agentsclimarketplace

Review & quality

19,040 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

  • Pr reviewer

    bmaltais/skills/pr-reviewer Skill

    no license2โ˜… repo

    Expert automated code reviewer (Copilot Reviewer persona). Given a GitHub PR URL or raw diff, fetches the changes and produces the exact structured review (Summary + ๐Ÿ”ด Critical + ๐ŸŸก Suggestions + etc.). Posts the feedback directly as top-level comments on the real GitHub PR by default (using the built-in helpers in scripts/ (post_review.py + github.sh) and gh auth token). Use --no-post for review-only mode. Never uses Approve/Request Changes. Triggered by /pr-reviewer <url>, 'review this PR', etc. (posts by default).

  • Receiving code review

    bmaltais/skills/receiving-code-review Skill

    no license2โ˜… 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

  • Simplify

    bmaltais/skills/simplify Skill

    no license2โ˜… repo

    Automated code review and simplification workflow that reviews git changes through three parallel analyses (code reuse, quality, efficiency) and applies high-confidence fixes. Use whenever users want to clean up code, simplify code, review changes before committing, check for duplicate logic, find N+1 patterns, improve code efficiency, refactor messy code, or reduce technical debt. Trigger on phrases like "simplify my code", "review my changes", "check for duplicates", "optimize this code", "clean up before commit", "any code smells?", "make this more efficient", or "reduce complexity". Always use this skill when the user mentions code review, refactoring, or wants to improve code quality.

  • Thermo nuclear code quality review

    bmaltais/skills/thermo-nuclear-code-quality-review Skill

    no license2โ˜… repo

    Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.

    The same file is in 5 other repositories

  • Verification before completion

    bmaltais/skills/verification-before-completion Skill

    no license2โ˜… repo

    Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

    The same file is in 40 other repositories

  • Rx review

    fnord123/hermes-skills/rx-review Skill

    2โ˜… repo

    Review the user's medications and supplements against their blood tests. Takes lab PDFs and a regimen โ€” typed in chat, or from a source you resolve first (a Google Doc via the google-docs skill, a local file) โ€” then a kanban pipeline transcribes, looks up product doses, researches each substance, screens interactions and timing, adversarially verifies every claim, and produces a discussion brief for their prescriber. Use when the user asks to review their meds, supplements, or labs, add new lab results, answer a question the review is waiting on, or check on a review already running.

  • Post build review

    olzn/skills/skills/post-build-review Skill

    2โ˜… repo

    Run a post-implementation review that checks a built change against the intent that was set. Run lint, typecheck, tests, and build; confirm the result matches the chosen design direction and covers its promised states (empty, loading, error, disabled, long content, and partially complete data); check accessibility and responsive behaviour; flag any risky surface; and assemble the handoff evidence a reviewer needs. Read-only: it reviews and reports, it never edits. Use after a build or a meaningful change, after ui-craft and before opening or finalising a PR, especially when the user asks to verify, review, sign off, or sanity-check a built change before handoff.

  • Pre build review

    olzn/skills/skills/pre-build-review Skill

    2โ˜… repo

    Run a pre-implementation plan review that attacks a settled product, UI, or technical plan for blockers, missing states, edge cases, accessibility gaps, mobile failures, awkward data assumptions, and implementation ambiguity. Use before coding after grill-with-docs, paper-prototype, a design decision, prototype, PRD, brief, or implementation plan, especially when the user asks to red-team, sanity-check, review, or decide go/no-go before build.

  • Hig review

    olzn/skills/suites/hig/hig-review Skill

    2โ˜… repo

    Audit designs, prototypes, or code against Apple's Human Interface Guidelines. Use for Apple-marked review asks โ€” "is this HIG compliant", "review my iOS app", "review my Mac app", "does this feel native", "would Apple reject this", "check this against the HIG" โ€” or when reviewing SwiftUI UI code, an HTML prototype that imitates native Apple UI, or Figma frames built on Apple's kits. Covers screens, flows, copy, accessibility, Liquid Glass usage, system surfaces (widgets, Live Activities, notifications), and App-Review-enforced rules. Model priors on Apple's design system are stale (Liquid Glass era) โ€” never judge native correctness from memory. Does NOT fire on unmarked "review my prototype/UI" for web apps (use ui-craft or interface-craft); web mechanics of HTML prototypes stay with ui-craft โ€” this skill owns native idiom and metric values.

  • Adversarial review

    IrfanSadiqRahat/constellation/methodology/adversarial-review Skill

    no license2โ˜… repo

    Three competing reviewer roles produce independent verdicts in parallel; coordinator synthesizes.

  • Artifact validation

    IrfanSadiqRahat/constellation/methodology/artifact-validation Skill

    no license2โ˜… repo

    Mechanical schema + invariant checking of artifacts. The unit test for typed handoffs.

  • Verify before done

    IrfanSadiqRahat/constellation/methodology/verify-before-done Skill

    no license2โ˜… repo

    Validate artifact against schema, acceptance criteria, and downstream readiness BEFORE marking a task complete.

  • Prime gnadd

    AlexHagemeister/gnadd/skills/prime-gnadd Skill

    2โ˜… repo

    Orient a new chat session with a read-only project snapshot using the bundled gnadd script, git, and gh: project shape, current branch state, whether main is behind or diverged from origin, stashes, recent commits, open issues, open and merged PRs, and active issue context. Fetches latest remote state first. Use when the user asks to inspect project state, orient a session, see what work is open, or decide what to do next.

  • Quickfix gnadd

    AlexHagemeister/gnadd/skills/quickfix-gnadd Skill

    2โ˜… repo

    Land a trivial change on main through a PR in one flow using the bundled gnadd script and gh: no GitHub issue required โ€” the PR is the record. Branch off synced main, commit, push, PR, wait for CI, squash-merge, sync main, and clean up. Refuses oversized or mechanics-touching changes with a redirect to the full loop. Use when the user wants to quickfix, quickly land, or ship a small change โ€” a typo, one-line doc fix, or tiny tweak โ€” without opening an issue.

  • Resolve issue gnadd

    AlexHagemeister/gnadd/skills/resolve-issue-gnadd Skill

    2โ˜… repo

    Wrap up work on a GitHub issue using the bundled gnadd script and gh: identify the issue branch, verify the work against acceptance criteria, run the project's tests, commit final changes, create or resume the PR, check mergeability and CI, optionally merge, sync the issue record, and clean up. Does not rebase. Use when issue work appears complete, the user wants to ship an issue branch, or the next step is verification, PR creation, merge decision, and cleanup.

  • Backend

    tufantunc/review-pro/core/skills/backend Skill

    2โ˜… repo

    Backend design audit of changed code: error handling, input validation, transactional/atomic boundaries, idempotency, rate limiting, API shape, service-boundary leaks. Use for backend review, API handler audit, validation or transaction-safety check of a diff.

  • Frontend

    tufantunc/review-pro/core/skills/frontend Skill

    2โ˜… repo

    Frontend design audit of changed code: component structure, state placement, prop drilling, design-system consistency, effect correctness, loading/error states, i18n-readiness. Use for frontend review, component or state audit, UI consistency check of a diff.

  • Review pro synthesize

    tufantunc/review-pro/core/skills/review-pro-synthesize Skill

    2โ˜… repo

    Stage 3 of review-pro: dedup, weight, resolve conflicts, calibrate severity, and produce the final verdict + report from specialist findings. Use to merge reviewer results into one review verdict.

  • Review pro triage

    tufantunc/review-pro/core/skills/review-pro-triage Skill

    2โ˜… repo

    Stage 1 of review-pro: classify changed files, detect relevant specialist reviewers, detect active stacks, scope context per reviewer, and emit a dispatch plan. Use to start a review-pro review, triage a PR/branch, or fan out reviewers.

  • Review pro

    tufantunc/review-pro/core/skills/review-pro Skill

    2โ˜… repo

    One-command AI code review. Runs triage -> relevant specialist reviewers -> synthesis on the current branch and returns the verdict + report. Stack-specific signals are loaded automatically from the repo's .review-pro/ directory. Use to review a branch or PR with review-pro.

  • Funnel audit

    fjilvvi/growthlens/skills/funnel-audit Skill

    2โ˜… repo

    Map and critique a company's marketing/sales funnel from its public site โ€” from first touch (ad/SEO/landing) through lead capture, nurture, and conversion โ€” using an AARRR/awareness-to-action lens, and find the leaks. Use when the user asks to "audit the funnel", "map their funnel", "where are we losing people", "review our conversion path", or shares a site and wants the acquisition-to-conversion journey analyzed.

  • Landing ux review

    fjilvvi/growthlens/skills/landing-ux-review Skill

    2โ˜… repo

    Conversion-focused UX review of a landing page โ€” above-the-fold clarity, visual hierarchy, copy, CTA, trust, friction, mobile, and load โ€” scored section by section with prioritized fixes. Use when the user shares a landing page URL or screenshot and asks "why isn't this converting", "review this landing page", "audit the UX", "improve this page", or "give me CRO feedback".

  • Review mining

    fjilvvi/growthlens/skills/review-mining Skill

    2โ˜… repo

    Mine public customer reviews of a product or competitor (G2, Capterra, Trustpilot, app stores, Amazon) to extract voice-of-customer insights โ€” top pains, delights, switching triggers, objections, feature requests, and the exact language customers use โ€” ranked by frequency. Use when the user asks to "mine reviews", "analyze reviews for <product>", "what do customers say about <competitor>", "voice of customer", "find copy angles from reviews", or shares review text and wants themes and insights pulled out.

  • Receiving code review

    grimaldost/craft-collection/plugins/humblepowers/skills/receiving-code-review Skill

    2โ˜… repo

    Evaluate incoming review feedback technically before acting on it: read all items, restate or ask about anything unclear before implementing any of them, verify each suggestion against the actual codebase, push back with evidence when a suggestion is wrong for this code, and skip performative agreement entirely. Use when processing review comments from a human or an automated reviewer, when feedback seems technically questionable or context-blind, when a reviewer proposes 'implementing properly' something nothing calls (grep usage first, propose removal), or when a reply is about to start with 'you're absolutely right'. Order of work: clarify everything, then blocking issues, simple fixes, complex fixes โ€” testing each individually; a pushback that turns out wrong gets a one-line factual correction, not an apology. Not for performing a review of someone else's change (/code-review or review-panel) and not for triaging accumulated feedback reports into a backlog (feedback-triage).

  • Systematic debugging

    grimaldost/craft-collection/plugins/humblepowers/skills/systematic-debugging Skill

    2โ˜… repo

    Root-cause-first debugging in four phases โ€” investigate (read the full error, reproduce, check recent changes, instrument component boundaries), pattern-match against working examples, test one hypothesis at a time, then fix the cause with a failing test. Use when any bug, test failure, or unexpected behavior lacks a proven cause, when a fix is being proposed before the data flow was traced, when the previous fix didn't work, especially under time pressure (guessing is slower than the protocol), and when three or more fixes have failed โ€” treat that as an architecture signal and raise it with the user instead of attempting a fourth. The bright line: no fix before the root cause is identified with evidence; in multi-component systems, log what enters and exits each boundary before theorizing. Hands the reproducing test to test-driven-development and the resolution claim to verification-before-completion. Not for changes whose cause is already proven (just fix them) and not for performance tuning without a defect (profile first).

  • Verification before completion

    grimaldost/craft-collection/plugins/humblepowers/skills/verification-before-completion Skill

    2โ˜… repo

    Evidence before completion claims: identify the command that would prove the claim, run it fresh in this session, read the full output including exit code, and only then state the result โ€” with the evidence. Use when about to report work as done, fixed, passing, or ready; before committing, opening a PR, or moving to the next task; when relaying a subagent's result (verify the diff, not the report); and when adding a regression test (red-green it: revert the fix, watch it fail, restore, watch it pass). Claims match their evidence โ€” 'tests pass' means this session's run with zero failures, not a previous run or an expectation; if verification fails, the deliverable is the actual state with output. Prefer wiring recurring checks into pre-commit or CI over re-remembering them. Not for designing what to verify (a test-strategy concern) โ€” this skill governs the moment of claiming, not the shape of the suite.

  • Corpus review

    grimaldost/craft-collection/plugins/session-workflow/skills/corpus-review Skill

    2โ˜… repo

    Audit a large file corpus โ€” dozens to hundreds of docs, configs, or mixed code-plus-docs-plus-tests โ€” by fanning out blind reviewers over partitions, adversarially verifying every high-severity finding before acting on it, fixing in disjoint file partitions, and re-auditing with fresh eyes until the findings converge. Use when reviewing or auditing a whole repo's documentation, a release's doc set, an entire plugin or package, or any file set too large for one reader to hold at once; on asks like "review all the docs before we push", "audit the whole repo for X", "blind review across these N files", "do a pre-push review of everything", or "check the docs still match the code across the project". It orchestrates the audit on the harness's parallel subagent and workflow primitives and ships no engine of its own. Not for a fresh-eyes panel on a single design, spec, or artifact (that is review-panel), not for reviewing one change's diff for bugs and regressions (that is a diff review / code-review), and not for behaviorally measuring whether a skill triggers and performs (that is evaluate-skill).

  • Llm signature

    grimaldost/craft-collection/plugins/session-workflow/skills/llm-signature Skill

    2โ˜… repo

    Sign agent-assisted work with a machine-generated provenance signature: an Assisted-By git trailer naming the exact model that wrote and orchestrated the change, and an Agent-Stack trailer naming the harness and plugin versions it ran on. Use when committing or writing a PR body in a project that adopts the signature, when asked to sign a commit with the model / add model attribution or an LLM signature, when asked which model or tool stack produced a change, or when replacing Co-Authored-By AI boilerplate with provenance trailers. The signature is rendered by a script from live sources, never typed from memory, and the model is listed only in Assisted-By โ€” never as a commit co-author. Not for human authorship credit (real co-authors keep their Co-Authored-By lines).

  • Review panel

    grimaldost/craft-collection/plugins/session-workflow/skills/review-panel Skill

    2โ˜… repo

    Use when the user has iterated on a design, plan, spec, architecture, code, or prose over several rounds and can no longer judge it cleanly, before a high-stakes or hard-to-reverse decision, or when they ask for "fresh eyes", "a second opinion", "red team this", "poke holes in this", "sanity-check this independently", "am I anchored" / "too close to this", "critique this from different angles", or run "/review-panel". Prefer this over reviewing the artifact yourself โ€” its value is convening fresh reviewer subagents that are blind to this conversation and to each other, which a review you run while anchored on the same context cannot replicate. Requires spawning fresh-context reviewers (subagents where the harness has them; sequential clean contexts otherwise); always show the plan and rough cost and ask before firing. Not for a quick factual check, a single obvious answer, or a first-pass review of something just created.

  • Laravel production readiness review

    ArtemProshkovskiy/laravel-maintenance-skills/skills/laravel-production-readiness-review Skill

    2โ˜… repo

    Laravel production-readiness reviewer. Audits the "works locally, breaks/leaks in production" gap before deploy: env() called outside config/ (returns null after config:cache), closure routes that make route:cache fail, unsafe .env values (APP_DEBUG=true, empty APP_KEY, sync queue, APP_URL=localhost), secret exposure (.env tracked in git, real values in .env.example), .env drift, and leftover debug calls. Anchored to real .env / config / route:list output, advise-only. Use when the user wants a pre-deploy check or hits a prod-only bug โ€” e.g. "is this safe to deploy", "production readiness check", "env is null after deploy", "config:cache broke my app", "closure route route:cache fails", "why does it work locally but not in production". Advise-only: never edits files.

  • Scope guard

    logicleap-labs/claude-plugins/plugins/scope-guard/skills/scope-guard Skill

    2โ˜… repo

    Use at the START of any focused task โ€” a bug fix, one feature, a single file's refactor โ€” and ALWAYS when more than one agent shares a working tree. Declare which files the task is allowed to touch so edits outside that set are blocked. Triggers on "only change X", "just fix the bug in", "don't touch anything else", "stay in your lane", "scoped change", "while you're in there" (the thing to prevent), shared-tree / multi-agent work, and any task where creep is the risk.

  • Secret guard

    logicleap-labs/claude-plugins/plugins/secret-guard/skills/secret-guard Skill

    2โ˜… repo

    Use whenever you are about to put a credential, API key, token, or password into code โ€” or whenever a secret already appears in a file you're editing. Triggers on "add the API key", "paste the token", "hardcode the secret", "set the password", "AWS/Stripe/OpenAI/GitHub key", "connect to <service>", "use this credential", config/setup work that wires up a third-party service, and any moment a real secret value is in hand. The rule: secrets go in the environment, never in source.

  • Verify before done

    logicleap-labs/claude-plugins/plugins/verify-before-done/skills/verify-before-done Skill

    2โ˜… repo

    MANDATORY before declaring ANY code change "done", "fixed", "working", "ready", "shipped", or before ending a turn after editing source. Use whenever you modified code, config, scripts, SQL, infra, or tests and are about to say it works. Forces you to RUN something that exercises the change (test, build, lint, typecheck, smoke script, reproducible command) and record the evidence. Triggers on "done", "fixed", "working", "all tests pass", "build succeeded", "should work now", "ready to merge".

  • Visual self review

    logicleap-labs/claude-plugins/plugins/visual-quality/skills/visual-self-review Skill

    2โ˜… repo

    MANDATORY acceptance gate before declaring ANY visual or UI work "done", "good", "working", or before screenshotting an interface and ending the task. Use whenever you build, redesign, restyle, or fix a user-facing screen in ANY stack โ€” Xcode/SwiftUI/UIKit apps, iOS/macOS, web (Next.js/React/HTML), Electron, Flutter, generated design mockups โ€” and whenever you are asked to "review the screenshot", "check what you built", "is this good", "spot the issues", or "look at this design". Forces a structured, written, adversarial inspection of the ACTUAL rendered pixels (not the code, not your memory of intent) so obvious defects โ€” blank/unlabelled elements, dead empty space, duplicated or garbage content, misalignment, inconsistent spacing, truncation, low contrast, leftover placeholders, broken states, and lag/jank โ€” are caught BEFORE you claim completion. Triggers on "done", "looks good", "finished the UI", "here's the redesign", "screenshot", "ship it".

  • Auth flow review

    tunahanaliozturk/secure-dotnet-skills/skills/auth-flow-review Skill

    2โ˜… repo

    Use when reviewing authentication and authorization in an ASP.NET Core app โ€” JWT / OIDC / Entra ID configuration, token validation, and scope/role enforcement.

  • Azure hardening review

    tunahanaliozturk/secure-dotnet-skills/skills/azure-hardening-review Skill

    2โ˜… repo

    Use when reviewing Azure infrastructure (Bicep, Terraform, ARM, or App Service / Container Apps config) for hardening โ€” least-privilege identity, network exposure, Key Vault, encryption, and TLS.

  • Container deployment review

    tunahanaliozturk/secure-dotnet-skills/skills/container-deployment-review Skill

    2โ˜… repo

    Use when reviewing how a .NET app is containerized and deployed โ€” Dockerfile, base image, runtime user, configuration, health probes, resources, and secrets โ€” before it runs in Kubernetes or Azure Container Apps.

  • Dependency supplychain check

    tunahanaliozturk/secure-dotnet-skills/skills/dependency-supplychain-check Skill

    2โ˜… repo

    Use when reviewing a .NET project's NuGet dependencies for known vulnerabilities, abandoned packages, supply-chain hygiene, and version pinning hygiene โ€” before merging a dependency change or during a periodic security audit.

  • Dotnet performance review

    tunahanaliozturk/secure-dotnet-skills/skills/dotnet-performance-review Skill

    2โ˜… repo

    Use when reviewing .NET code for performance โ€” allocations and GC pressure, async/IO misuse, hot-path LINQ, repeated enumeration, string handling, caching, and serialization.

  • Dotnet security review

    tunahanaliozturk/secure-dotnet-skills/skills/dotnet-security-review Skill

    2โ˜… repo

    Use when reviewing a .NET / ASP.NET Core service, pull request, or diff for security issues โ€” authorization gaps, injection, insecure crypto, secret leakage, unsafe deserialization โ€” before merge or deploy.

  • Ef core review

    tunahanaliozturk/secure-dotnet-skills/skills/ef-core-review Skill

    2โ˜… repo

    Use when reviewing Entity Framework Core usage โ€” for performance (N+1, tracking, projections), correctness (transactions, concurrency), and security (raw-SQL injection, migrations).

  • Observability review

    tunahanaliozturk/secure-dotnet-skills/skills/observability-review Skill

    2โ˜… repo

    Use when reviewing logging, tracing, and metrics in a .NET app โ€” structured logging, OpenTelemetry, correlation, and avoiding PII / secret leakage in telemetry.

  • Rate limiting review

    tunahanaliozturk/secure-dotnet-skills/skills/rate-limiting-review Skill

    2โ˜… repo

    Use when reviewing rate limiting and overload protection in an ASP.NET Core app โ€” limiter algorithm, partitioning, 429 semantics, and where limiting belongs โ€” to protect against abuse and overload.

  • Resilience review

    tunahanaliozturk/secure-dotnet-skills/skills/resilience-review Skill

    2โ˜… repo

    Use when reviewing how a .NET service handles transient faults and downstream failures โ€” timeouts, retries, circuit breakers, bulkheads, and fallback โ€” for calls to databases, queues, and HTTP dependencies.

  • Solid review

    tunahanaliozturk/secure-dotnet-skills/skills/solid-review Skill

    2โ˜… repo

    Use when reviewing C# / .NET code for SOLID design adherence โ€” single responsibility, open/closed, Liskov, interface segregation, dependency inversion โ€” to surface coupling and concrete refactor opportunities.

  • Loop review

    VioletScar-Hui/Build_Great_Loop/loop-review Skill

    2โ˜… repo

    Audit and harden an EXISTING agentic-loop prompt or harness against loop-engineering best practices. Use this whenever the user has an agent/loop iterative/autonomous prompt and wants it reviewed, critiqued, scored, or made more reliable โ€” or when they describe loop misbehavior and want to know why: "my agent runs forever / never stops", "it quits too early", "it says it's done but it isn't", "it keeps redoing the same thing", "it forgets progress after a restart", "it edits the tests to pass", "review/improve my iterative agent prompt", "why is my loop flaky". It produces a scored report โ€” critical gaps first, each with a concrete fix โ€” and can rewrite the prompt to close them. Exclude one-shot chatbot/system prompts. If symptoms belong to a completed run or run artifacts, loop-retro diagnoses first. Whole-harness audits are led here even when criteria are the suspected defect. This skill also owns maintenance audits of this six-skill router.

  • Git workflow

    pablodiazjorge/prompt-forge/.github/skills/git-workflow Skill

    2โ˜… repo

    Git best practices for AI coding agents. Use when committing changes, creating branches, splitting PRs, reviewing code, or setting up worktrees. Covers Conventional Commits v1.0.0 spec, atomic commits, stacked PRs, squash-based workflow, and worktree patterns.

  • Git workflow

    pablodiazjorge/prompt-forge/packages/claude/.claude/skills/git-workflow Skill

    2โ˜… repo

    Git best practices for AI coding agents. Use when committing changes, creating branches, splitting PRs, reviewing code, or setting up worktrees. Covers Conventional Commits v1.0.0 spec, atomic commits, stacked PRs, squash-based workflow, and worktree patterns.

  • Git workflow

    pablodiazjorge/prompt-forge/packages/copilot/.github/skills/git-workflow Skill

    2โ˜… repo

    Git best practices for AI coding agents. Use when committing changes, creating branches, splitting PRs, reviewing code, or setting up worktrees. Covers Conventional Commits v1.0.0 spec, atomic commits, stacked PRs, squash-based workflow, and worktree patterns.

  • Git workflow

    pablodiazjorge/prompt-forge/packages/custom/.github/skills/git-workflow Skill

    2โ˜… repo

    Git best practices for AI coding agents. Use when committing changes, creating branches, splitting PRs, reviewing code, or setting up worktrees. Covers Conventional Commits v1.0.0 spec, atomic commits, stacked PRs, squash-based workflow, and worktree patterns.

  • House style

    RightBlogger/bloggingskills/skills/house-style Skill

    2โ˜… repo

    When the user wants to define, apply, or enforce a consistent writing style across their blog, or check whether a draft follows it. Also use when the user says 'house style', 'style guide', 'make it consistent', 'does this follow our style', 'set our writing rules', 'tone of voice', or asks why their content keeps reading like AI across posts. This is the shared quality layer every other blogging skill reads. For rewriting one AI-sounding draft, see humanize. For the blog's niche, audience, voice, and CMS setup, see blog-context. For writing a post from scratch, see article.

  • Git workflow

    affectionatec/agentic-engineering/skills/git-workflow Skill

    2โ˜… repo

    Use when implementation work is about to touch code (branch before the first commit), when a built task needs to ship as a pull request, when defining how branches, commits, and PRs map to plan tasks, or when parallel agents share one repository. Triggers on "create a branch", "commit this", "open a PR", "ship this task", "how do we merge", task start or completion during an implementation plan, worktree setup, or noticing commits landing directly on main.

  • Independent verification

    affectionatec/agentic-engineering/skills/independent-verification Skill

    2โ˜… repo

    Use when a task or milestone claims completion and must be verified before being marked done, when acting as a verifier sub-agent checking a producer's work, or when a "done" claim needs evidence. Triggers on "verify this task", "is this actually done", "acceptance check", "run verification", any completion claim, any ๐Ÿ” โ†’ โœ… status transition, or dispatching a maker-checker review loop.

  • Clean up

    dustinkeeton/wafflestack/.claude/skills/clean-up Skill

    2โ˜… repo

    Tidy up after a finished process: delete local git branches and worktrees whose pull request has already merged, prune stale remote-tracking refs, and spin down background tasks and agents that have completed their work. Use this whenever one or more PRs have just merged, after a /delegate run wraps up, or when the user says things like "clean up", "clean up the merged branches", "remove stale worktrees", "tidy up my branches", or "we're done, spin down the agents". This is git + agent housekeeping โ€” NOT source-code cleanup or refactoring.

  • Git workflow

    dustinkeeton/wafflestack/.claude/skills/git-workflow Skill

    2โ˜… repo

    Git branching strategy, commit standards, and PR workflow for the wafflestack project. Use when performing any git operations (commits, branches, pushes, PRs).

  • Adversarial review

    dustinkeeton/wafflestack/stacks/code-quality/skills/adversarial-review Skill

    2โ˜… repo

    Adversarially review a green PR from a hostile reviewer's seat โ€” read the full diff and poke holes in correctness edge cases, API/naming choices, missing tests, error handling, and simplification opportunities, posting findings as actionable PR review comments. Severity stays honest โ€” no manufactured blockers; "no holes found" is a valid outcome for a genuinely solid PR. Invokable by users and agents.

  • Clean up

    dustinkeeton/wafflestack/stacks/github-workflow/skills/clean-up Skill

    2โ˜… repo

    Tidy up after a finished process: delete local git branches and worktrees whose pull request has already merged, prune stale remote-tracking refs, and spin down background tasks and agents that have completed their work. Use this whenever one or more PRs have just merged, after a /delegate run wraps up, or when the user says things like "clean up", "clean up the merged branches", "remove stale worktrees", "tidy up my branches", or "we're done, spin down the agents". This is git + agent housekeeping โ€” NOT source-code cleanup or refactoring.

  • Git workflow

    dustinkeeton/wafflestack/stacks/github-workflow/skills/git-workflow Skill

    2โ˜… repo

    Git branching strategy, commit standards, and PR workflow for the {{project.name}} project. Use when performing any git operations (commits, branches, pushes, PRs).

  • Code review

    risadams/ink-and-agency/skills/codebase-build/code-review Skill

    no license2โ˜… repo

    Two-axis review of the working diff since a fixed point โ€” Standards (does it follow this repo's coding standards + a code-smell baseline?) and Spec (does it match the originating ticket/spec?). Runs both as parallel sub-agents. Use when the user wants to review a branch or work-in-progress changes, says "review since X", or asks for a pre-MR review before a merge request exists.

  • Codebase churn

    risadams/ink-and-agency/skills/codebase-build/codebase-churn Skill

    no license2โ˜… repo

    Analyze a git repository's history and produce an SVG treemap of file churn โ€” area = lines changed, color = commit frequency. Use when user wants to find unstable areas of a codebase, predict bug-prone files, see "where do we change the most", spot refactor candidates, or invokes /codebase-churn.