by the run-parity-test-h entry skill to supply operating protocol and invariants for YAML config validation in the parity-test-h pipeline. Not user-invocable.
Finishing a development branch
gustavo-meilus/superpipelines/plugins/superpipelines/skills/finishing-a-development-branch Skill
5★ repoStructured integration protocol that enforces a test-verification gate and presents branch disposition options (merge, PR, keep, or discard). Use when implementation is complete, all tests pass, and an integration decision for the development branch is pending.
Pipeline quality reviewer protocol
gustavo-meilus/superpipelines/plugins/superpipelines/skills/pipeline-quality-reviewer-protocol Skill
5★ repoLoaded by the pipeline-quality-reviewer agent to perform Stage 2 code-quality review after spec compliance passes.
Pipeline spec reviewer protocol
gustavo-meilus/superpipelines/plugins/superpipelines/skills/pipeline-spec-reviewer-protocol Skill
5★ repoLoaded by the pipeline-spec-reviewer agent to perform Stage 1 spec-compliance review.
gustavo-meilus/superpipelines/plugins/superpipelines/skills/sk-worktree-safety Skill
5★ repoEnforces a mandatory 4-step safety protocol (Ignore, Setup, Baseline, Commit) for creating, managing, and destroying git worktrees in pipeline isolation contexts. Use when a pipeline step declares `isolation: worktree`, when parallel pattern tasks require branch isolation, or when the iterative or spec-driven patterns require atomic rollback capability.
gustavo-meilus/superpipelines/plugins/superpipelines/skills/sk-write-review-isolation Skill
5★ repoEnforces structural separation between the writing agent and the reviewing agent, with Stage 1 (spec compliance) hard-gating Stage 2 (code quality). Use when dispatching a reviewer after a pipeline worker has produced output, when authoring any pipeline step that requires formal verification against a specification, or when implementing a two-stage review loop.
Verification before completion
gustavo-meilus/superpipelines/plugins/superpipelines/skills/verification-before-completion Skill
5★ repoEnforces the Iron Law — no completion claim without fresh verification evidence. Use when an agent is about to claim work is complete, a bug is fixed, or a system state is passing; before committing changes or opening PRs; or after receiving a subagent DONE report that has not been independently verified.
Finishing a development branch
gustavo-meilus/superpipelines/skills/finishing-a-development-branch Skill
5★ repoStructured integration protocol that enforces a test-verification gate and presents branch disposition options (merge, PR, keep, or discard). Use when implementation is complete, all tests pass, and an integration decision for the development branch is pending.
Pipeline quality reviewer protocol
gustavo-meilus/superpipelines/skills/pipeline-quality-reviewer-protocol Skill
5★ repoLoaded by the pipeline-quality-reviewer agent to perform Stage 2 code-quality review after spec compliance passes.
Pipeline spec reviewer protocol
gustavo-meilus/superpipelines/skills/pipeline-spec-reviewer-protocol Skill
5★ repoLoaded by the pipeline-spec-reviewer agent to perform Stage 1 spec-compliance review.
gustavo-meilus/superpipelines/skills/sk-worktree-safety Skill
5★ repoEnforces a mandatory 4-step safety protocol (Ignore, Setup, Baseline, Commit) for creating, managing, and destroying git worktrees in pipeline isolation contexts. Use when a pipeline step declares `isolation: worktree`, when parallel pattern tasks require branch isolation, or when the iterative or spec-driven patterns require atomic rollback capability.
gustavo-meilus/superpipelines/skills/sk-write-review-isolation Skill
5★ repoEnforces structural separation between the writing agent and the reviewing agent, with Stage 1 (spec compliance) hard-gating Stage 2 (code quality). Use when dispatching a reviewer after a pipeline worker has produced output, when authoring any pipeline step that requires formal verification against a specification, or when implementing a two-stage review loop.
Verification before completion
gustavo-meilus/superpipelines/skills/verification-before-completion Skill
5★ repoEnforces the Iron Law — no completion claim without fresh verification evidence. Use when an agent is about to claim work is complete, a bug is fixed, or a system state is passing; before committing changes or opening PRs; or after receiving a subagent DONE report that has not been independently verified.
sergeyklay/.agents/.agents/skills/create-pr Skill
5★ repoUse when asked to create a pull request, open a PR, or submit changes for review. Handles branch verification, change analysis, title and description generation, and gh pr create. Do NOT use for committing, pushing without PR, or reviewing existing PRs
sergeyklay/.agents/.agents/skills/git-commit Skill
5★ repoUse when asked to commit, save, or persist changes to Git. Handles atomic commits, branch safety, Conventional Commits format, and project style matching. Do NOT use for pushing, creating PRs, or branch management beyond safety checks.
sergeyklay/.agents/.agents/skills/research-it Skill
5★ repoInvestigate a technical question with a detective's discipline - gathering evidence from primary sources, cross-referencing independent confirmations, and never accepting the first plausible answer. Use when asked to investigate, research, fact-check, verify, deep-dive, or 'find out the truth' about a technology, claim, system, or behaviour. Also use before any explanation of a real-world system, library, or protocol that depends on external facts. Establishes source priority, scales effort to question complexity, triangulates every implementation claim across at least two independent sources, reports conflicts between sources, and refuses to cite training data as evidence. Do NOT use for opinion questions, code generation independent of external facts, internal refactoring, or trivial lookups the user could do themselves.
sergeyklay/.agents/.agents/skills/review-arch Skill
5★ repoConduct a principal-level architecture review of a system, specification, diagram, or set of design decisions. Use when asked to review an architecture, evaluate a design, assess coupling/cohesion, check for anti-patterns, audit system boundaries, or produce an Architecture Review Board (ARB) style verdict. Also use when someone says 'review this architecture', 'is this design sound', 'what's wrong with this topology', 'evaluate these tradeoffs', or 'audit this system'. Produces a structured verdict organized around critical risks, significant concerns, observations, strengths, and open questions, grounded in evidence from the codebase and cited against established methodology (ATAM, ISO/IEC 25010, documented anti-pattern catalogues). Do NOT use for line-by-line code review, spec-vs-implementation verification, or PR-level correctness checks.
sergeyklay/.agents/.agents/skills/review-impl Skill
5★ repoReview implementation changes for a given task against architectural standards. Use when reviewing a PR, evaluating recently committed code, assessing whether implementation changes are correct and architecturally sound, or when asked to 'review my changes', 'check this implementation', 'review what I built', 'is this PR ready', or 'audit recent commits'. Accepts a task description, task tracker URL, or issue shorthand (owner/repo#123, #123) as input. Produces a structured review with severity-rated findings, code evidence, and a verdict (Block / Request changes / Approve with notes / Approve). Saves the review to .reviews/Review-impl-{slug}.md. Do NOT use for specification review or spec-vs-implementation verification.
sergeyklay/.agents/.agents/skills/review-spec Skill
5★ repoArchitectural review of a specification or design document, performed before implementation begins. Use whenever a spec or design proposal is in scope and the user asks any quality question — even when not phrased explicitly: 'review this spec', 'evaluate this design', 'is this spec implementable', 'is this ready to build', 'check this architecture proposal', 'review the design for feature X', 'is this design sound', 'what's missing from this spec'. Also triggers when a file under `.specs/` is being evaluated without an existing implementation. Do NOT use for verifying an existing implementation against a spec, reviewing a PR or implementation changes, reviewing an existing system's architecture, or security review.
sergeyklay/.agents/.agents/skills/verify-impl Skill
5★ repoForensic audit of an implementation against its authoritative specification. Use whenever a specification document and an implementation are both in scope and the user asks any conformance question - even when not phrased explicitly: 'does this code match the spec', 'verify this implementation', 'check spec conformance', 'audit compliance between design and code', 'is the implementation faithful', 'verify spec coverage', 'audit against requirements', 'spec-vs-code'. Also triggers when a file path under `.specs/` is mentioned alongside an implementation. Do NOT use for general code review, specification design review before implementation begins, security review, or architecture review without a spec document.
sergeyklay/.agents/.agents/skills/writing-plans Skill
5★ repoConvert a technical specification, tracker reference, or feature request into a rigorous, atomic, dependency-ordered implementation plan the coder agent executes step-by-step. Use whenever the output is a Markdown plan file under `.plans/`, or when asked to plan, break down work, sequence implementation phases, turn a spec into actionable tasks, write a roadmap, decompose a feature into phases, or convert a `Spec-*.md` into a `Plan-*.md` artifact. Defines phase structure, output-style rules (WHAT not HOW, signatures only, no language-tagged code fences, symbol references over file paths), step anatomy (atomic, file-explicit, verify-gated), per-phase constraint checks, the philosophy-checklist self-gate, and a validation script. Do NOT use for writing the specification itself, writing implementation code, writing tests, code review, or evaluating an existing plan.
klovaaxel/web-a11y-agent-skills/skills/web-a11y-review Skill
5★ repoReviews frontend changes for accessibility regressions across semantics, keyboard/focus behavior, forms, dynamic updates, styling, ARIA, and tests. Use for pull requests, diffs, audits, and pre-merge sign-off.
IncommensurableHubris/fullstack-director/.agents/skills/05-reviewer Skill
5★ repoVerify the sprint build in isolation - a reviewer spawned FRESH, seeded ONLY with 04's build-handoff + spec-slice paths, checked against the spine's Gherkin + the 02 contract; emits SHIP / FIX REQUIRED / BLOCK + a severity tally + attestation. READ-ONLY: writes only the QA report, attestation, and tests (RED per defect - 05 owns RED, 04 owns GREEN); never edits implementation. Re-derives judgment (EXECUTED/OBSERVED/INFERRED states); SHIP is unreachable while anything is INFERRED or a MUST/P0 REQ is uncovered. A non-amender but honest escalator (code/test to 04, spec to 03, declaration to 00/gate). Use when the user says 'review sprint N', 'verify the build', or 'QA'. Writes docs/quality/qa-report-sprint-NN.md + tests under src/**; never edits src/**, docs/spec/**, docs/architecture/**, or docs/design/**. Do NOT build or fix code - /04-builder. Do NOT refactor - /08-refactor. Do NOT audit security - /07-security. Do NOT plan sprints - /01-planner. Do NOT architect - /03-architect.
IncommensurableHubris/fullstack-director/.agents/skills/06-release Skill
5★ repoShip the verified sprint: the release gate the spine protects, then a verified deploy. GATE FIRST: BLOCKs on a non-SHIP qa-report, an unresolved amendment/[NEEDS CLARIFICATION] marker, src/** drift since review, a failing security verdict, or secret-hygiene failures. Only when clear: SETUP once, then ONE human-approved deploy plan, executed, health/smoke-checked, rolled back on failure. Statuses RELEASED | ROLLED-BACK | FAILED | BLOCKED (RELEASED needs captured evidence). A non-amender: appends no amendment-log row, blocks on them instead. Use when the user says 'release sprint N', 'ship it', 'deploy', or 'go live'. Writes docs/release/release-report-sprint-NN.md + deployment-config.md + a release tag; appends deployment-guardrails.md; never writes src/** or docs/{spec,architecture,design,quality}/**. Do NOT verify/QA - /05-reviewer. Do NOT build/fix code - /04-builder. Do NOT audit security - /07-security. Do NOT resolve amendments - /00-discovery. Do NOT refactor - /08-refactor.