agentsclimarketplace

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

  • Code review

    Muvon/octomind-tap/skills/code-review Skill

    6★ repo

    Code review checklist and guidelines for giving and receiving constructive feedback on pull requests. Activate when reviewing a PR, preparing code for review, or establishing review standards.

  • Git workflow

    Muvon/octomind-tap/skills/git-workflow Skill

    6★ repo

    Git commit conventions, branch naming, and workflow best practices for clean version history. Activate when committing, branching, rebasing, or reviewing git history.

  • Seo structural audit

    Muvon/octomind-tap/skills/seo-structural-audit Skill

    6★ repo

    Operational playbook for diagnosing the structural and technical layer of a site or page: crawlability (robots.txt), indexability (meta robots, canonicals), sitemap.xml validity, redirect chains, JSON-LD schema validation, Core Web Vitals interpretation, hreflang, JS-render parity, URL architecture, and internal-link topology. Encodes the fetch protocol (parallel webfetch + shell curl), the per-surface check rubric, the severity matrix (Critical / Moderate / Minor), and the unverified-check escalation rule. Use when auditing the technical layer of a URL, sitemap, or site. Output: prioritized structural findings with evidence and fix direction.

  • Db migration review

    ldilov/harness-forge/skills/db-migration-review Skill

    6★ repo

    review database migrations for safety, compatibility windows, backfills, reversibility, and rollout risk. use when migration files, schema diffs, orm model changes, indexes, constraints, or data backfills change.

  • Hforge review

    ldilov/harness-forge/skills/hforge-review Skill

    6★ repo

    runtime health review for harness forge workspaces. use when the user wants drift checks, decision coverage, stale task review, managed-surface integrity, or a clear pass-fail summary of the current runtime state.

  • Speckit git commit

    ldilov/harness-forge/.agents/skills/speckit-git-commit Skill

    6★ repo

    Auto-commit changes after a Spec Kit command completes

  • Speckit git feature

    ldilov/harness-forge/.agents/skills/speckit-git-feature Skill

    6★ repo

    Create a feature branch with sequential or timestamp numbering

  • Speckit git initialize

    ldilov/harness-forge/.agents/skills/speckit-git-initialize Skill

    6★ repo

    Initialize a Git repository with an initial commit

  • Speckit git remote

    ldilov/harness-forge/.agents/skills/speckit-git-remote Skill

    6★ repo

    Detect Git remote URL for GitHub integration

  • Speckit git validate

    ldilov/harness-forge/.agents/skills/speckit-git-validate Skill

    6★ repo

    Validate current branch follows feature branch naming conventions

  • Gitleaks

    jph4cks/redhound-arsenal/gitleaks Skill

    6★ repo

    Operate and configure Gitleaks — a SAST/secret-detection tool that scans git repositories, commit histories, and staged changes for leaked credentials, API keys, tokens, and private keys. Use when working with gitleaks/gitleaks, when the user needs to audit a repository for secrets, set up pre-commit hooks, integrate into CI/CD pipelines, write custom detection rules, or establish baselines to suppress known findings. Covers installation, detect/protect modes, .gitleaks.toml configuration, custom rules, allowlists, output formats, and CI/CD integration.

  • Playwright camera mask testing

    simiancraft/simiancraft-skills/skills/playwright-camera-mask-testing Skill

    6★ repo

    Specialization of playwright-harness for CAMERA / segmentation testing in the browser: put a real PERSON in front of getUserMedia so MediaPipe / selfie segmentation produces an actual mask, then verify background-replacement / blur / shader effects by vision. Use when the task is "test the mask on web", "verify segmentation in the browser", "feed the camera a person fixture", "check a camera/background effect in Chrome", or any time a web app must SEE a human through the webcam without physical hardware. Read playwright-harness FIRST for script conventions and execution; this skill only adds the camera-feed pieces. The web analog of android-emulator-mask-testing. Validated on Linux/WSL, headless Chromium, against MediaPipe Selfie Segmentation.

  • Gh set active project

    yu-iskw/github-project-skills/skills/gh-set-active-project Skill

    no license6★ repo

    Sets the active GitHub project and repository context by writing a repo-level config file at .github/project-config.json. Run once per repository to eliminate repeated context verification prompts and share the context with all team members via git. All subsequent agent sessions will auto-verify silently against this config.

  • Write agent handoff

    Daaaaave/agentic-workspace-core/payload/.agents/skills/write-agent-handoff Skill

    6★ repo

    Use when temporary task state, delegation payload, cold-start resume packet, review/debug brief, or compaction snapshot must be handed to another agent, workspace, subagent, reviewer, or future session. Do not use for durable project facts, raw transcript dumps, or ordinary same-session status summaries.

  • Validation orchestrator

    LuckyOneTwoThree/pm-skill/pm-03-design/orchestrators/validation-orchestrator Skill

    no license6★ repo

    当需要验证产品方案时使用。方案验证子模块指挥官,调度子Skill:validation-assumption-map、validation-mvp、validation-experiment、validation-usability。关键词:方案验证、假设验证、MVP、可用性测试、实验设计、假设地图、风险评估、验证想法、最小可行产品。

  • Validation assumption map

    LuckyOneTwoThree/pm-skill/pm-03-design/skills/validation-assumption-map Skill

    no license6★ repo

    当需要提取和评估产品假设时使用。假设地图自动生成工具,根据方案设计和PRD,自动提取价值假设、可行性假设、可用性假设、增长假设,并进行风险评估和验证方法推荐。关键词:假设提取、风险评估、假设地图、验证方法、假设梳理、风险假设。

  • Validation experiment

    LuckyOneTwoThree/pm-skill/pm-03-design/skills/validation-experiment Skill

    no license6★ repo

    当需要设计验证实验方案时使用。验证实验自动设计工具,根据假设地图和MVP范围,智能选择验证方法并设计实验方案,包括A/B测试和可用性测试的参数设计。关键词:实验设计、A/B测试、样本量、验证方法、验证方案、测试设计。

  • Validation mvp

    LuckyOneTwoThree/pm-skill/pm-03-design/skills/validation-mvp Skill

    no license6★ repo

    当需要界定MVP功能范围时使用。MVP范围自动界定工具,基于假设地图和资源约束,智能识别Must Have、MUST NOT和Nice to Have功能,并评估MVP规模占比。关键词:MVP范围、最小可行产品、功能优先级、资源约束、最小产品、核心功能。

  • Validation usability

    LuckyOneTwoThree/pm-skill/pm-03-design/skills/validation-usability Skill

    no license6★ repo

    当需要辅助可用性测试时使用。可用性测试辅助工具,在测试前、中、后各阶段提供AI辅助支持:测试前生成任务脚本和招募问卷,测试后整理数据并生成洞察报告。注意:实际测试执行必须由人类研究员主持。关键词:可用性测试、任务脚本、招募筛选、问题聚类、洞察提炼、用户体验测试、测试任务。

  • Agile review

    LuckyOneTwoThree/pm-skill/pm-08-project/skills/agile-review Skill

    no license6★ repo

    当需要自动化Sprint评审和复盘报告时使用。Sprint评审与复盘报告一体化,Step 1完成Sprint评审(产出清单整理、Demo准备清单、反馈收集分类、数据收集、问题识别、改进建议生成),Step 2生成完整复盘报告(Sprint目标达成分析、交付质量评估、团队速率趋势、改进行动项、下一Sprint建议),Step 3完成上线复盘(效果复盘、工程质量复盘、过程复盘、改进行动项生成)。关键词:Sprint Review、Sprint Retro、迭代评审、迭代回顾、敏捷复盘、评审会、复盘报告、Sprint复盘、改进行动项、做得怎么样、上线复盘、发布复盘、效果评估、持续改进。

  • External review workflow

    ucsahinn/codex-chef/plugins/codex-chef-workflows/skills/external-review-workflow Skill

    6★ repo

    Prepare a secret-safe, hash-pinned repository snapshot for manual review by an external model, generate a local handoff contract, and verify returned structured findings against the live repository without automatic upload or external execution.

  • Agent front design

    northseadl/norix-skills/agent-front-design Skill

    no license6★ repo

    Frontend design blueprints with craftsmanship scoring, self-critique loops, and engineering handoff. Aesthetic intelligence against AI homogeneity. Use for: UI/UX design specs, design system creation, visual direction exploration, component design review, design-to-engineering handoff.

  • Ultra review

    keithhegit/ultra-orchestration/skills-vnext/ultra-review Skill

    6★ repo

    Spec and engineering review for Codex Ultra vNext. Use after planning or implementation to check specification fidelity, evidence quality, constraints compliance, regression risk, and whether work should be accepted, rejected back to execution, or escalated back to planning.

  • Code review

    keithhegit/ultra-orchestration/skills/code-review Skill

    6★ repo

    Review implementation results for production bugs, regressions, risk, evidence quality, and missing tests before integration. Use after code changes or when validating a worker result against acceptance criteria.

  • Qa verify

    keithhegit/ultra-orchestration/skills/qa-verify Skill

    6★ repo

    Run scenario-based verification and regression checks for changed behavior, user flows, and bug fixes before delivery. Use after implementation or review whenever behavior changed or user-visible quality matters.

  • Safety guard

    keithhegit/ultra-orchestration/skills/safety-guard Skill

    6★ repo

    Apply careful, freeze, and guard behaviors to dangerous commands, broad edit scope, and high-impact operations. Use when execution needs command warnings, path restrictions, or combined safety guardrails.

  • Spec review

    keithhegit/ultra-orchestration/skills/spec-review Skill

    6★ repo

    Review plans and work packages for specification completeness, hidden assumptions, dependency gaps, interface risks, and acceptance-check quality. Use after planning and before substantial implementation.

  • Gh actionlint

    Unique-Divine/jiyuu/ai-skills/gh-actionlint Skill

    6★ repo

    Validate GitHub Actions workflow YAML with actionlint when editing files under `.github/workflows/`, checking CI workflow syntax, diagnosing GitHub Actions expression or schema errors, or when the user asks to lint/check Actions workflows. Prefer `bunx github-actionlint` when `bun` is available and fall back to `npx --yes github-actionlint`; use this proactively after modifying GitHub Actions workflows.

  • Gh pr review

    Unique-Divine/jiyuu/ai-skills/gh-pr-review Skill

    6★ repo

    Review GitHub pull requests for correctness, design quality, test coverage, security, performance, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".

  • Gh pr

    Unique-Divine/jiyuu/ai-skills/gh-pr Skill

    6★ repo

    Writes clear pull request descriptions from the current branch diff against a base branch. Defaults to `main`, but supports `dev` or any other user-specified comparison branch. Use when the user asks for a PR description, pull request summary, or a markdown write-up for changes against a base branch.

  • Code reviewer

    HK-hub/AgentSkills/code-reviewer Skill

    6★ repo

    精选 Claude Code , Open Code等Agent Skills 合集,覆盖 Agent/Skill 工程化、后端架构、事件驱动、CI/CD、前端设计、文档办公自动化与可视化创作

    The same file is in 3 other repositories

  • Critique

    HK-hub/AgentSkills/critique Skill

    6★ repo

    Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.

  • Minimax docx

    HK-hub/AgentSkills/minimax-docx Skill

    6★ repo

    Professional DOCX document creation, editing, and formatting using OpenXML SDK (.NET). Three pipelines: (A) create new documents from scratch, (B) fill/edit content in existing documents, (C) apply template formatting with XSD validation gate-check. MUST use this skill whenever the user wants to produce, modify, or format a Word document — including when they say "write a report", "draft a proposal", "make a contract", "fill in this form", "reformat to match this template", or any task whose final output is a .docx file. Even if the user doesn't mention "docx" explicitly, if the task implies a printable/formal document, use this skill.

    The same file is in 7 other repositories

  • Api contract review

    Mozurok/fhorja.dev/.claude/skills/api-contract-review Skill

    6★ repo

    Review an API contract (endpoints, request/response shapes, error codes, auth model) BEFORE implementation for naming consistency, versioning, pagination, idempotency, and alignment with existing endpoints. Distinct from review-hard (post-implementation risk) and repo-consistency-sweep (pattern matching on written code). Use when designing new endpoints or modifying existing API contracts. Do not use when the API is already implemented (use review-hard or repo-consistency-sweep instead).

  • App runtime verify

    Mozurok/fhorja.dev/.claude/skills/app-runtime-verify Skill

    6★ repo

    Verify a built mobile or app runtime at runtime: run the app (device, emulator, or headless), read the captured runtime output (native logcat, iOS device log, or the Metro/JS console), classify any runtime errors against a per-stack taxonomy, and decide a PASS/FAIL runtime gate for the slice's acceptance behavior. The run's real output IS the Layer-1 runtime evidence (ADR-0048); a claimed-but-not-shown run is unverified. Capability-routed and MCP-agnostic about how the app is run; React Native/Expo (logcat plus Metro) is the first documented adapter. It verifies and routes fixes, it does not apply them. Use after an app slice is implemented to gate runtime behavior the static checks (typecheck, lint) cannot catch. Do not use to plan a screen (use implementation-plan), to write or fix code (use implement-approved-slice), to triage a failure into a fix size (use incident-triage), to verify a Godot scene (use godot-runtime-verify), or with no implemented app to run.

  • Approve plan

    Mozurok/fhorja.dev/.claude/skills/approve-plan Skill

    6★ repo

    Atomically lock IMPLEMENTATION_PLAN.md as the approved execution baseline and stamp TASK_STATE.md with the approval signal. Symmetric counterpart to approve-proposed but for the plan itself, not for arbitrary PROPOSED artifacts. Use when IMPLEMENTATION_PLAN.md has been produced (or revised via self-critique-and-revise) and the user authorizes execution to begin. Do not use when the plan is still draft, when implementation-plan returned NO_OP, when the plan contains [NEEDS CLARIFICATION:] markers, or when revisions are still pending review.

  • Branch commit

    Mozurok/fhorja.dev/.claude/skills/branch-commit Skill

    6★ repo

    Return a branch name and a concise commit message (at most 2 lines) for the current task, grounded in the real `git diff` rather than a paraphrase of the task summary. Use when the user only needs quick branch and commit naming right before committing, full PR packaging is unnecessary, and there is a real inspectable diff (staged or unstaged changes, or a branch diff vs an integration base). Do not use when the task needs a complete PR package (use pr-package), there is no diff yet (naming a branch from a task summary alone is the failure mode this command exists to avoid; ask the user to stage at least one change first), or the diff is still too unclear to summarize safely.

  • Design spec review

    Mozurok/fhorja.dev/.claude/skills/design-spec-review Skill

    6★ repo

    Review a component or screen implementation against its spec doc for alignment on variants, states, accessibility, tokens, and visual fidelity. Distinct from review-hard (general risk) and repo-consistency-sweep (pattern matching). Activates when a slice's declared Scope touches a design-system button, icon, or component convention file (a shared atom/component under a design-system package) with no cited design-spec-review pass for that change. Use when a design system component or screen has been implemented and you want to verify it matches the documented spec. Do not use when no spec exists (write one first with component-spec or screen-spec).

  • Feature library scout fleet

    Mozurok/fhorja.dev/.claude/skills/feature-library-scout-fleet Skill

    6★ repo

    Orchestrator-workers variant of feature-library-scout for deep per-feature-problem library research. The orchestrator derives the feature-problem list and dispatches one Sonnet worker per problem; each worker ranks candidate libraries by adoption signal (registry downloads, dependents, last release, stars and trend, maintenance, framework/platform fit) relative to the project's ecosystem, grounded in captured REFERENCES.md sources, and returns a typed payload via StructuredOutput; the orchestrator is the sole writer that merges into one FEATURE_LIBRARIES.md and runs the orphan-scan gate (ADR-0038, ADR-0045). Stack-agnostic (npm, PyPI, crates.io, Go, Maven). Use when the product has 3 or more distinct feature problems that each warrant a deep multi-angle read. Do not use for 1-3 problems (use feature-library-scout inline), to pick stack layers (use stack-recommend), to verify framework pattern currency (use stack-currency-check), or with no active task folder (run task-init first).

  • Feature library scout

    Mozurok/fhorja.dev/.claude/skills/feature-library-scout Skill

    6★ repo

    Research and recommend community-vetted best-in-class libraries for each feature problem in the product (lists, camera, forms, keyboard, sheets), ranked by adoption signal (downloads, dependents, recency, stars-trend, maintenance, platform fit) relative to the project's ecosystem. Stack-agnostic across registries (npm, PyPI, crates.io, Go, Maven). Researches five angles (web, repo, registry, AAA practices, reference repos) and writes FEATURE_LIBRARIES.md, grounding every pick in a captured REFERENCES.md source; picks are optional guidance. Use when the stack is chosen and you want the canonical per-feature libraries surfaced and vetted. Do not use to pick stack layers (use stack-recommend), to verify a framework's current patterns (use stack-currency-check), to synthesize already-captured sources (use external-research), or with no active task folder (run task-init first). For a deep per-problem sweep, use feature-library-scout-fleet.

  • Frontend architecture review

    Mozurok/fhorja.dev/.claude/skills/frontend-architecture-review Skill

    6★ repo

    Review a frontend architecture at scale and gate micro-frontend adoption BEFORE building. The first step is an adopt-or-don't-adopt decision (default: you probably do not need micro-frontends; prefer a modular monolith until 3 or more independently deploying teams and real coordination pain exist), then a checklist covering team-and-domain boundaries, independent deployability, governed shared dependencies, design-system sharing, runtime isolation, cross-app communication, routing and composition tier, rendering strategy, state at scale, a performance budget across the composition, and governance and failure handling. Capability-routed, not stack-locked. Use when reviewing a frontend architecture, evaluating whether to adopt micro-frontends, or hardening a multi-team frontend before it scales. Do not use to design one system (use frontend-system-design), to review a GraphQL or REST contract (use graphql-contract-review or api-contract-review), or with no active task folder (run task-init first).

  • Godot runtime verify

    Mozurok/fhorja.dev/.claude/skills/godot-runtime-verify Skill

    6★ repo

    Verify a built Godot 2D scene at runtime: run the scene (press-play or headless), read the captured debugger output, classify any runtime errors against a Godot-specific taxonomy, and decide a PASS/FAIL runtime gate for the slice's acceptance behavior. The run's real output IS the Layer-1 runtime evidence (ADR-0048); a claimed-but-not-shown run is unverified. MCP-agnostic about how the scene is run; it verifies and routes fixes, it does not apply them. Use after a Godot slice is implemented to gate runtime behavior the static checks (lint, typecheck) cannot catch. Do not use to plan a scene (use godot-scene-plan), to write or fix the code (use implement-approved-slice or implement-slice-complement), to triage a failure into a fix size (use incident-triage), or with no implemented scene to run.

  • Graphql contract review

    Mozurok/fhorja.dev/.claude/skills/graphql-contract-review Skill

    6★ repo

    Review a GraphQL schema and a Backend-for-Frontend (BFF) contract BEFORE implementation, against a GraphQL-specific checklist: schema shape and nullability (null-bubbling), errors-as-data unions, N+1 and DataLoader, query cost and depth limits, cursor-connection pagination, federation entity ownership, breaking-change gate (schema checks), auth layering and BFF token posture, BFF thinness, and partial-failure degradation. Distinct from api-contract-review (REST and HTTP) and review-hard (post-implementation risk). Capability-routed, not stack-locked. Use when designing a new GraphQL schema, a federated subgraph, or a BFF contract, or modifying an existing one. Do not use for a REST contract (use api-contract-review), when the schema is already implemented (use review-hard or repo-consistency-sweep), or with no active task folder (run task-init first).

  • Portfolio review

    Mozurok/fhorja.dev/.claude/skills/portfolio-review Skill

    6★ repo

    Read-only cross-task board across every active task in all projects. Runs scripts/portfolio-review.sh to classify each active task as done-unclosed, blocked, my-move, stale, or in-flight, then renders one ranked board with a single recommended next action per row, so picking the next thread and catching finished-but-unarchived tasks stop depending on memory. An --outcomes mode reports closed-task outcome telemetry (merge status, cycle time) instead of the live board. Use when you have many concurrent active tasks and want a portfolio-level view of whose move it is and what has gone quiet, when deciding which task to pick up next, or when sweeping for tasks that should be closed. Do not use for routing inside a single active task (use what-next), for a deep checkpoint of one task (use where-we-at), or to change any task's state (this command never writes).

  • Post deploy verifier

    Mozurok/fhorja.dev/.claude/skills/post-deploy-verifier Skill

    6★ repo

    Senior reliability engineer producing a per-slice post-deploy verification plan mapping each acceptance criterion to a concrete live signal (exact log query, dashboard panel, smoke-test walkthrough, flag check, DB invariant query) plus negative checks and rollback trigger checklist. Activates when TASK_STATE.md ## Current phase is delivery or review after a deploy event without a paired plan, when branch-commit produced a deploy without a ## Post-deploy checks section, when slice-closure is about to close a slice without one, or when IMPLEMENTATION_PLAN.md ### Slice N is implemented (pending closure) without a verification block. Do not use BEFORE the slice ships (use verify-against-rubric for pre-deploy verdicts against a locked rubric), for documentation-only slices, when verification is already authored and the deploy diff is unchanged, or when no infra-free signal (smoke test, DB query, flag check) exists for any criterion; an empty observability inventory alone degrades per ADR-0102 instead of blocking.

  • Post review pivot

    Mozurok/fhorja.dev/.claude/skills/post-review-pivot Skill

    6★ repo

    Capture what a PR or team review changed about the intended behavior or approach, separate keep vs revert/replace, and produce the smallest safe set of updates to task memory and follow-on work. Does not implement product code. Use when a PR or team feedback requests a meaningful direction change (wrong fields, wrong migrations, wrong integration shape), you must keep core logic but change data contracts/schema steps/supporting code in a coordinated way, or you need a structured pivot digest before rewriting plan or slices. Do not use when feedback is primarily corrective under the existing contract (use pr-feedback-ingest), there is no concrete review or team signal yet, the change is a trivial fix inside the same approved contract (use implement-approved-slice), only task-memory drift exists (use state-reconcile or sync-task-state), the pivot is actually new unrelated work (start a new task per the Fhorja task lifecycle), or no active task folder exists yet.

  • Pr package

    Mozurok/fhorja.dev/.claude/skills/pr-package Skill

    6★ repo

    Prepare a clean delivery package for GitHub from the real git diff vs an explicit base branch, persisted as PR_PACKAGE.md (or PR_PACKAGE.<repo>.md for multi-repo tasks). Produces branch name, commit messages, fetch, checkout, add, commit, and push commands, PR title and body, and reviewer attention points; never invents work outside the diff. Per-repo when SOURCE_OF_TRUTH.md has a Repositories section. Use when the task is ready for delivery, scope is complete enough for PR preparation, there is a real inspectable diff against an explicit base branch, and that diff is stable. Do not use during active implementation, when blockers or unresolved contract issues remain, when the diff is still changing rapidly, when you only need a quick branch and commit name (use branch-commit), when the trigger is review feedback (use pr-feedback-ingest or post-review-pivot), or when the need is only slice closure (use slice-closure). After the draft, use self-critique-and-revise before delivery.

  • Repo consistency sweep

    Mozurok/fhorja.dev/.claude/skills/repo-consistency-sweep Skill

    6★ repo

    Proactive defect-class detection that handles the lower-value half of code review (per Bacchelli and Bird 2013) so human reviewers stay focused on design, intent, and knowledge transfer. Catches convention drift, ordering bugs, type-safety gaps, security and multi-tenant invariants (CWE-grounded), and operability issues against a curated bug-class library before PR packaging. Runs after review-hard, before pr-package. Reduces what external review systems (Greptile, CI) catch and grows its detection library from declined and applied user feedback over time. Use when at least one slice is implemented and you want a proactive codebase-consistency check before PR packaging. Do not use when no implementation has happened yet, the task is still in planning, or the goal is design review (use review-hard for that).

  • Review hard

    Mozurok/fhorja.dev/.claude/skills/review-hard Skill

    6★ repo

    Review the current task changes for real correctness, safety, and maintainability risks before slice closure or PR prep, and recommend the smallest safe next step. Surfaces meaningful issues (not cosmetic feedback); not a replacement for external review systems. Returns no-op when the review would not materially change conclusions. Use when a slice or task-level implementation was completed, the user wants a focused engineering risk review before closure or PR prep, or the current need is to surface meaningful issues. Do not use when no meaningful implementation has happened yet, the task is still in discovery or contract refinement or planning, or the goal is full external code review replacement rather than a focused internal risk check. Supports an opt-in `--consistency N` consensus mode (off by default) that runs N independent review passes over the same changes and merges them by consensus, per ADR-0073.

  • Security review

    Mozurok/fhorja.dev/.claude/skills/security-review Skill

    6★ repo

    Dedicated security review of the current task changes covering threat modeling, OWASP ASVS L1 checklist pass, auth/authz flow tracing, and dependency/secret scanning reminders. Distinct from review-hard (general risk) and repo-consistency-sweep (pattern matching). Activates when DECISIONS.md, IMPLEMENTATION_PLAN.md, or TASK_STATE.md's Active files in scope names an auth or biometric-scoped change without a completed security-review for that scope. Use when the task touches authentication, authorization, public endpoints, PII handling, crypto, or external integrations. Do not use when no implementation has happened yet or the task has no security surface (pure documentation, internal tooling with no user data). Supports an opt-in `--consistency N` consensus mode (off by default) that runs N independent review passes over the same diff and merges them by consensus, per ADR-0073.

  • Self critique and revise

    Mozurok/fhorja.dev/.claude/skills/self-critique-and-revise Skill

    6★ repo

    Take a draft artifact (IMPLEMENTATION_PLAN.md, SLICES/*.md, or PR_PACKAGE.md), run a structured critique against a locked per-artifact-type rubric, and produce a revised draft. Evaluator-optimizer pattern per ADR-0021. PROPOSED-by-default in Plan mode; user reviews critique AND revision before APPLIED. Distinct from review-hard (judges; no revision), direction-adjust (D-N entry; no artifact revision), and post-review-pivot (external feedback; not self-critique). Use when a draft artifact has just been written and a single-pass critique + revision is cheaper than running the upstream command again. Do not use when the artifact is not in the locked set (commands/, TASK_STATE.md, DECISIONS.md), when the issue is operational state not draft quality (use sync-task-state or state-reconcile), when external feedback drives the change (use pr-feedback-ingest or post-review-pivot), or when the artifact has not been drafted yet (run the authoring command first).

  • Stack currency check

    Mozurok/fhorja.dev/.claude/skills/stack-currency-check Skill

    6★ repo

    Verify that the patterns the model is about to use for a given framework+version are current per official docs, and cache the result as CURRENT_PATTERNS.md at the project level. Prevents the "gold-standard audit" anti-pattern where training-data defaults ship outdated patterns (e.g. Supabase getSession when getUser is current, sequential await when Promise.all is recommended). Use when impact-analysis flags greenfield work in an established framework, when starting a new project with frameworks released or updated after the model's training cutoff, or when an existing CURRENT_PATTERNS.md is stale (>30 days). Do not use when working incrementally on an established codebase with clear internal precedent, when the question is about choosing the stack itself (use stack-recommend), or when fetching an arbitrary URL (use capture-references).

  • State reconcile

    Mozurok/fhorja.dev/.claude/skills/state-reconcile Skill

    6★ repo

    Detect drift between TASK_STATE.md, other task-memory artifacts, and observable reality (code, tests, diff when provided), then propose the minimum set of updates so operational memory is trustworthy again. Use when TASK_STATE.md is stale or internally inconsistent after many edits, IMPLEMENTATION_PLAN.md or SLICES/*.md or slice status disagree with each other or with what was actually done, you need a full cross-check before trusting routing or before delivery prep, or the user explicitly wants a one-shot "repair state" pass. Also runs an opt-in read-only memory-lint mode that reports memory-hygiene issues (dead cross-links, orphaned slice files, stale facts) without writing. Do not use with no active task folder (run task-init first), when a small incremental update fits (use sync-task-state), when the need is fast routing on trusted artifacts (use what-next or resume-from-state), or for broad product discovery.

  • Task workspace

    Mozurok/fhorja.dev/.claude/skills/task-workspace Skill

    6★ repo

    Provision, report, or attach a dedicated git worktree and branch for the active task on a git-backed project, so multiple tasks run in parallel on one repository without colliding on a single working tree. Opt-in and git-gated: a non-git project or an un-opted task is a no-op. Records the worktree path and task branch in SOURCE_OF_TRUTH.md and runs standalone to retrofit a task already in progress. Use when a task needs an isolated working tree and branch, or to attach one to an in-flight task. Do not use for the ephemeral slice-level worktrees implement-fleet already manages, for a non-git project, or to close the whole task (task-close owns teardown).

  • Verify against rubric fleet

    Mozurok/fhorja.dev/.claude/skills/verify-against-rubric-fleet Skill

    6★ repo

    Orchestrator-workers generalization of verify-against-rubric to N=many artifacts against ONE locked rubric. Dispatches N stateless Sonnet sub-agents in parallel; each receives ONE artifact + the SAME rubric + read-only tools (no TASK_STATE, no DECISIONS, no prior history); returns structured per-criterion verdict. Orchestrator merges into VERIFICATION_LOG.md with aggregate pass/fail counts + failure clustering (which criteria fail most often across the cohort -> likely system-level signal). Use when N >= 4 artifacts share one rubric (multi-slice retrospective, batch PR review, cohort spec audit). Do not use for single artifacts (use verify-against-rubric), when rubrics differ per artifact (run separately or refactor the rubric first), or on LOW/MEDIUM complexity slices (use self-critique-and-revise).

  • Verify against rubric

    Mozurok/fhorja.dev/.claude/skills/verify-against-rubric Skill

    6★ repo

    Spawn a stateless sub-agent (Claude Code Task tool, Cursor agent mode, or equivalent) with ONLY the artifact path plus the locked rubric plus read-only tools. Sub-agent returns a structured verdict (satisfied, needs_revision, or failed) plus per-criterion feedback. Distinct from self-critique-and-revise (same-context; rewrites in place). Use after pr-package, contract-signoff, or implement-approved-slice on HIGH-complexity slices when independent verification matters more than throughput. Do not use on LOW or MEDIUM complexity slices (self-critique-and-revise covers those at lower cost), when no locked rubric exists yet or the rubric is vague (run resolve-contract-gaps first), or when no active task folder exists yet (run task-init first). For 4 or more artifacts against one rubric, use verify-against-rubric-fleet.

  • Web runtime verify

    Mozurok/fhorja.dev/.claude/skills/web-runtime-verify Skill

    6★ repo

    Verify a built web or static frontend at runtime: serve the build on an ephemeral free port, assert page identity FIRST (automatic recovery on a collision or stale server), run the web battery (overflow 320 to 2560, keyboard and focus, console errors, Lighthouse and axe when available), and decide a PASS/FAIL/BLOCKED runtime gate. The run's real output IS the Layer-1 evidence (ADR-0048); a claimed-but-not-shown run is unverified. Capability-routed and MCP-agnostic; serving mechanics live in wos/frontend-preview-and-experience-verdict.md (ADR-0099), referenced never duplicated. It verifies and routes fixes, it does not apply them. Use after a web slice is implemented to gate runtime behavior the static checks cannot catch. Do not use to plan a page (implementation-plan), to write or fix code (implement-approved-slice), to record the HUMAN experience verdict (the ADR-0091 floor), for numeric perf budgets (performance-budget), for Godot or mobile (the sibling verify commands), or with no built frontend to serve.

  • Post deploy verifier

    Mozurok/fhorja.dev/commands/post-deploy-verifier Skill

    6★ repo

    Senior reliability engineer producing a per-slice post-deploy verification plan mapping each acceptance criterion to a concrete live signal (exact log query, dashboard panel, smoke-test walkthrough, flag check, DB invariant query) plus negative checks and rollback trigger checklist. Activates when TASK_STATE.md ## Current phase is delivery or review after a deploy event without a paired plan, when branch-commit produced a deploy without a ## Post-deploy checks section, when slice-closure is about to close a slice without one, or when IMPLEMENTATION_PLAN.md ### Slice N is implemented (pending closure) without a verification block. Do not use BEFORE the slice ships (use verify-against-rubric for pre-deploy verdicts against a locked rubric), for documentation-only slices, when verification is already authored and the deploy diff is unchanged, or when no infra-free signal (smoke test, DB query, flag check) exists for any criterion; an empty observability inventory alone degrades per ADR-0102 instead of blocking.

  • Review animations

    sarveshsea/design-skills/skills/review-animations Skill

    6★ repo

    Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.

  • Receiving code review

    dolutech/dolu-agents-skills/skills/receiving-code-review Skill

    6★ repo

    Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

    The same file is in 28 other repositories