Awesome Claude Skills

Run a health check on an existing project: dependency audit, security scan, test runner detection, CI/CD evaluation, and missing configuration analysis. Maps the three execution ga

Act as a research ethics committee — stress-test a protocol the way an IRB / REC / HREC would. Reviews informed consent, risk-benefit balance, vulnerable populations, data privacy,

Adversarial smart contract security audit. Auto-selects 5-7 specialist agents based on contract features (from a roster of 12). Attacks from every relevant angle: SWC registry, sig

Audit de sécurité complet pour les projets Supabase. Lance un pentest automatisé qui vérifie RLS, buckets, auth, keys exposées, et génère un rapport avec remediation. Utiliser quan

Use when the user wants to set up Draftwise, scan a codebase for an overview, trace a specific flow through the code, draft a product spec from a feature idea, draft a technical sp

Numerical computing verification and optimization agent for Python/Dart. Provides expert analysis of ndarray/tensor operations, floating-point correctness, broadcasting validation,

Use Codemod CLI whenever the user wants to migrate, upgrade, update, or refactor a codebase in a repeatable way. This includes framework migrations, library upgrades, version bump

Identifies the architecture decisions that need ADRs and produces a prioritised adr-plan.md before technical design proceeds. Use when the user mentions "plan ADRs", "what ADRs do

Use when assessing blast radius of changes, when understanding WHY code was written a certain way, when planning risky modifications, or when a refactor could have hidden side effe

Contract-first API 설계 에이전트. OpenAPI 3.1 스펙 생성, API 버전 간 Breaking Change 감지, REST 설계 패턴 (페이지네이션, 필터링, 에러 응답 RFC 7807) 적용, Mock 서버 설정, Contract Test 스텁 생성을 수행한다. Activated by keyword

TDD development with Red-Green-Refactor cycle. Use to implement a feature by writing tests BEFORE the code. Trigger automatically when the user asks for TDD, wants to write tests f

Multi-model deliberation via mumo's MCP server. Best for contested architecture/product decisions, design reviews, pressure-testing a pre-launch spec, resolving tradeoffs with mult

Generate, revise, translate, and manage App Store / Google Play marketing screenshots. Full flow: initialize a .shots workspace, scrape App Store metadata, research the product fro

Audience-first content discovery via 10 psychologische dimensies. Genereert 50 content angles (5 per dimensie) vanuit het doelgroep- perspectief. Drie modes: angles (puur), keyword

SEO & GEO content linter — validates Markdown/MDX files for AI search visibility using 92 deterministic rules (35 GEO, 32 SEO, 14 content quality, 8 technical, 3 i18n). Runs an aut

Find relevant Telegram channels, groups, and admins as prospects without scraping member lists. Uses TGStat, Telemetr.io, web search (site:t.me), and Telegram Bot API to discover c

Draft personalized outreach messages for LinkedIn connections, hiring managers, or recruiters. Creates targeted messages using a hook + proof + proposal structure. Under 300 charac

Code qualitative data — interview transcripts, open-ended survey responses, field notes, documents, social media — using inductive, deductive, or hybrid approaches. Generates and r

Draft long-form manuscript sections — abstract, introduction, related work / literature review, methods, results, discussion, limitations, conclusion — from a methodology document

Локальная транскрибация аудиофайлов без отправки в облако. Используй когда пользователь просит транскрибировать запись, расшифровать аудио, сделать конспект встречи, преобразовать

Veille tech francophone pour développeurs. Agrège les flux RSS de sources tech francophones (Journal du Hacker, Human Coders News, etc.) et produit un récap des articles récents tr

Interactive KubeCon CFP submission writer. Guides through topic selection, title crafting, abstract writing, and benefits section using acceptance data from 1,100+ talks across 7 K

Reviews lyrics and prose for AI-written patterns (abstract noun stacking, over-explained metaphors, cliche escalation, missing idiosyncrasy, prose AI tells). Advisory Warning/Info

Polishes raw Suno audio by processing per-stem WAVs (vocals, backing_vocals, drums, bass, guitar, keyboard, strings, brass, woodwinds, percussion, synth, other) with targeted clean

Validates all pre-generation gates before sending tracks to Suno. Checks sources verified, lyrics reviewed, pronunciation resolved, explicit flag set, style prompt complete, and ar

Turn a paper (or several, a thesis, a body of work) into an academic talk — outline, per-slide content, speaker notes, opening hook, single take-home message, backup slides for Q&A

Design a direct, conceptual, or generalization replication of a published study. Walks through identifying the target effect, extracting the original design with enough fidelity to

Advise on quantitative and qualitative research methodology — design, sampling, validity, reliability, measurement, ethics, analysis plan, and — mandatory in every methodology outp

Manage the beads backlog for this project. Use when the user wants to review or triage open issues, reprioritize the backlog, identify obsolete issues to close, investigate a topic

Orchestrate multi-agent development sprints with wave-based parallelism. Use when the user wants to plan a swarm sprint, partition work into file-disjoint waves, map file contentio

Generate, sharpen, and pressure-test research ideas — research questions, hypotheses, study angles, novel contributions, and contrarian framings. Pushes beyond obvious next steps t

Assess an existing project's stack for agent-friendliness using the 4 quality gates (typed, convention-based, popular in training data, well-documented) as an evaluation lens. Dete

Facilitate a structured discovery conversation that turns an idea — greenfield or brownfield — into shape-notes.md, the input to /10x-prd. Auto-detects context type from project ma

Pick a starter and a stack for a greenfield project after the PRD is written. Reads context/foundation/prd.md, opens with a Q0 path-fork (recommended default for the (product_type,

Generate prototype React components + Storybook stories from Figma URLs. 6-phase pipeline: figma_to_react → UntitledUI matching → prototype synthesis → verify → storybook integrati

Generate context/foundation/prd.md from shape-notes.md (or raw notes) against the locked PRD schema. Auto-routes to greenfield (10 sections) or brownfield (11 sections) template ba

Autonomous batch task execution with PRD parsing, task decomposition, and continuous execution until all tasks complete. Uses /orchestrator internally. Stops only for major failure

Generate a time-windowed pulse report on what users experienced and how the product performed - usage, quality, errors, signals worth investigating. Use when the user says 'run a p

Interactive wizard to create PRD or task lists for /task-batch. Uses /clarify and /ask-questions-if-underspecified for precise task definition. Use when: (1) preparing batch execut

Scan a repo for mixed ADRs, PRDs, SPECs, and DOCs and bootstrap or merge the full .planning/ setup from them. Classifies each doc in parallel, synthesizes a consolidated context wi

Write PRD — Product Requirements Documents with structured 8-section templates, user stories, acceptance criteria, and value proposition validation. Use when writing PRDs, defining

(Who) Claude Code or any user. (What) Archive all non-core skills from {project_root}/.claude/skills/ to .gem-squared/external-skills/. (When) 1. At init-session (automatically), 2

Connect a CMS to toprank SEO tools. Guides users through configuring WordPress, Strapi, Contentful, or Ghost — tests the connection, and writes credentials to .env.local. Once set

Этот скилл MUST быть вызван для всех операций с MXL-макетами и шаблонами объектов 1С: создание MXL из JSON (compile), получение JSON из MXL (decompile), добавление макета к объекту

Bilateral SYNERGY/UPSTREAM reconciliation across sibling projects. Use when the user wants to sync sibling SYNERGY/UPSTREAM files, compare both sides to surface drift, find recipro

Scaffold a project into the current working directory after the tech stack has been picked. Reads context/foundation/tech-stack.md (the hand-off written by /10x-tech-stack-selector

User-invoked skill to scan the current project, detect its tech stack, map technologies to installed rad-* plugins, identify missing plugins, inject stack-aware guidance into CLAUD

Manage cross-project synergy tracking between sibling projects. Use when the user wants to log a shared pattern, a divergence, an extraction candidate, or something a sibling proje

Iterative title tag and headline optimizer with multi-round refinement. Generates 5 variations per round across 3 rounds (diverge, refine, polish) with transparent scoring on 7 dim

Применять при переписывании текстов, сгенерированных LLM-агентами (отчеты, README, доки, письма, посты), в живой человеческий стиль. Триггеры - пользователь пишет «убери AI-стиль»,

Экспертная арена — динамический подбор реальных экспертов, исследование, независимая оценка вариантов с перекрёстным обогащением. Используй этот скилл когда пользователь спрашивает

Multi-agent code review using Agent Teams. Summons up to 8 built-in Ashes (plus custom Ash from talisman.yml), each with their own dedicated context window. Handles scope selection

Ověř výsledek nezávislým modelem od jiného providera — Codex (OpenAI), Gemini (Google) nebo Claude Code (Anthropic). Použij na fráze: 'získej druhý názor', 'ověř z jiného modelu',

Hierarchical plan execution — orchestrates parent/child plan decomposition with dependency DAGs, requires/provides contracts, and feature branch strategy. Use when a plan has been

Bridge THIS Claude Code or Codex session to Telegram, Discord, Feishu/Lark, QQ, or WeChat so the user can chat with Claude from their phone. Use for: setting up, starting, stopping

(What) Search .claude/skills/ and .gem-squared/external-skills/ for skills and skill directories relevant to the current task. (When) During /plan-work when domain capability is ne

Critique a Claude implementation plan before approving execution. Spawns parallel persona subagents (Skeptic, Architect, Verifier) to evaluate the plan against the codebase and ret

Imports a Claude Design (claude.ai/design) handoff bundle and scaffolds the proposed components into the project. Accepts a bundle URL or local file, parses and validates the schem

Refresh plugins previously installed by skills-toolkit by re-fetching their GitHub sources and presenting updated .plugin files to Cowork. Use when the user says "update my loaded

End-to-end Claude Design handoff to pull request: imports a handoff bundle from claude.ai/design, generates Storybook stories and Playwright tests, runs diff-aware browser verifica

Save the current in-conversation version of loaded skills as a new plugin. Use when the user says "save these skills", "save my iterated skills", "save loaded", "package what I've

IM bridge for AI coding tools — chat with Claude Code / Codex from Telegram, Discord, or Feishu. Approve permissions, get streaming responses, manage sessions from your phone. Use

Resolve a specific GitHub PR review comment. Supports review thread comments (line-level) and issue comments (PR-level from bots). Handles copilot, gemini-code-assist, coderabbitai

Manage Git branches and pull requests using git-spice (gs). Use when user says "/gs", "create branch", "new branch", "switch branch", "checkout branch", "rebase branch", "update br

Этот скилл MUST быть вызван для всех операций с внешними обработками 1С (EPF): создание (init), сборка (build), разборка (dump), добавление формы (add-form), регистрация в БСП (bsp

(What) Format a SUCCESS WP or unit-contract into a TPMN SKILL.md and store in .claude/skills/. (When) After /archive-work SUCCESS, or anytime human says "extract this as a skill" o

Package skills already installed in your Cowork session as a downloadable .zip file you can save to disk and share. Use when user says "share my skills", "export installed skills",

Claude-powered ecommerce business review toolkit for D2C stores. Single command: review. Analyzes order transaction data across multiple time periods (30d/90d/365d), produces KPI t

Interactively create a new Jira issue (and optional sub-tasks with dependency links) from conversation context. Gathers details via dialog, proposes a sub-task breakdown when the s

Discover requirements from a free-form natural-language topic. Searches the codebase, asks batched clarifying questions, then writes a structured requirements document with an issu

Gather phase context through adaptive questioning before planning. Use --all to skip area selection and discuss all gray areas interactively. Use --auto to skip interactive questio

Load skills from a GitHub repository into the current Cowork session as a unified plugin. Use when the user says "load skills from GitHub", "import skills from repo", "add skills f

Этот скилл MUST быть вызван для всех операций с подсистемами и командным интерфейсом 1С: создание подсистемы (compile), редактирование состава (edit), настройка командного интерфей

Locally merge a Jira task branch into the base branch without a remote or PR. Handles merge strategy selection, Jira status transition, and MCP config removal. Outputs worktree cle

Pull latest upstream changes from vendor subtrees into this project. Use when the user says 'sync vendor', 'pull upstream', 'update subtrees', 'vendor pull', 'vendor sync', 'sync v

Plan-vs-implementation deep audit using Agent Teams. Parses a plan file (or inline description), extracts requirements, and summons 4 Inspector Ashes to measure implementation comp

Fetch assigned high-priority Jira tasks and set up git worktrees for each. Supports three argument modes - count (bulk init), issue key (sub-task analysis), or natural language. Us

Этот скилл MUST быть вызван когда есть design.md и нужно разбить доработку на атомарные задачи (2-5 мин) с точными путями файлов и критериями проверки в tasks.md. SHOULD также вызы

Post Rune review findings to a GitHub PR as a formatted comment. Parses TOME.md findings, formats as collapsible markdown, posts via gh api. Use after /rune:appraise or /rune:arc t

Batch resolve all unresolved PR review comments. Fetches review threads AND issue comments (bot feedback) with pagination. Categorizes, auto-resolves outdated, groups related comme

Extract design DNA from existing app screenshots or live URLs using Google Stitch. Produces color palettes, typography specs, spacing tokens, and component patterns as design-token

Answer Engine Optimization (AEO) audit and SERP analysis for AI-generated answers. Analyzes pages for AEO readiness (structured data, FAQ patterns, heading hierarchy, meta quality)

Search 21st.dev component registry for production-ready React components. Finds components by natural language description, filters by framework and style system, returns ranked re

Этот скилл MUST быть вызван для всех операций с внешними отчётами 1С (ERF): создание (init), сборка (build), разборка (dump). SHOULD также вызывать при любой работе с ERF-файлами и

Run tests for a Jira task and report results to Jira. Supports Playwright E2E tests, unit tests (vitest/jest), and custom test commands. Generates test reports and posts summaries

Start working on a Jira task. Fetches issue details, creates a feature branch or git worktree, transitions the issue to "In Progress", and sets up the development context. Use when

Этот скилл MUST быть вызван когда пользователь просит обновить БД, применить конфигурацию, выполнить UpdateDBCfg. SHOULD также вызывать после db-load-xml или db-load-cf для примене

Upgrade toprank plugin to the latest version. Updates the marketplace repo, installs the new version to the plugin cache, and updates installed_plugins.json. Use when asked to "upg

Этот скилл MUST быть вызван когда нужно создать управляемую форму с нуля по JSON-определению элементов. SHOULD также вызывать когда структура формы хорошо определена и требует гене

Cross-platform, hardware-adaptive system optimizer. Auto-detects macOS / Linux / WSL / Windows (MINGW/Cygwin/MSYS2) and CPU/RAM/disk/GPU profile, then picks the right cleanup strat

(What) Search proven unit-contracts and live work-plans for reusable patterns. (When) Before /plan-work, or anytime human asks "have we done something like this before?" (Why) Prov

Multi-LLM consensus engine. Queries multiple AI models and synthesizes a single answer using strategies like voting, judge synthesis, and multi-round debate. Use when the user want

Learn patterns from a specific GitHub repository. Clones, analyzes code structure, extracts patterns, and populates procedural memory. Use for: targeted learning from known quality

(What) Mutate a live WP — add, modify, reorder, or abort PENDING unit-works. (When) Mid-execution discovery: scope changed, new unit needed, CONTRACT needs revision. (Why) Sanction

Full inbox management across all channels — WhatsApp (wacli), Email (Gmail MCP), Slack (MCP), Telegram (user-auth MCP), Discord (webhook + REST read), Notion (MCP — comments, menti

Этот скилл MUST быть вызван когда нужно создать новую роль 1С с набором прав на объекты. SHOULD также вызывать при настройке разграничения доступа для новой функциональности. Do NO

Run code review and gap analysis on changes for a Jira task, then post results to Jira. Compares design document against implementation and reviews code quality. Use when user says

Generate a design document for a Jira task. Analyzes the codebase, references the planning document, then generates a structured design document. Use when user says "design task",

Configure Code Connect dans un projet pour mapper les composants Figma vers le code existant. Utiliser pour initialiser l'intégration Figma dans un projet, quand l'utilisateur dit

(What) Verify results against CONTRACTs — determine STATE (SUCCESS|FAILURE) per unit. (When) After each unit completes (inline from /proceed-work) or after all units complete (batc