agentsclimarketplace

Review & quality

19,016 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

  • Self verify

    Skydooooog0221/claude-code-skills/self-verify Skill

    no license0★ repo

    学术写作过程中的实时引用核查。对 Claude 刚输出的内容(或用户指定的文本)中的文献引用做存在性验证:作者、年份、标题是否指向一篇真实的 PubMed 文献。定位为写作中的随手抽查,不是全量核查(全量用 ref-verifier)。当用户说"verify 一下""self-verify""核查一下引用""check citations""查一下刚才的引用"时触发。仅显式触发,不自动执行。

  • Thesis critical review

    Skydooooog0221/claude-code-skills/thesis-critical-review Skill

    no license0★ repo

    A collection of Claude Code skills for academic writing and literature work.

  • Code review and quality

    dills122/ai-central/templates/skills/imported/agent-skills/code-review-and-quality Skill

    0★ repo

    Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.

    The same file is in 9 other repositories

  • Git workflow and versioning

    dills122/ai-central/templates/skills/imported/agent-skills/git-workflow-and-versioning Skill

    0★ repo

    Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multiple parallel streams.

    The same file is in 9 other repositories

  • Cavecrew

    dills122/ai-central/templates/skills/imported/caveman/skills/cavecrew Skill

    0★ repo

    Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".

    The same file is in 7 other repositories

  • Caveman commit

    dills122/ai-central/templates/skills/imported/caveman/skills/caveman-commit Skill

    0★ repo

    Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.

    The same file is in 2 other repositories

  • Caveman review

    dills122/ai-central/templates/skills/imported/caveman/skills/caveman-review Skill

    0★ repo

    Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.

    The same file is in 11 other repositories

  • Review

    dills122/ai-central/templates/skills/imported/claude-skills/engineering-team/playwright-pro/skills/review Skill

    0★ repo

    Review Playwright tests for quality. Use when user says "review tests", "check test quality", "audit tests", "improve tests", "test code review", or "playwright best practices check".

    The same file is in 4 other repositories

  • Api design reviewer

    dills122/ai-central/templates/skills/imported/claude-skills/engineering/skills/api-design-reviewer Skill

    0★ repo

    Comprehensive REST API design review with automated linting, breaking-change detection, and design scorecards. Catches inconsistent conventions, missing versioning, and design smells before APIs ship. Use when reviewing a PR that adds or changes API endpoints, auditing an existing API for v2 migration, or establishing API standards for a team.

    The same file is in 1 other repository

  • Lint hunter

    dills122/ai-central/templates/skills/imported/rust-agentic-skills/lint-hunter Skill

    0★ repo

    Debugging compiler errors and tracing lifetimes.

  • Review

    ardellashuddery616/modularity/skills/review Skill

    no license0★ repo

    Analyzes a codebase's modularity imbalances using the Balanced Coupling model and produces a review of design issues. Use when reviewing existing code for coupling problems, assessing architecture quality, identifying distributed monolith risks, or finding areas where changes are unexpectedly expensive.

    The same file is in 1 other repository

  • Energieausweis check

    immoJUMP/immo-agent-skills/skills/energieausweis-check Skill

    no license0★ repo

    Analysiert Energieausweise (Bedarfs-/Verbrauchsausweis), bewertet energetischen Zustand, prueft GEG-2024-Konformitaet und berechnet Wirtschaftlichkeit energetischer Massnahmen (Kosten vs. Mieterhoehung vs. Wertsteigerung). Nutze diesen Skill wenn du einen Energieausweis vorliegen hast.

  • Emdash worktree orchestrator

    riteshkew/yc-skills/skills/emdash-worktree-orchestrator Skill

    0★ repo

    Given a list of coding tasks and a repo base branch, produce a deterministic parallel-agent orchestration plan: git worktree setup commands (one isolated worktree and branch per agent), an assignment table, and teardown commands. Use this skill whenever you need to spin up multiple coding agents in parallel across isolated git worktrees and want a safe, reviewable plan before executing anything.

  • Sonarly incident remediator

    riteshkew/yc-skills/skills/sonarly-incident-remediator Skill

    0★ repo

    Given a log or stack-trace snippet, produce a structured incident remediation plan covering ranked root-cause hypotheses with evidence, ordered fix steps each with a verification check, a rollback plan, and preventive follow-ups.

  • Git flow pro

    ak-ship/fullstack-agent-skills/skills/git-flow-pro Skill

    0★ repo

    Handle git hygiene — write commit messages that explain the why, name branches that match the issue, draft PR descriptions reviewers actually read. Knows Conventional Commits, semantic branch names, and how to break a noisy WIP into clean atomic commits. Use when the user says "commit this", "make a PR", "write the commit message", "draft a PR description", "clean up my branch", "rebase this", or finishes work and wants it shipped.

  • Implement

    specscore/specstudio-skills/skills/implement Skill

    0★ repo

    Turns an approved SpecScore Plan into focused, AC-traceable source-code changes by dispatching one subagent per task in parallel batches computed from the Plan's **Depends-On:** dependency graph. Fires the `implementation.pre_commit` / `implementation.pre_push` reviewer gates at its checkpoints, so per-batch approval is gate-config-driven (a `type: human` reviewer is the human checkpoint; a `auto-approve` gate commits autonomously). Applies publication policy at approved implementation milestones; provides a Verifies: commit-message trailer template. Also accepts a Feature directly (no Plan) or an Idea directly (no Feature or Plan) for single-pass conversational implementation. Trigger: "implement", "/implement", "implement this plan", "specstudio:implement", or event `plan.approved`.

  • Pull request

    specscore/specstudio-skills/skills/pull-request Skill

    0★ repo

    Gate-and-create-one-PR twin of the ship skill. Enforces the project's pre-PR gates on the current branch via the shared reviewer-gates layer, then creates exactly one pull request — built-in git push + gh pr create by default, or a project-configured delegate skill — and emits pull_request.created. It gates, creates one PR, and records; it never merges, deploys, stacks multiple PRs, retries a delegate, or orchestrates. Trigger: "pull-request", "/pull-request", "open a PR", "specstudio:pull-request".

  • Verify

    specscore/specstudio-skills/skills/verify Skill

    0★ repo

    Consumes an approved SpecScore Feature and produces a machine-checkable per-AC verdict report at spec/features/<feature-slug>/_verify/<sha>.md. Walks `git log` for the `Verifies:` commit-message trailer per AC, dispatches one built-in AI subagent per mapped AC (serial, not parallel), aggregates verdicts into a Markdown report opened by a grep-friendly YAML summary block, emits `verify.completed`, and transitions only to `specstudio:recap`. Applies publication policy to the report checkpoint. Trigger: "verify", "/verify", "verify this feature", "specstudio:verify", or the explicit downstream transition from `specstudio:implement`.

  • Grill me

    yanickfischer/zhaw-bsc-latex-claude-skelett/.claude/skills/grill-me Skill

    no license0★ repo

    Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

    The same file is in 3 other repositories

  • Release readiness

    alinafe82/cognitive-deadlift/skills/release-readiness Skill

    0★ repo

    Check release readiness before tagging, publishing, or distributing a skills repo or plugin. Use when preparing a release, version bump, public package update, adapter publication, or handoff that depends on consistent versioning, changelog, adapters, licenses, docs, and make prod-gate. NOT for ordinary feature branches or local-only validation changes.

  • Skill deprecation review

    alinafe82/cognitive-deadlift/skills/skill-deprecation-review Skill

    0★ repo

    Review whether a stale, overlapping, unused, or harmful skill should be kept, merged, renamed, archived, or deleted. Use when a skill overlaps with another, stops matching repo purpose, has weak usage evidence, or creates routing confusion. NOT for adding new skills or for minor edits that keep scope intact.

  • Thinking ledger review

    alinafe82/cognitive-deadlift/skills/thinking-ledger-review Skill

    0★ repo

    Review thinking ledgers for substantive reasoning evidence. Use when accepting a staged or submitted thinking ledger for non-trivial work to check problem, assumptions, alternatives, evidence, verification, tradeoffs, and risk. NOT for checking only whether a ledger file exists or for reviewing unrelated prose docs.

  • Transcript review

    alinafe82/cognitive-deadlift/skills/transcript-review Skill

    0★ repo

    Review real agent transcripts against expected skill behavior. Use when a Codex, Claude, Gemini, or other agent session needs review to see whether the assistant followed the named skill, skipped evidence, overclaimed checks, or exposed a rubric gap. NOT for reviewing source diffs directly or for hypothetical skill design without a transcript.

  • Migration safety check

    amineorion/claude-code-safety-skills/skills/migration-safety-check Skill

    0★ repo

    Review a database migration for safety before it runs against a multi-tenant production database, where one bad migration hits every customer at once. Use when the user writes, edits, or is about to run a migration, or asks whether a schema change is safe.

  • Two tenant verify

    amineorion/claude-code-safety-skills/skills/two-tenant-verify Skill

    0★ repo

    Verify tenant isolation by exercising a data change as a second tenant and confirming the first tenant's data is invisible — in the running app, not just tests. Use after changing data-access code on a multi-tenant SaaS, before merging, or when the user asks to prove isolation holds or test for leaks end to end.

  • Workflow monthly skill audit

    slogsdon/skills-workflows/skills/workflow-monthly-skill-audit Skill

    0★ repo

    Run the monthly Claude Code skill hygiene pipeline — skill-audit (rank skills by usage + quality) → consolidate-memory (prune stale memories) → vault-lint (catch orphans created by deprecated workflows). Use when the 1st of the month rolls around, when the user says "monthly skill audit", "is my context layer healthy", "skill hygiene check", or after deprecating a workflow / removing a skill. Do NOT use for single-skill review (read the SKILL.md directly) or in the same week as the last audit. Output goes to ~/Downloads + Inbox/.

  • Workflow vault weekly

    slogsdon/skills-workflows/skills/workflow-vault-weekly Skill

    0★ repo

    Run the full weekly vault-health pipeline — vault-lint (consistency check) → backlinks (graph repair) → vault-index (rebuild overview) → weekly-signals (deferral / pattern surface) → weekly-learnings (publishable thread surface). Use when /weekly-review is invoked, on Friday afternoons, when the user says "weekly vault review", "audit my vault", "what should I publish this week", or after a week of heavy capture activity. Skips stages whose preconditions aren't met (e.g. weekly-learnings needs ≥3 daily notes from the week).

  • Business idea validator

    GreenSchool-AI/claude-skills/skills/business-idea-validator Skill

    0★ repo

    Validates a small business idea for the Australian market: verdict, ICP, AUD pricing, MVP options, risks, and first steps. Use when someone describes a business idea or asks if it's viable.

  • Discipline check versions

    yli769227-jpg/awesome-claude-code-cn/skills/discipline-check-versions Skill

    0★ repo

    先测炉温再铸剑 —— 涉及语言特性、运行时行为、框架 API 时,先查实际版本,再查文档,再写代码。触发: 即将使用任何具体语言特性 / 运行时 API / 框架方法(Node/Python/Go/Rust/任何 SDK)、即将判定"这个 API 应该这么用"、即将怀疑训练数据里记得的写法时。禁止基于 AI 训练数据的版本假设直接写代码。

  • Check inbox

    markbaindesign/bain-studio/.claude/skills/check-inbox Skill

    no license0★ repo

    Read and process any pending messages in the current project's .claude/inbox/. Surfaces alerts, handoffs, and events from other agents or the studio system. Archives processed messages.

  • Review checklist

    markbaindesign/bain-studio/.claude/skills/review-checklist Skill

    no license0★ repo

    Generate a pre-release QA checklist from CHANGELOG.md. Creates an Asana task (or markdown fallback) with one checkbox per changed item. Pass --walk to run an interactive sign-off session. Failed items go to qa/qa-inbox/.

  • Review spec

    markbaindesign/bain-studio/.claude/skills/review-spec Skill

    no license0★ repo

    Spec candidate review gate. Reads specs from {CONTENT_DIR}/specs/candidates/, scores them against a checklist, and returns a verdict — approve (graduate to project folder), revise (back to drafts with notes), or defer (valid but not now). Run before any spec is cleared for build.

  • Pg pressure test

    talgacapri/pm-os/.claude/skills/pg-pressure-test Skill

    no license0★ repo

    Pressure-test any startup idea, product bet, or new feature with the brutal honesty of a Paul Graham YC application review. Six named passes — Pressure Test the Idea (fatal flaws), Validate the Real Problem (vitamin vs painkiller), Map the Real Competition (current behavior + indirect), Find the First 10 Customers (manual traction plan), Build the MVP in 2 Weeks (riskiest assumption only), and the Brutal Verdict (strong / weak / pivot). Use when the user says "pressure test this idea", "is this a real startup", "would PG fund this", "kill or keep this idea", "is this a vitamin or a painkiller", "what's the riskiest assumption", "find me my first ten customers", "scope an MVP", "brutal feedback on this concept", or pastes a startup idea, feature concept, or one-line pitch. Triggers on `/pg-pressure-test`, `/pressure-test`, `/paul-graham`, `/brutal-verdict`, or any explicit request for PG-style critique.

  • Prd review panel

    talgacapri/pm-os/.claude/skills/prd-review-panel Skill

    no license0★ repo

    Multi-agent PRD review (7 perspectives)

  • Ralph wiggum

    talgacapri/pm-os/.claude/skills/ralph-wiggum Skill

    no license0★ repo

    Devil's advocate PRD/document reviewer with humor and sharp critique

  • Weekly review

    talgacapri/pm-os/.claude/skills/weekly-review Skill

    no license0★ repo

    Review week's progress, meetings, learnings

  • Conventional commits

    jzills/claude-marketplace/plugins/conventional-commits/skills/conventional-commits Skill

    no license0★ repo

    Enforces Conventional Commits message format and branch naming conventions when the user wants to create a branch, make a commit, commit and push, or any combination of git branching/committing tasks. Trigger this skill whenever the user says things like "create a branch", "make a commit", "commit my changes", "commit and push", "create a branch and commit", "branch off and commit", "push this up", "commit everything", "stage and commit", or any variant involving git branch creation or committing. Also trigger when the user describes a change they made and wants it committed, even if they don't use the exact words "commit" or "branch". This skill ensures branch names follow the type/description pattern and commit messages follow the type(scope): description format.

  • Github pr

    jzills/claude-marketplace/plugins/github-pr/skills/github-pr Skill

    no license0★ repo

    Creates GitHub pull requests for the authenticated user using the gh CLI. Use this skill whenever the user wants to open a PR, submit their work for review, push a branch and create a pull request, or says anything like "make a PR", "open a pull request", "create a PR", "submit for review", "push this up and PR it", or "ready to merge". Also trigger when the user has finished a feature or fix and mentions reviewing, merging, or sharing their changes — even if they don't say "pull request" explicitly. This skill handles branch detection, base branch selection, and title/description generation from git history. Creates regular PRs by default; only creates draft PRs when the user explicitly requests it.

  • Prompt reviewer

    jzills/claude-marketplace/plugins/prompt-reviewer/skills/prompt-reviewer Skill

    no license0★ repo

    Review and refine prompts to improve clarity, specificity, token efficiency, and missing context. Use this skill whenever the user hands you a prompt as an artifact and asks for feedback — regardless of the target model (Claude, ChatGPT, Midjourney, system prompts, etc.). Trigger when the user says "review this prompt", "improve my prompt", "refine this prompt", "make this prompt better", "is this prompt clear", "check this system prompt", "optimize this prompt", "fix my prompt", "critique this prompt", or any similar phrasing where a prompt is the subject of review rather than the instruction itself. Supports three modes: default (single-pass), --deep (guided dialogue), --variants (three rewrites). Also trigger when the user uses "--deep" or "--variants" flags alongside a prompt.

  • Python pep8

    jzills/claude-marketplace/plugins/python-pep8/skills/python-pep8 Skill

    no license0★ repo

    Enforce PEP 8 style in Python code. Use this skill whenever the user shows you Python code and asks you to review, lint, format, clean up, or fix style issues — even if they don't say "PEP 8" explicitly. Also trigger when the user asks "is this good Python?", "check my code style", "format this", "clean this up", or "what's wrong with this Python?". Trigger proactively when writing new Python code to ensure it is PEP 8 compliant from the start. Also use when the user asks "what does PEP 8 say about X?", "how should I name this?", or any question about Python style conventions.

  • Repo review

    mickzijdel/dev-hooks/plugins/dev-hooks/skills/repo-review Skill

    0★ repo

    Whole-repository review/audit of an existing or inherited codebase. Use when the user says "review this repository", "audit this codebase", "do a full code review of the repo", "what's wrong with this app", "I just inherited this project", or asks for a multi-axis sweep (e.g. "review for 1. performance 2. code smells 3. structure"). NOT for reviewing a single diff/PR (use the /code-review command) or a one-file change.

  • Commit digest

    mickzijdel/dev-hooks/plugins/thinking-tools/skills/commit-digest Skill

    0★ repo

    Use on a weekly (or on-demand) cadence to review recent commits from tracked external repos (e.g. dotfiles, framework repos) and optionally Atom/RSS feeds, then pull in improvements applicable to the current project. Opens a separate PR for each implementation and logs skipped suggestions to a dedicated branch for searchable, dedup-safe history. Triggers on "check for new ideas", "what changed upstream", "any improvements to pull in from <repo>", "review dotfiles commits", or as a scheduled agent. Companion to weekly-automation-review, which reviews the local repo's own activity.

  • Grill

    mickzijdel/dev-hooks/plugins/thinking-tools/skills/grill Skill

    0★ repo

    Use when a plan, design, or feature idea needs to be interrogated until it is fully specified — the user wants to be interviewed, one question at a time, until every open decision is resolved. Triggers on "grill me", "interview me", "ask me questions about this", "stress-test this plan with me", "help me fully specify this", or before writing a plan/PRD from a still-fuzzy idea — offer to grill first rather than drafting from guesses. Not for generating ideas from scratch (that's brainstorming), third-party critique (that's [[board]]), or failure-mode hunting (that's [[premortem]]).

  • Premortem

    mickzijdel/dev-hooks/plugins/thinking-tools/skills/premortem Skill

    0★ repo

    Use before committing to a non-trivial plan, design, architecture, migration, launch, or irreversible decision — especially when momentum or optimism is high and nobody has named what could go wrong. Triggers when you're about to start executing a plan, when stakes are high or the decision is hard to reverse, or when the user asks to stress-test, pressure-test, or sanity-check an approach. Not for generating ideas (that's brainstorming).

  • Weekly automation review

    mickzijdel/dev-hooks/plugins/thinking-tools/skills/weekly-automation-review Skill

    0★ repo

    Use on a weekly (Monday) cadence, or when asked what repetitive work is worth automating, what to turn into a skill/hook/tool, or to review recent activity for automation opportunities. This is the skill the scheduled Monday remote agent invokes. Triggers on recurring-task review, "what should I automate", and end-of-week/start-of-week retrospectives.

  • Novel review

    chianglianglin/novel-writer/.claude/skills/novel-review Skill

    0★ repo

    Run a four-pass literary review of a chapter — produces a scored editorial report with specific improvement directives, and optionally applies rewrites and saves an improved version.

  • Code review

    Methasit-Pun/ts-ddd-clean-architecture/skills/_shared/code-review Skill

    0★ repo

    Review TypeScript DDD clean architecture code for correctness bugs, layer violations, and simplification opportunities. Trigger when the user says "review this", "check this code", "code review", "what's wrong with this", "is this correct DDD?", "does this follow clean architecture?", or when changes touch domain, application, or infrastructure layers.

  • Security review

    Methasit-Pun/ts-ddd-clean-architecture/skills/_shared/security-review Skill

    0★ repo

    Security review for TypeScript DDD code — OWASP-mapped checks for injection, auth/authz, data exposure, and misconfiguration. Trigger when the user says "security review", "check for vulnerabilities", "is this secure?", "review auth code", or when changes touch authentication, authorization, input handling, external APIs, file uploads, or user-controlled data.

  • Zod express validation

    Methasit-Pun/ts-ddd-clean-architecture/skills/zod-express-validation Skill

    0★ repo

    Runtime request validation with Zod for Express and Socket.IO. Generates TypeScript DTOs via z.infer. Blocks unvalidated data from reaching Use Cases.

  • Nts review project

    juncoding/nextjs-trpc-prisma-starter/skills/nts-review-project Skill

    0★ repo

    Review an existing project scaffolded with nextjs-trpc-prisma-starter against the architectural invariants and patterns. Use this whenever the user wants to audit project conventions, asks 'does this follow our patterns', wants a pre-PR architecture check, suspects drift, is onboarding a new contributor, or invokes /nts-review-project. Runs a mechanical check script for fast objective violations (missing server-only, DB queries in src/app/, Server Actions present, wrong cache primitives), then samples files for judgment calls, then produces a categorized report grouped by severity (must fix / should fix / notes / passing).

  • Clean evasion

    AntonioTimo/skillchecker/examples/clean-evasion Skill

    0★ repo

    Formats measurements and prices with proper Unicode symbols. Benign — a negative test for the NFKC normalization pass.

  • Verify db change

    decebal/curated-claude-skills/skills/stack-agnostic/verify-db-change Skill

    no license0★ repo

    End-to-end verification of a database change (new tables, columns, indexes, writers/projectors) against real Postgres before review or merge. Replaces vibes-only "looks fine" sign-off with a structured proof block — schema applied per tenant, behavioural SQL exercised inside BEGIN…ROLLBACK on the live dev DB, app booted with the new wiring, and migration reversibility proved against a throwaway schema clone. Produces a PR-ready markdown excerpt with real captured output. Use this skill whenever the user asks to verify a migration, test a migration, prove a schema change works, verify a projector / writer / repository, "run any manual test needed to prove completion", or anything that means "show me the database actually works, not just the unit tests". Also use proactively when reviewing a PR that touches migrations or DB writers and the existing description has no real-Postgres proof. Designed for TypeORM + Nest + Postgres monorepos with multi-tenant DBs and Docker-Compose local infra, but the principles apply to any stack with a programmatic migration system.

  • Weekly monday review

    mccarthy606/claude-operator-stack/skills/weekly-monday-review Skill

    no license0★ repo

    Run the operator's Monday 30-minute review across `~/Brain/Projects/*.md`, ranking active projects by needle-mover heuristic and producing the 2-of-N focus pick, the 3 Friday touchpoints, the paused list, and a force-visible flag for any project silent more than 4 days.

  • Scaffold

    Shankulkarni/RN-Lib-Claude/plugins/rn-lib-claude/skills/scaffold Skill

    no license0★ repo

    Use when creating a new React Native library from scratch — sets up create-react-native-library, bob config, TurboModule / Fabric view (New Architecture) or JS-only library, Expo example app, peer deps, ESLint, Prettier, Husky, and Changesets.

  • Fix validator

    mb3rgel-ui/debug-claude-skill/skills/fix-validator Skill

    no license0★ repo

    Verify that a bug fix is complete before closing the bug. Runs the targeted test, runs the full suite, checks for regressions, and updates the bug log. Use after applying a fix in debug-session Step 5.

  • Code review

    GRIDLOCK-NYC/claude-skills/skills/code-review Skill

    0★ repo

    Staged code review — runs tests, extracts intent, dispatches 3 specialist agents (state-enumeration bug detection, project rule compliance, history + regression detection), then verifies findings with type-stratified confidence thresholds. Works on git diff (pre-commit) or PR diff. Use when user says 'code review', 'review this code', 'review changed code', 'review for regressions', 'check for bugs', 'is this good code', 'review what I just wrote'. Do NOT use for plan review (use /plan-review). Do NOT use for security/dead code scanning (use /code-security). Do NOT use for edge case auditing (use /code-edges). Do NOT use for pre-refactor impact analysis (use /code-blast-radius). Do NOT use for style cleanup or simplification (use /code-review).

  • Plan review

    GRIDLOCK-NYC/claude-skills/skills/plan-review Skill

    0★ repo

    Reviews plans from plan mode for real problems, then fixes them. Catches breaking bugs, security holes, over-engineering, and missing steps — but only when grounded in specific evidence. Returns CLEAN when a plan has no issues. Use when user says 'review this plan', 'check my plan', 'plan review', 'is this plan good', 'critique this plan', 'sanity check', 'poke holes in this', 'review my approach', or 'is this a bad idea'. Do NOT use for code review of written code (use simplify). Do NOT use for incident investigation (use postmortem). Do NOT use for generating alternative approaches (use directions).

  • Research critique

    GRIDLOCK-NYC/claude-skills/skills/research-critique Skill

    0★ repo

    Evaluate scientific claims, review manuscripts, assess evidence quality. Bias detection, GRADE assessment, logical fallacy identification, structured peer review reports. Use when user says 'review this paper', 'evaluate this claim', 'peer review', 'is this study valid', 'check the methodology', 'evidence quality', 'critical analysis'. Do NOT use for literature search (use research-search). Do NOT use for code review (use code-review).

  • Update pr

    GRIDLOCK-NYC/claude-skills/skills/update-pr Skill

    0★ repo

    Auto-commit dirty working tree, push feature branch, and create or update the GitHub PR with an auto-generated description. One command to go from uncommitted changes to an up-to-date PR. Use when user says 'update my PR', 'update the PR', 'push and update PR', 'refresh PR', 'sync my PR', 'create a PR', 'open a PR', 'push my changes', 'get my PR up to date', 'rebase and push', 'push to the PR', 'PR update', or 'ship it'. Do NOT use for reviewing PRs, reading PR comments, or merging PRs.

  • Work review

    Jim4546/ai-workflow-skills/work-review Skill

    no license0★ repo

    精简日报(work review):一次扫全当天所有 Claude Code 对话窗口 + 飞书会话 + 今日会议,按大项目聚类,直接产出「王佳玮工作日报_YYYYMMDD」DocxXML,发布到飞书知识库「开发日报」节点并推送到「每日日报组」群。当用户要写精简日报、工作日报精简版、总结今天干了什么并直接出对外汇报稿时使用。触发词:精简日报、写今天的精简日报、工作日报精简版、recap、work review、jjrb。