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

  • Code reviewer

    Ortus-Solutions/skills/code-reviewer Skill

    no license0★ repo

    Use when performing high-signal code reviews focused on correctness, security, maintainability, performance, and test coverage risk. Invoke for pull request review, architecture drift detection, bug risk assessment, and actionable feedback with severity-ranked findings.

  • Explaining code changes

    msewell/agent-stuff/skills/explaining-code-changes Skill

    0★ repo

    Creates self-contained HTML learning walkthroughs of code changes with background, intuition, code walkthroughs, embedded diagrams, and a self-check quiz. Use when the user asks to explain a diff, branch, commit, pull request, PR, or code change for learning, onboarding, or handoff. Not for code review, approval/readiness verdicts, or merge decisions.

  • Quizzing before approving

    msewell/agent-stuff/skills/quizzing-before-approving Skill

    0★ repo

    Administers a structured comprehension quiz on a scoped code change to verify the reviewer genuinely understands it before approving or merging. Generates 5–7 questions in three batched rounds using a fixed rubric (restatement, alternatives, invariant, failure-mode, scope, targeted trickiest lines), grades strictly, provides context without revealing answers on failures, and loops until the user passes. Use when the user wants to be quizzed on a diff, wants to verify their understanding before merging or approving AI-generated code, wants a comprehension check before approving, or says things like "quiz me on this change", "test my understanding of this diff", "quiz before approve", or "quiz me before I merge."

  • Reviewing pull requests

    msewell/agent-stuff/skills/reviewing-pull-requests Skill

    0★ repo

    Reviews GitHub pull requests end-to-end using gh CLI. Gathers PR metadata, diff, linked issues, and CI status. Analyzes code for bugs, security risks, performance issues, and goal alignment against repo conventions. Runs available lint, type-check, and test commands locally. Produces a prioritized report with severity-classified feedback (blocking, suggestion, nit, praise) and an approve/request-changes verdict. Optionally posts the review to GitHub after user confirmation. Use when asked to review a PR, check a pull request, audit code changes, evaluate if a PR is ready to merge, provide code review feedback, assess PR quality, or when the user says review PR #N, is this PR ready, look at this pull request, or code review.

  • Tweet review

    msewell/agent-stuff/skills/tweet-review Skill

    0★ repo

    Reviews draft tweets and provides engagement optimization recommendations with improved alternatives. Use when the user has a draft tweet or thread and wants feedback on how to maximize reach, replies, and engagement on Twitter/X. Primarily niche-agnostic with additional guidance for tech Twitter.

  • Using git notes for ai context

    msewell/agent-stuff/skills/using-git-notes-for-ai-context Skill

    0★ repo

    Reads, writes, and configures git notes and trailers for AI agent context — attribution, decision reasoning, prompts, and CI/CD metadata. Sets up namespace conventions, hook automation, team sync, and compliance. Use when storing AI attribution in git, setting up git notes for AI tracking, querying constraints or directives before modifying code, configuring notes sync for a team, choosing between git notes and trailers, or when the user mentions git notes, git trailers, AI attribution, AI provenance, Lore protocol, or decision context in commits.

  • Writing git commit messages

    msewell/agent-stuff/skills/writing-git-commit-messages Skill

    0★ repo

    Writes and reviews git commit messages following Conventional Commits and the seven fundamental rules. Produces well-formatted, atomic, automation-friendly commit messages. Use when writing a commit message, reviewing commit messages, committing code changes, or when the user mentions git commits, commit messages, or changelogs.

  • Build

    Pamacea/smite/plugins/studio/skills/build Skill

    0★ repo

    MANDATORY entry point for ALL implementation tasks in smite project. Invoke FIRST when building features, implementing functionality, or creating components - provides 12-flag system (--speed, --scale, --quality, --team, --clean, --test, --debug, --docs, --git, --branch, --profile, --types) with auto-detection, memory integration, and quality metrics. Specific phrases: 'build feature', 'implement this', 'create component', 'add functionality', 'develop API'. (user)

  • Multi review

    Pamacea/smite/plugins/studio/skills/optional/multi-review Skill

    0★ repo

    MANDATORY gate BEFORE merging PR or deploying. Orchestrates parallel review by 4 specialized agents (security, performance, testing, documentation) with consolidated report. Specific phrases: 'review this PR', 'security audit', 'performance check'.

  • Refactor

    Pamacea/smite/plugins/studio/skills/optional/refactor Skill

    0★ repo

    MANDATORY gate before ANY refactoring task. Systematic validation with 6 modes (--quick, --full, --analyze, --review, --resolve, --verify) plus 3 specialized modes (--profile for performance, --security for vulnerabilities, --types for TypeScript). Specific phrases: 'refactor this', 'clean up code', 'improve this function'.

  • Refactor

    Pamacea/smite/plugins/studio/skills/refactor Skill

    0★ repo

    MANDATORY gate before ANY refactoring task in smite project. Invoke FIRST when cleaning up code, improving structure, or optimizing - provides systematic validation with 6 modes (--quick, --full, --analyze, --review, --resolve, --verify) plus 3 specialized modes (--profile for performance, --security for vulnerabilities, --types for TypeScript) with auto-team activation for complex refactors. Specific phrases: 'refactor this', 'clean up code', 'improve this function', 'optimize this', 'restructure this module'. (user)

  • Specs checker

    chawkitariq/fidely/.claude/skills/specs-checker Skill

    0★ repo

    Vérifie qu'une implémentation respecte les specs de PLANING.MD (source de vérité Fidely). Déclencher quand : ajout feature, modification composable/page, avant commit important, si une règle métier semble violée, si un élément hors-scope est introduit. Mots-clés : client_id immuable, points ≥ 0, surplus récompense, RGPD, IndexedDB, QR code reset, Zod validation, light mode, switch mode, confirmation suppression, CardForm, useDB, consumeReward, updatePoints, hors-scope, PLANING.MD.

  • Spec driven initiation engineer

    papanito/ai-skills/skills/spec-driven-initiation-engineer Skill

    no license0★ repo

    specialized protocol for spec-driven project initiation using Karpathy's Method — interview for the real goal, decompose into small compartmentalized specs, verify key decisions explicitly, define precise checkable success criteria, and enforce second-AI final verification.

  • Coldbox reviewer

    ColdBox/skills/coldbox/coldbox-reviewer Skill

    no license0★ repo

    Use this skill when reviewing ColdBox application code for correctness, security, performance, testability, and adherence to ColdBox conventions. Covers handlers, services, models, interceptors, modules, routing, ORM/OBM usage, REST APIs, dependency injection patterns, and common anti-patterns to flag during pull request reviews.

  • Code review

    Victoriakaey/build-reliable-agents/skills/code-review Skill

    0★ repo

    Use when reviewing code — either Claude reviews your code and produces a structured report, or Claude guides you through reviewing someone else's code. Default mode: Claude performs the review and produces a report organized by severity. Second mode: guided self-review with a structured checklist and probing questions. Covers correctness, security, performance, maintainability, and AI-specific concerns for LLM applications.

  • Experiment driven development

    Victoriakaey/build-reliable-agents/skills/experiment-driven-development Skill

    0★ repo

    Use at the start of any implementation task on an LLM system. A 10-step process from evidence collection to git commit. Prevents the most common failure mode in LLM development: writing code based on assumptions instead of observed system behavior. Use for any change — prompt tuning, node logic, routing, architecture — not just experiments.

  • Scope guard

    owen-dev-6174/bodhisattva-skills/skills/scope-guard Skill

    0★ repo

    Use when making code changes to prevent scope creep, over-engineering, and unrelated modifications beyond what was asked. Activates on any task involving file edits to enforce strict scope boundaries, flag unnecessary extras, and ensure changes match the request — nothing more, nothing less. Prevents bloat, YAGNI violations, and unsolicited refactoring.

  • Review

    RhythmMittal19/claude-config/skills/review Skill

    0★ repo

    Review current branch changes for bugs, security, and quality before merging.

  • Toolchain discovery

    jsynowiec/claude-toolkit/plugins/stackshift/skills/toolchain-discovery Skill

    0★ repo

    Identifies build, test, lint, type-check, and formatting tooling in a repository. Use before running verification steps or assessing a project's development setup.

  • Version checker

    jsynowiec/claude-toolkit/plugins/stackshift/skills/version-checker Skill

    0★ repo

    Determines latest stable or LTS versions of runtimes (Node.js, Python) and packages (npm, PyPI), checks EOL status, identifies upgrade paths, and looks up the VS Code compatibility matrix. Use when checking if project versions are outdated, need upgrading, or determining minimum VS Code engine version after a runtime change.

  • Setup

    pedroberaldo87/pedro-plugins/plugins/context-guard/skills/setup Skill

    no license0★ repo

    Configura o plugin context-guard — registra o wrapper de statusLine e as env vars no settings.json (os hooks de reset/guarda vêm do próprio plugin via hooks.json). Rode 1× após instalar o plugin.

  • Grill me

    pedroberaldo87/pedro-plugins/plugins/grill-me/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 23 other repositories

  • Grill with docs

    pedroberaldo87/pedro-plugins/plugins/grill-with-docs/skills/grill-with-docs Skill

    no license0★ repo

    Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

    The same file is in 8 other repositories

  • Intent guard

    pedroberaldo87/pedro-plugins/plugins/intent-guard/skills/intent-guard Skill

    no license0★ repo

    Use quando o usuário digitar /intent-guard (status, baixa N, off, on, projeto-off, projeto-on), perguntar o que está no caderno de pedidos, pedir para arquivar um pedido, ou quando o gate de entrega do intent-guard bloquear o Stop. Mostra e opera o ledger de pedidos verbatim e a auditoria independente de entrega. Plugin EXPERIMENTAL — baixa automática por auditoria pode migrar para baixa manual.

  • Ship

    pedroberaldo87/pedro-plugins/plugins/ship/skills/ship Skill

    no license0★ repo

    Use quando o código está pronto pra ir pra produção — roda lint, type-check, commit, push e deploy num fluxo disciplinado. Dispara em "ship", "manda", "deploya tudo". No fim de um ciclo de implementação, OFEREÇA pra dar ship — nunca deploye por conta própria sem o usuário pedir.

  • Privacy guard

    alainlebret/claude-agents/higher-ed-teaching-agents/skills/privacy-guard Skill

    0★ repo

    Detects and redacts personally identifiable or sensitive data in submissions and generated reports before evaluation outputs are finalized.

  • Spotter

    missionbuilt/loadout/spotter Skill

    0★ repo

    The Spotter — a skill for reviewing, building, and iterating on B2B product epics across nine areas spanning empathy, competitive landscape, AI decisions, governance, and post-launch ownership. Use when asked to review, critique, strengthen, draft, or push forward an epic.

  • Memory retro

    ztnkv/personal-operating-system/.claude/skills/memory-retro Skill

    0★ repo

    Orchestrator for writes into memory. Analyzes the source (the current conversation OR an external file/text passed as an argument), decides which new facts, changes, contradictions, and deprecations should be recorded in memory/, builds a diff proposal, and confirms it with the user. Only after an explicit "yes" does it call memory-write to apply changes. Triggered four ways — (1) explicit user command ("sum it up", "write down what you learned", "update memory", "/memory-retro"); (2) the agent's own initiative when meaningful new facts or contradictions surface in the dialog; (3) **mandatory auto-run from grill-me** — after a grill session completes, memory-retro always runs without re-asking the user; (4) bootstrap mode for bulk import from an external file (chat history dump, personal notes, session transcript) — fully autonomous, no dialog confirmations, all edge cases resolved by deterministic heuristics with confidence demoted to low as a signal for later review. In normal mode, never writes to memory silently.

  • Json schema validator

    baronguyen001/ai-automation-skills/skills/json-schema-validator Skill

    0★ repo

    Validate a dict/JSON payload against a useful subset of JSON Schema (type, required, properties, items, enum, min/max, length) with zero dependencies, returning readable errors. Use when the user wants to validate a webhook payload, API response, or config against a schema, or gate bad data before processing - without adding the jsonschema package.

  • Pr body formatter

    baronguyen001/ai-automation-skills/skills/pr-body-formatter Skill

    0★ repo

    Generate a complete GitHub PR body with Summary, Changes, How tested, Test plan, and issue link from a branch diff plus issue reference, and never ship a placeholder body. Use for pr body template, format pr description, write a PR description, or API/CLI PR creation.

  • Review html

    GGGODLIN/claude-skills/skills/review-html Skill

    0★ repo

    把 spec.md / plan.md 渲染成繁中互動 HTML,方便 review 數百到上千行的長文件。讀懂 spec 段落語意、抽 semantic kind、用對應 component 重排,不是純 markdown 美化。Context-aware 翻譯:若 context 已有中文版 md 就用既有翻譯、否則 inline 翻。輸出單檔 HTML 到 ~/.claude/review-html/,自動開瀏覽器。

  • Review zh

    GGGODLIN/claude-skills/skills/review-zh Skill

    0★ repo

    Invoke when writing or editing English markdown content that will be shown to the user - skill SKILL.md files, CLAUDE.md edits in shared repos, plan files, README, design docs, technical proposals, RFC drafts. Generates a Traditional Chinese review copy at ~/.claude/review-zh/ so the user can review the gist in their native language. Skip when source is already Traditional Chinese, is pure code, or is trivial (commit messages, PR titles, short config comments). Also invokable manually via /review-zh.

  • Review epic gh

    semanticpixel/abc/plugins/abc/skills/review-epic-gh Skill

    0★ repo

    GitHub · Review-only counterpart to /abc:ship-epic-gh. Self-arming /loop that watches a GitHub parent issue's managed `## Sub-issues` task-list, reviews each child PR as it surfaces against the FULL epic context (parent spec + merged-sibling decisions + pending children's criteria), posts inline + spec-cross-referenced summary comments via the abc:reviewer subagent, and exits when the epic closes. Never merges. TRIGGER when the user says "/abc:review-epic-gh <owner>/<repo>#<n>", asks to "review this epic as it ships", or wants a standing reviewer session running parallel to /abc:ship-epic-gh.

  • Review epic

    semanticpixel/abc/plugins/abc/skills/review-epic Skill

    0★ repo

    Linear · Review-only counterpart to /abc:ship-epic. Self-arming /loop that watches a Linear parent issue's sub-issues, reviews each child's PR/MR (GitHub or GitLab, routed via the `repo:` label) as it surfaces against the FULL epic context (parent spec + merged-sibling decisions + pending children's criteria), posts inline + spec-cross-referenced summary comments via the abc:reviewer subagent, and exits when the parent reaches Done. Never merges. TRIGGER when the user says "/abc:review-epic PARENT-ID", asks to "review this epic as it ships" against a Linear parent, or wants a standing reviewer session running parallel to /abc:ship-epic.

  • Review sweep

    semanticpixel/abc/plugins/abc/skills/review-sweep Skill

    0★ repo

    Scan all open PRs (GitHub) and MRs (GitLab) the user authored, triage unresolved reviewer threads via the abc:triage subagent, present a dashboard of fixable vs judgment-required items, and apply confirmed fixes per PR/MR. Auto-detects which platforms to scan. TRIGGER when the user says "/review-sweep", "sweep my MRs", "triage my open PRs", or wants to bulk-process reviewer feedback. Designed to compose with /loop for periodic sweeps.

  • Review

    semanticpixel/abc/plugins/abc/skills/review Skill

    0★ repo

    Review a GitHub PR or GitLab MR with craft-level attention to semantic HTML, CSS architecture, accessibility, TypeScript patterns, and code quality. Auto-detects platform from URL or git remote. Proposes inline diff comments, shows them for approval, only posts what the user approves. TRIGGER when the user says "/abc:review", "review this PR/MR", "review <url>", or passes a PR/MR number.

  • Ship issue gh

    semanticpixel/abc/plugins/abc/skills/ship-issue-gh Skill

    0★ repo

    GitHub · GitHub-Issues sibling of /abc:ship-issue. Drives a GitHub issue (or list, or parent with task-list children) from `pending` to `merged` through the implement → PR → address-review → merge loop. Emulates Linear's state machine on top of GitHub Issues using the label conventions documented in scaffold-sub-issues-gh/github-conventions.md. TRIGGER when the user says "/ship-issue-gh <owner>/<repo>#<n>", asks to ship/land/drive a GitHub issue, or wants Claude to take a GitHub-tracked ticket through review to merge. Also trigger when resuming work on a GitHub issue with an open PR and pending reviewer comments. Self-arms its own `/loop` — the user invokes once and walks away.

  • Ship issue

    semanticpixel/abc/plugins/abc/skills/ship-issue Skill

    0★ repo

    Linear · Drives a Linear issue (or list, or parent with sub-issues) from Backlog to Done through the implement → PR → address-review → merge loop. TRIGGER when the user says "/ship-issue TICKET-ID", asks to ship/land/drive/autoland a ticket, or wants Claude to take a Linear issue through review to merge. Also trigger when resuming work on a ticket with an open PR and pending reviewer comments. Supports GitHub + GitLab and multi-repo parent issues via `repo:` Linear labels. Self-arms its own `/loop` — the user invokes once and walks away.

  • Scaffold

    Shankulkarni/react-native-ai-plugin/plugins/rn-ai/skills/scaffold Skill

    0★ repo

    Use when creating a new React Native app from scratch -- Expo SDK 52+ managed workflow, NativeWind v4, Expo Router, React Query, zustand-x, EAS config, ESLint/Prettier/Husky.

  • Nebo git workflow

    lifenewjob/nebo-claude-skills-public/skills/nebo-git-workflow Skill

    0★ repo

    GIT-WORKFLOW. Triggers: git commit, PR, code review, branch, worktree, issue triage

  • Scour

    kennykankush/skillpack/plugins/workbench/skills/scour Skill

    no license0★ repo

    The reality-check hotline. Mid-conversation, leave the closed room and go to the internet to ground what was just said against how the world actually does it. Two faces - verify (we concluded something confidently; pull the load-bearing claims and check each against real fetched sources - confirmed / wrong / oversimplified / outdated / no-consensus) and discover (we're stuck or starting fresh; find the dominant pattern and the gotchas). Use when the user says "scour this", "are we on the right page?", "is this actually how people do it?", "go check the internet", "make sure we're not confidently wrong", or asks how something is normally done. Fast and conversational like isomorph - never writes files, never answers from memory.

  • Fact check workflow tw

    richardvt/claude-skills-journalism-tw/journalism-core-tw/skills/fact-check-workflow-tw Skill

    no license0★ repo

    台灣新聞事實查核工作流程 (繁體中文/台灣專用版,對應 upstream fact-check-workflow 的美國版)。涵蓋:主張提取與優先級、台灣主要資料來源 (政府開放資料、機關澄清專區、IFCN 認證查核機構)、台灣主要查核來源 (台灣事實查核中心、MyGoPen、Cofacts、蘭姆酒吐司) 與 LINE 訊息查證、證據蒐集與存檔、求證來源、評等量表 (6 級制)、更正流程、法律風險 (《刑法》§310 誹謗罪、《社會秩序維護法》§63 散布謠言)、常見台灣假訊息類別 (政治/兩岸/健康/食安/詐騙)、發稿前 checklist。涉及事實查核、查證、闢謠、求證、評等、發稿前審核時觸發。投入查核報導、調查報導、新聞編輯部、媒體素養教育之記者必備。

  • Interview transcription tw

    richardvt/claude-skills-journalism-tw/journalism-core-tw/skills/interview-transcription-tw Skill

    no license0★ repo

    台灣採訪錄音轉錄與引語管理工作流程 (繁體中文/台灣專用版,對應 upstream interview-transcription 的美國版)。涵蓋:錄音檔管理、Whisper 中文模型 (large-v3、台/客/原民族語)、雅婷逐字稿、台灣商用轉錄服務、引語提取、時間軸對照、查證用 quote database、轉錄品質檢核、與 source-verification-tw / fact-check-workflow-tw 整合。錄音轉逐字稿、引語對照查核、訪談檔案管理、語音檔保存時觸發。記者、查核員、研究員、法務、紀錄片工作者必備。

  • Source verification tw

    richardvt/claude-skills-journalism-tw/journalism-core-tw/skills/source-verification-tw Skill

    no license0★ repo

    台灣新聞來源驗證與數位內容查證工作流程 (繁體中文/台灣專用版,對應 upstream source-verification 的美國版)。涵蓋:SIFT 方法、來源可信度評估、社群帳號驗證 (Threads/PTT/Dcard/LINE/FB/X)、反向圖片搜尋 (TinEye/Yandex/Google Lens)、影片驗證 (InVID/WeVerify)、C2PA 內容憑證、AI 生成內容與深偽偵測 (Hive AI/Reality Defender/法務部調查局)、台灣深偽真實案例 (2024 大選賴清德、高嘉瑜變造影片)、台灣資訊作戰研究機構 (DoubleThink Lab/IORG)、文件驗證、訪談前公開資料查證、法律風險 (《選罷法》§104 加重深偽條款、《刑法》§310、§315-1、《個資法》)。驗證社群帳號真偽、查證圖片影片、偵測 AI 生成內容、追蹤協同操作帳號、訪談前公開資料查證時觸發。記者、查核員、調查報導工作者必備。

  • Reactprinciples review

    sindev08/react-principles-skills/skills/reactprinciples-review Skill

    0★ repo

    Review React/TypeScript code against the React Principles cookbook. Invoke when the user asks to "review", "audit", or "check" their React code, or asks whether code follows React Principles. Reads the target file(s), flags violations across the documented principle categories (folder structure, TypeScript, components, state, forms, services, etc.), and reports findings with severity, reasoning, and concrete fix suggestions. Does not modify code.

  • Open pr

    kompiro/hane/skills/open-pr Skill

    0★ repo

    Open the pull request for the branch you are working on in the browser via `gh pr view --web`. Trigger when the user says: "PRを開いて", "PRをブラウザで", "PRを見せて", "open pr", "open the PR", "show me the PR", or similar phrases requesting to open the working pull request in the browser.

  • Review docs

    kompiro/hane/skills/review-docs Skill

    0★ repo

    Review documentation for broken links and cross-document consistency issues. Trigger when the user says: "ドキュメントレビュー", "docs review", "review docs", "リンク切れ確認", "ドキュメントの整合性", or similar phrases requesting documentation review.

  • Verify

    SashaMarchuk/claude-plugins/plugins/claude-migrate/skills/verify Skill

    0★ repo

    (beta) The verify gate - run node bin/verify-copy-page.cjs for a headless byte-exact copy-page check, spawn a cross-model brief==source audit on a different model than distilled the briefs, reconcile apply/*.result.json, flag injection-class briefs, and surface the kept==0 message. Re-runnable on demand. Use when the user types /claude-migrate:verify, or says "verify the migration", "re-run the copy-page check", "audit the briefs".

  • Write changeset

    brandtam/skills/skills/write-changeset Skill

    0★ repo

    Agent skills that follow the open Agent Skills spec — usable by Claude Code, Codex, and any compliant agent.

  • Write commit

    brandtam/skills/skills/write-commit Skill

    0★ repo

    Generate structured commit messages and optionally commit for the user. Checks for repo-level commit templates, handles staging decisions, and enforces user approval before any commit. Use when user says "commit", "write a commit message", "stage and commit", or invokes /write-commit.

  • Grill me

    rahul-kulkarni105/skills/skills/grill-me Skill

    no license0★ repo

    Aggressively challenge the user's plan, design, or claim. Use when the user says "grill me", "poke holes", "stress test", "challenge this", or otherwise invites adversarial scrutiny. Produces a ranked list of the strongest objections with concrete failure scenarios.

  • Gmt plot verify

    zhongpenggeo/gmt_plot_skill/.claude/skills/gmt_plot-verify Skill

    no license0★ repo

    GMT 图件布局校验技能。调用 `scripts/verify_plot.py` 脚本,对绘制完成的 GMT 图件进行两项核心检测: 图例/色标/比例尺是否覆盖主图框边框,以及是否放置在数据高密度区域。输出结构化的校验报告, 作为后续图件修饰的反馈指导。触发场景:GMT 图件已生成、需要检查图件布局质量、修饰前需要定位具体排版问题。

  • Claude code content validator

    mercedesperezcapilla-gif/claude-skills/skills/claude-code-content-validator Skill

    0★ repo

    Keeps Claude Code teaching content factually correct against Anthropic's live documentation. Claude Code changes fast, so any course, tutorial, lesson set, or internal guide about it drifts out of date: invented commands, renamed conventions, archived MCP packages, stale model ids. This skill reads your content, checks every Claude Code claim against the current official docs (never from memory), and returns a section-by-section validity report plus the safe fixes. Use before you publish or re-share any Claude Code training material. Works on any course or docs repo.

  • Content formatter

    mercedesperezcapilla-gif/claude-skills/skills/content-formatter Skill

    0★ repo

    Transforms dense lesson content into beautiful, web-ready, student-friendly format suitable for Notion, slides, or course platforms. Makes content scannable, visual, and easy to understand. Use when converting lesson content for student delivery.

  • Fs governance tier checker

    mercedesperezcapilla-gif/claude-skills/skills/fs-governance-tier-checker Skill

    0★ repo

    Helps financial services professionals think through the governance tier of an AI use case. Returns a suggested tier, the routing logic, governance considerations, and a plain-English checklist to prepare for an enterprise governance conversation. Use when scoping an AI tool, writing a business case, or before any governance review.

  • Sdlc release validator

    mercedesperezcapilla-gif/claude-skills/skills/sdlc-release-validator Skill

    0★ repo

    Validates that a software change has met all required SDLC gates before or after release in a regulated financial services environment. Checks 14 gates — change record, design agreement, code review, developer testing, independent testing, environment consistency, UAT sign-off, bug management, go/no-go, post-release validation, exceptions and manual interventions, rollback plan, impact communication, and security review. Returns a gate-by-gate status report and a structured sign-off block ready for audit. Use before a release to check readiness, after to confirm completeness, or during a review to evidence what was done.

  • Prepare review

    chris-peterson/anchor/skills/prepare-review Skill

    0★ repo

    Open the PR/MR on an already-pushed branch, rebase on the default branch if behind, and draft a description that tells reviewers WHY the change exists. Use when opening an MR/PR or creating a review.

  • Clerk webhooks

    bertbertov/claude-stack/skills/clerk-webhooks Skill

    0★ repo

    Receive and verify Clerk webhooks. Use when setting up Clerk webhook handlers, debugging signature verification, or handling user events like user.created, user.updated, session.created, or organization.created.

  • Critique

    bertbertov/claude-stack/skills/critique Skill

    0★ 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, automated anti-pattern detection, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.

  • Git workflow

    bertbertov/claude-stack/skills/git-workflow Skill

    0★ repo

    Git workflow patterns including branching strategies, commit conventions, merge vs rebase, conflict resolution, and collaborative development best practices for teams of all sizes.

    The same file is in 3 other repositories