agentsclimarketplace

Review & quality

19,000 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

  • Prototype

    bingelp/skills/skills/prototype Skill

    no license0★ repo

    Build a throwaway prototype to answer a design question. Use when the user asks to spike, prototype, run a PoC, de-risk an idea, sanity-check a state model, compare options, or explore UI directions before committing to implementation.

  • Review

    bingelp/skills/skills/review Skill

    no license0★ repo

    Final spec-conformance review comparing the implementation against specs/<slug>/spec.md and plan.md. Only runs when the user explicitly types /review.

  • Ship

    bingelp/skills/skills/ship Skill

    no license0★ repo

    Turns spec-conformant, reviewed work into shippable git state — branch, commit per task, draft PR — then hands off to code-review/security-review. Only runs when the user explicitly types /ship.

  • Commit

    getpipher/skills/skills/git-tools/skills/commit Skill

    0★ repo

    Commit and push current changes to remote repository

  • Create issue

    getpipher/skills/skills/git-tools/skills/create-issue Skill

    0★ repo

    Comprehensive issue creation (GitHub/GitLab) with intelligent questioning, labels, and type assignment

  • Create pr

    getpipher/skills/skills/git-tools/skills/create-pr Skill

    0★ repo

    Create a pull request (GitHub) or merge request (GitLab) from FROM branch to TO branch

  • Get pr review

    getpipher/skills/skills/git-tools/skills/get-pr-review Skill

    0★ repo

    Retrieve and analyze PR/MR review feedback to improve code quality

  • Label issues

    getpipher/skills/skills/git-tools/skills/label-issues Skill

    0★ repo

    Intelligently analyze and label unlabeled GitHub issues (works with any repo)

  • Local sync

    getpipher/skills/skills/git-tools/skills/local-sync Skill

    0★ repo

    Comprehensive git synchronization - fetch all remotes, update all branches, and ensure local repo matches remote completely (dual-remote aware)

  • Merge pr

    getpipher/skills/skills/git-tools/skills/merge-pr Skill

    0★ repo

    Merge a pull request (GitHub) or merge request (GitLab) by number or URL with configurable merge strategy

  • Pr audit

    getpipher/skills/skills/git-tools/skills/pr-audit Skill

    0★ repo

    PR auditor — reviews open PRs, merges sequentially with rebase, handles conflicts (auto org-aware)

  • Solve

    getpipher/skills/skills/git-tools/skills/solve Skill

    0★ repo

    Issue solver — creates conventional branch (feat/fix/chore), tackles issues serially, creates PR

  • Standup

    getpipher/skills/skills/git-tools/skills/standup Skill

    0★ repo

    Morning standup - PRs, Issues, and activity digest across all GitHub orgs with actionable suggestions

  • Lint fix

    getpipher/skills/skills/quality/skills/lint-fix Skill

    0★ repo

    Run linter and auto-fix all issues in the project

  • Qa

    getpipher/skills/skills/quality/skills/qa Skill

    0★ repo

    Multi-persona QA skill — dev-engineer code review + end-user UX critique via Chrome MCP. Spawns parallel dev-QA agents and sequential end-user QA agents (each playing a different user archetype). Output is structured improvement feedback for continuous iteration, not pre-ship gatekeeping. Stack-agnostic; safe to load in any project.

  • Type check strict

    getpipher/skills/skills/quality/skills/type-check-strict Skill

    0★ repo

    Run TypeScript strict checks and create comprehensive plan to fix all errors

  • Rocky review

    dianbrown/rocky/skills/rocky-review Skill

    no license0★ repo

    One-line code review findings with a rocky-voice severity scale. Each finding: line, severity, problem, fix. Ends with a ship / no-ship verdict. Use when user invokes /rocky-review or asks for a code review in rocky style.

  • Local changes review

    aneviaro/pipack/agent/skills/local-changes-review Skill

    no license0★ repo

    Review current uncommitted and untracked local changes for correctness, quality, best practices, and verification. Use when asked to review local changes, diffs, or implementation progress without a required implementation plan.

  • Plan linked review

    aneviaro/pipack/agent/skills/plan-linked-review Skill

    no license0★ repo

    Review current local changes for correctness, quality, and best practices against a required implementation plan link or path. Use when asked to review local changes, diffs, or implementation progress against a plan/spec step. If no plan link/path is provided, use ask_user_question before reviewing.

  • Ce code review

    Pdbjork/hermosskills-site/skills/ce-code-review Skill

    no license0★ repo

    Structured code review for bugs, regressions, tests, and standards. Use before PRs or when asked for review; interactive mode can fix locally, while mode:agent reports only for pipeline callers.

    The same file is in 1 other repository

  • Ce commit push pr

    Pdbjork/hermosskills-site/skills/ce-commit-push-pr Skill

    no license0★ repo

    Commit, push, and open a PR. Use when asked to ship/open a PR, or for PR-description-only flows like writing, rewriting, or describing a PR body.

    The same file is in 1 other repository

  • Ce commit

    Pdbjork/hermosskills-site/skills/ce-commit Skill

    no license0★ repo

    Create a git commit with a clear, value-communication message. Use when the user asks to commit/save staged or unstaged changes with a repo-appropriate, value-communicating message.

    The same file is in 1 other repository

  • Ce doc review

    Pdbjork/hermosskills-site/skills/ce-doc-review Skill

    no license0★ repo

    Review requirements, plans, or specs with role-specific lenses. Use when the user wants to improve an existing planning document.

    The same file is in 1 other repository

  • Domain availability checker

    Pdbjork/hermosskills-site/skills/domain-availability-checker Skill

    no license0★ repo

    Use when picking a brand name and you need to know which .com (or other TLD) variants are actually registerable before you commit. Runs concurrent whois lookups, retries on timeout, sorts FREE candidates first, and prints a clean table or machine-readable JSON/CSV. Safe and unattended — never touches registrar APIs or purchases anything.

  • Ecc security review

    Pdbjork/hermosskills-site/skills/ecc-security-review Skill

    no license0★ repo

    Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.

    The same file is in 2 other repositories

  • Ecc verification loop

    Pdbjork/hermosskills-site/skills/ecc-verification-loop Skill

    no license0★ repo

    A comprehensive verification system for Claude Code sessions.

    The same file is in 2 other repositories

  • Stripe go live workflow

    Pdbjork/hermosskills-site/skills/stripe-go-live-workflow Skill

    no license0★ repo

    Operational workflow for taking a working test-mode Stripe integration to live AND for verifying an already-live integration end-to-end. Covers the Dashboard walkthrough, the "never see the live key" safety rule, the test-mode dry run, the live deploy ritual, and the Express/Node verify-the-pipes ritual. Load when a user says "go live," "flip to live," "launch payments," "we're ready for real cards," "real money now," "production time," "I need money," "verify the live Stripe pipes," "smoke test the checkout," or "show me money," or has either a working test-mode Stripe integration that needs to ship OR an already-live Express/Worker integration that needs end-to-end verification. Default assumption when a user says "go live" is wrong: the integration may already be live from a previous session. Always audit state first. Skip for API design questions, key-management theory, or pure code-review tasks — those are covered by `stripe-best-practices`.

  • Review pr

    galaxyuliana/skill-graph/tests/fixtures/claude-home/plugins/cache/demo-market/demo-plugin/1.0.0/skills/review-pr Skill

    0★ repo

    Use when reviewing a pull request diff for bugs and style problems in changed files

  • Heyeddi pr review

    HeyEddi-com/skills/skills/heyeddi-pr-review Skill

    0★ repo

    Reviews submitted PRs using only committed changes: product fit, docs drift, engineering quality, test coverage, and pre-merge gate. Use when approving a PR, doing reviewer QA, or self-checking before requesting review. Not for replying to review comments (use heyeddi-pr-respond).

  • Heyeddi product

    HeyEddi-com/skills/skills/heyeddi-product Skill

    0★ repo

    Product leadership: user stories, acceptance criteria, backlog, holistic reviews. Verifies the product works and is useful; delegates UX flow, design critique, visual contrast, and engineering audits; synthesizes plans and change recommendations. Use after @heyeddi-intake, before ship, or when the user asks for PM review, user stories, acceptance criteria, or "is this feature good enough?"

  • Verify build

    HeyEddi-com/skills/skills/verify-build Skill

    0★ repo

    Runs npm run build to catch Vite/Rollup failures before merge. Use when validating frontend changes or in CI pre-merge loops.

  • Verify build

    HeyEddi-com/skills/evals/runs/2026-07-04T22-58-59Z/full-product-integration/.agents/skills/verify-build Skill

    0★ repo

    Runs npm run build to catch Vite/Rollup failures before merge. Use when validating frontend changes or in CI pre-merge loops.

  • Verify build

    HeyEddi-com/skills/evals/runs/2026-07-04T22-58-59Z/full-product-integration/.cursor/skills/verify-build Skill

    0★ repo

    Runs npm run build to catch Vite/Rollup failures before merge. Use when validating frontend changes or in CI pre-merge loops.

  • Loop architect

    ribbons-digital/skills/loop-architect Skill

    0★ repo

    Use this skill to design an execution loop for a repetitive, long-running, or recurring coding task before running it, including migrations, test/lint burn-downs, bug hunts, CI triage, and dependency updates. Invoke on "design/build a loop", "loop this until done", loop engineering, or when the agent repeats the same change or prompt across 3+ items; pause and propose a loop. Deliverable is a reviewed Loop Card (goal, exit condition, iteration unit, verification, state, stop conditions, human gates), runnable loop prompt, and initialized state. Skip one-shot tasks, already-designed loop runs, and questions about loops in program code.

  • Routine architect

    ribbons-digital/skills/routine-architect Skill

    0★ repo

    Use this skill to design a recurring routine for non-coding work before running it. Invoke when the user wants to turn repetitive non-coding work into an autonomous routine (daily digests, inbox or channel triage, news or market monitoring, knowledge-base or vault upkeep, content pipelines, data hygiene in external tools), asks to "design a routine", "automate this workflow", "do this every morning/day/week", or keeps manually re-issuing the same non-coding prompt. Also invoke proactively, without being asked, when the agent notices the same non-coding request recurring across 3 or more sessions or items - pause and propose a routine before continuing item by item. For repetitive coding tasks in a repository (migrations, test or lint burn-downs, CI triage), use loop-architect instead. The deliverable is a reviewed Routine Card (goal, exit or cadence, iteration unit, verification, state, stop conditions, human gates, trigger, write surfaces) plus a runnable routine prompt.

  • Swarm worker

    ribbons-digital/skills/swarm-worker Skill

    0★ repo

    Use when executing one approved coding slice in a parallel worker thread dispatched by the swarm coordinator, with explicit scope, an assigned git worktree and slice branch, focused implementation, verification, slice commits, and handoff back to the coordinating main thread. The coordinating thread is the only reviewer. No external reviewer model, no-mistakes, PR, merge, or post-merge workflow; for a solo slice with full PR workflow use blaze. Can also run standalone on a single bounded slice with the user acting as coordinator.

  • Safety stock review

    gulmezeren2-byte/industrial-engineering-ai-skills/skills/safety-stock-review Skill

    0★ repo

    Size or audit safety stock with assumption checks - the z*sigma*sqrt(LT) formula plus an empirical stress test of what it actually delivers (cycle service vs fill rate) per variability class. Use when the user mentions safety stock, emniyet stoku, emniyet stoğu, reorder point, service level, stok seviyesi belirleme. Differentiator - refuses to hand back a number without validating the demand-distribution assumptions behind it.

  • Grill me

    angpysha/api2skill/.agents/skills/grill-me Skill

    0★ repo

    A relentless interview to sharpen a plan or design.

  • Grill with docs

    angpysha/api2skill/.agents/skills/grill-with-docs Skill

    0★ repo

    Relentless interview to sharpen a plan or design. All resolved information is written via Spec Kit (/speckit.* → spec.md/plan.md). Glossary (CONTEXT.md) and ADRs supplement only. Composes grilling + domain-modeling + spec-kit.

  • Review

    gnjohnny/Maps2Chat/.agents/skills/review Skill

    no license0★ repo

    After building a feature, verify it matches what was planned, respects the system architecture and design standards, and is ready for production. Reports issues clearly so the developer decides what to fix.

  • Mr review

    ohyesgocool/feature-loop/skills/mr-review Skill

    0★ repo

    Get independent external-AI reviews on a merge request and post them as MR comments: sends the MR title, description, and diff to each configured external reviewer — OpenAI GPT (correctness-first implementation brief) and xAI Grok (code-quality review: DRY, cohesion, naming, testability) — and posts each reviewer's brief as a separate MR discussion. The point is independence: the reviewers are DIFFERENT models from the one that wrote the code, so they don't share its blind spots. Review-only — never modifies code, never approves, never merges. Feeds /address-review, which triages and resolves the posted comments. Requires OPENAI_API_KEY and/or XAI_API_KEY in the environment (see Configuration). Use when: "review this MR", "run the AI review", "get an external review", right after /build-feature raises an MR, or re-reviewing after fixes were pushed.

  • Stayingapi review intelligence digest

    stayingapi/travel-skills/skills/stayingapi-review-intelligence-digest Skill

    0★ repo

    Pull normalized reviews for a property on a schedule and deliver a weekly digest — average rating, recurring themes, and the latest complaints to act on. Powered by the StayingAPI REST API / MCP server.

  • Py review

    CodeSigils/py-review-skill/skills/py-review Skill

    no license0★ repo

    Route Python code review to focused skills for type safety, error handling, anti-patterns, async behavior, and code style. Use before or during Python code review to orient on project version, maturity, toolchain, changed files, and which py-* review skills should be loaded.

  • Missing review

    lilechen/skill-runtime-auditor/examples/missing-review Skill

    0★ repo

    Runtime coverage auditing for AI agent skills and workflow instructions.

  • Follow procedure

    jcdavis131/cursor-agent-skills/skills/follow-procedure Skill

    0★ repo

    When a documented, named procedure exists for the decision at hand (a dataviz palette procedure, a commit-message convention, a deploy checklist, a spec, an ADR), cite it by name and follow it rather than improvising. Use whenever a written procedure, spec, checklist, ADR, or convention applies to the current decision — especially in spec-driven repos.

  • Lane discipline

    jcdavis131/cursor-agent-skills/skills/lane-discipline Skill

    0★ repo

    In a multi-agent fleet, verify a piece of work is in your designated lane before doing it, and state the check out loud. Defer to the owning agent when the work belongs to another lane. Use whenever the repo has documented agent/team role boundaries (AGENTS.md, .cursor/rules/, .claude/TEAM.md, fleet-team rules) and the task touches a shared area.

  • Logical commit split

    jcdavis131/cursor-agent-skills/skills/logical-commit-split Skill

    0★ repo

    Split a large migration or multi-concern change into logical commits grouped by concern, on a branch whose name encodes the commit story, rather than one giant commit. Use when a change spans multiple distinct concerns (infra + data + UI, baseline + feature + commerce), when the change would be unreviewable as one commit, or when one slice might need to be reverted independently.

  • Monorepo review loop

    jcdavis131/cursor-agent-skills/skills/monorepo-review-loop Skill

    0★ repo

    A recurring review workflow that walks a monorepo through a fixed arc — orient, plan, fan out reviewers, review code, run gates, check guards, align metadata, deploy+smoke, close out — using the 39 codified skills as the steps. Use to continuously update and refine a detailed monorepo so "done" is unambiguous, every claim is auditable, and docs/registry/tests/deploy stay aligned with the code. Run on a cadence (e.g. daily) or on demand after a batch of changes.

  • Pre commit hygiene

    jcdavis131/cursor-agent-skills/skills/pre-commit-hygiene Skill

    0★ repo

    Before a large or migration commit, exclude junk (build output, local tool dirs, node_modules) and scan for secrets and sensitive files so they don't enter history. Use before any commit that spans many files or a migration, before `git add`, and whenever the user says "never commit secrets" or "let's push this".

  • Respect the guard

    jcdavis131/cursor-agent-skills/skills/respect-the-guard Skill

    0★ repo

    When blocked by a safety guard (push-to-main protection, destructive-command confirm, permission boundary, failed eval gate), uses the legitimate path instead of bypassing — and surfaces exactly how the operator relaxes the guard if desired. Use when a guard stops the fast path, when tempted to use --no-verify or --force, when a deploy script offers only an exec variant, or when input/API limits apply.

  • Smoke import

    jcdavis131/cursor-agent-skills/skills/smoke-import Skill

    0★ repo

    Fast sanity-check that new or edited packages import cleanly, without running a full dependency sync or test suite. Use after creating/editing a Python package's __init__.py, adding a new module to a monorepo, wiring sibling packages, or before wiring a package into a router — any time you want the cheapest possible "did I wire this up" signal.

  • Verify subagent output

    jcdavis131/cursor-agent-skills/skills/verify-subagent-output Skill

    0★ repo

    After parallel subagents (SME reviewers, research agents, task agents) return, spot-check their output against the named contract/standard before synthesizing or marking the task done. Use whenever you dispatched subagents and they've returned artifacts — especially before treating their output as ground truth in a synthesis or a "done" report.

  • Agent design review

    frankxai/skills/skills/reviews/agent-design-review Skill

    0★ repo

    Use when the user asks to review, grill, pressure-test, or sanity-check an AI agent or multi-agent system design before building it — triggers include "grill me on my design", "design review", "review my agent architecture", "is this architecture sound", "pressure-test this before I build". Interrogates the design against the four failure modes that kill enterprise agent initiatives and returns a go / no-go verdict with ranked fixes.

  • Codetruss

    DeliriumPulse/codetruss-plugins/skills/codetruss Skill

    0★ repo

    Operate CodeTruss local acceptance gates for coding-agent changes. Use when a developer asks to bind an agent task to allowed or denied files, configure repository verification, install or diagnose Claude Code or Codex hooks, review a working-tree or staged diff before commit, interpret or verify a signed CodeTruss receipt, repair a failed verdict, or explicitly opt into provider-backed review or receipt sync.

  • Conventional commit

    vaibhavsaxena022/skills/conventional-commit Skill

    0★ repo

    Write a Conventional Commits message from the staged git diff. Use when the user asks to commit, write a commit message, or has just staged changes. Produces a properly formatted "type(scope): subject" with an optional body and footer.

  • Pr description

    vaibhavsaxena022/skills/pr-description Skill

    0★ repo

    Generate a structured pull-request description from the diff between the current branch and its base. Use when opening a PR or when asked to write a PR description. Produces Summary, Changes, Testing, and Risks sections.

  • Review pr

    vaibhavsaxena022/skills/review-pr Skill

    0★ repo

    Review a pull request for what actually matters. Use when asked to review a PR or diff. A structured pass over correctness, boundaries, error handling, data, tests, performance, and security — findings ranked by severity.

  • Security review

    vaibhavsaxena022/skills/security-review Skill

    0★ repo

    Review an endpoint or service for common security flaws. Use when adding or reviewing code that handles auth, user input, or sensitive data. Checks authorization, injection, secrets, and data exposure (OWASP-style).

  • Sql review

    vaibhavsaxena022/skills/sql-review Skill

    0★ repo

    Review a SQL query (Postgres/MySQL) for performance and safety before it ships. Use when given a slow query, a new query, or asked to optimize SQL. Flags missing indexes, full scans, N+1 patterns, risky writes, and inefficient pagination.

  • Swarm review

    grimoire-rs/grimoire-vscode/.claude/skills/swarm-review Skill

    0★ repo

    Use for branch, PR, or diff review before landing on main. Tier (`low | auto | high | max`) scales breadth from single reviewer to adversarial panel with architect + SOTA-gap + Codex cross-model gate. Triggers: "review", "/swarm-review", pre-merge checks.