Engineering
98,234 rows, by stacks then stars
dombrovsky/dombrovsky-claude-skills/skills/git-atomic-workflow Skill
0★ repoUse this skill when committing code changes, creating commits, using git, rebasing branches, or syncing with main/master. Provides atomic commit workflow for feature branches using fixup commits and interactive rebase with autosquash. Maintains clean git history while preserving meaningful development context. Use when the user mentions commits, git, rebasing, fixing history, or syncing branches.
quanpersie2001/pulse/.claude/skills/gitnexus/gitnexus-debugging Skill
no license0★ repoUse when the user is debugging a bug, tracing an error, or asking why something fails. Examples: "Why is X failing?", "Where does this error come from?", "Trace this bug"
The same file is in 5 other repositories
clever-cc-plugins/cc-handoff/plugins/cc-handoff/skills/handoff Skill
0★ repoCreate a handoff summary for continuing work on another machine. Use when the user says handoff, end session, switch machine, wrap up, save progress, or hand off.
spider-rs/spider-claude-plugin/skills/spider-crawl-scrape Skill
0★ repoCrawl websites, scrape individual pages, search the web, extract links, and bypass bot protection with Spider Cloud. Use when the user wants to pull content from one URL or many, gather documentation, search the web and fetch results, or get past anti-bot blocks — and wants the right parameters for clean, LLM-ready output.
realraelrr/handoff-skill/.codex/skills/handoff Skill
0★ repoCompact Codex and Claude Code sessions into concise handoff documents for fresh LLM agent sessions.
The same file is in 5 other repositories
vidit19sharma/neogents/skills/map Skill
0★ repoDeep codebase mapping. Fans out parallel keymaker recon across an existing repository and has neo-shadow synthesize the findings into ARCHITECTURE.md. Use when adopting NEO in a mature codebase, when ARCHITECTURE.md is empty or stale, or when the user asks to map or document the codebase structure.
fathanghani864/oh-my-openclaw/src/presets/apex/skills/prompt-guard Skill
no license0★ repoRuntime security scanner for AI agents. Detects prompt injection, jailbreaks, and 600+ attack patterns offline.
bdmorin/.claude/skills/playwright-automation Skill
no license0★ repoExecute complex browser automation using Playwright Python. Use for video recording, multi-page navigation, data extraction. Triggers on "browser script", "record video of website", "extract data from webpage".
magnusrodseth/aoc-2025/.claude/skills/daily-reporter Skill
no license0★ repoGenerate comprehensive daily status reports after solving AoC puzzles. Documents success/failure, challenges faced, retry attempts, execution time, and insights for workflow tuning. Use after completing each day's puzzle to provide developer feedback on automation effectiveness.
YoniChechik/claude-code-config/skills/build-tests Skill
no license0★ repoPlan and build tests for the current feature
gagip/gagip-dev/.claude/skills/release Skill
no license0★ repo개발 전용 Claude Code 플러그인
RainLib/full-stack-skill/.claude/skills/dev-workflow Skill
0★ repo全栈开发工作流编排器,按 8 阶段顺序执行:需求分析 → 技术选型 → 技术评审 → 程序设计 → 任务拆分 → 单元测试 → 代码开发 → 自我验证。
ijufumi/claude-skills/skills/code-review/skills Skill
no license0★ repoGitHub Pull Request(またはローカルの差分)のコードレビューと動作確認を行うスキル。**既定の通常モード(normal)では 1 つの subagent A_review が 10 観点すべてを横断的にレビューし、1 つの subagent C_review がそのメタレビュー(検証)を行う**。ユーザーが「詳細に」「詳しく」「観点別に」「観点ごとに」「detailed」「徹底的に」「thoroughly」などのキーワードを依頼文に含めた場合のみ、**詳細モード(detailed)**に切り替わり、Claude Code 組み込みの `/review` コマンド由来の 5 基本観点(コード正確性 / プロジェクト規約準拠 / パフォーマンス / テストカバレッジ / セキュリティ)と、リポジトリ固有・品質深掘りの 5 観点(エラーハンドリング / 可読性・保守性 / シンプル化 / リポジトリ共通観点 / PR 固有観点)の最大 10 観点に分割し、**1 観点 1 subagent で並列レビュー / 観点ごとに別 subagent で評価**する。実行前に必ずユーザーへ 3 点を確認する — ①レビュー対象を **GitHub の PR から取得するか、ローカルの git diff から取得するか**、②**動作確認(テスト/lint/型チェック/ビルド等の実行検証)を実施するか、静的レビューのみに留めるか**、③レビュー結果を **GitHub にコメント投稿するか、コンソール表示のみに留めるか**。差分を取得し、🔴 MUST / 🟡 SHOULD / 🟢 NICE TO HAVE の 3 段階で指摘を分類した上で、選択された出力先に結果を提示する。動作確認(テスト/lint/型チェック/ビルド等の実行検証)は独立した subagent B として並列に走らせる。リポジトリ共通のレビュー観点(docs/REVIEW.md)と PR 固有のレビュー観点(PR 本文の `<!-- REVIEW_FOCUS -->` ブロック)も観点として扱う。GitHub の操作は MCP(`mcp__github__*` / `mcp__github_inline_comment__*` / `mcp__github_comment__*`)が使える場合は MCP を優先し、使えない場合は `gh` CLI にフォールバックする。ユーザーが「コードレビュー」「code review」「PR レビュー」「プルリクエストのレビュー」「レビューして」「review this PR」「指摘して」「レビューコメント」「MUST / SHOULD / NICE TO HAVE」「レビュー観点」「差分レビュー」「動作確認」「ローカルレビュー」「手元の変更をレビュー」などに言及した場合にこのスキルを使うこと。PR 番号や PR URL が渡された時、あるいは「この PR をレビューして」「今の変更をレビューして」といった依頼にも対応する。
danielsitek/skills/skills/handoff-close Skill
0★ repoClose a resolved handoff by number and delete its file from .handoffs/. Use this skill whenever the user is done with a parked task and wants to clear it — phrases like "close handoff 2", "handoff 3 is done", "remove that handoff", "delete handoff-0001", "ten handoff je hotový". Trigger when the user signals a handoff is finished and should be removed. This skill deletes a file, so it confirms before deleting unless the user gave an unambiguous numbered instruction.
pambrose/pambrose-claude-plugins/linear-integration/skills/create-linear-design-issues Skill
no license0★ repoThis skill should be used when the user asks to "review design", "find design problems", "check architecture", "find tight coupling", "find god classes", "audit separation of concerns", "review code structure", or wants a systematic codebase review focused on design and architecture issues that files findings as Linear issues.
sujeet-pro/agents-devkit/.cursor/skills/prj-add-adk-skill Skill
0★ repoAdd a skill to the adk plugin, create a new /adk: command, modify an existing adk skill's workflow / rules, or register a skill in the marketplace. Derives the house convention from the repo itself (AGENTS.md, SAFETY.md, existing skills) rather than memory. Writes repo files only — never publishes, never commits.
Alanless123/skillsmp-skills/mcp-config-reviewer Skill
no license0★ reporeview mcp configuration and implementation for security, correctness, and operational risk. use when chatgpt is asked to inspect mcp.json, claude desktop or codex mcp settings, server launch commands, oauth settings, token handling, tool exposure, startup failures, stdio handshake errors, timeout errors, or pull requests that add or modify mcp servers. especially useful for finding dangerous defaults, over-permissive tools, token forwarding, missing audience validation, unsafe stdio commands, hardcoded secrets, and weak review reports.
arova-ai/agent-skills/email-server-diagnostics Skill
0★ repoDiagnose and analyze self-hosted email server configurations. Checks DNS records (MX, SPF, DKIM, DMARC, MTA-STS, TLSRPT, rDNS, autodiscover, BIMI, DANE/TLSA), TLS certificates (HTTPS, IMAPS, SMTPS, protocol versions), port connectivity, IP/domain blacklist status, SPF lookup limits, open relay, IPv6 consistency, and server internals (Postfix, Dovecot, mailboxes, DKIM keys, mail queue). Also validates against Google/Yahoo/Microsoft 2024-2025 bulk sender requirements. Use this skill whenever the user mentions email server health checks, mail deliverability issues, DNS configuration for email, email authentication setup (SPF/DKIM/DMARC), mail server migration, diagnosing why emails go to spam or get rejected, or checking compliance with Gmail/Outlook sender policies. Also trigger when the user asks to set up or verify a mail domain, check email security, audit an existing mail server (mailcow, iRedMail, Postfix, etc.), or investigate email bounces.
JPDesignTech/graphite-skill/skills/graphite Skill
0★ repoManage Graphite stacked PRs. USE THIS SKILL when the user invokes "/graphite", "/gt", "/stack", says "debug my stack", "get stack comments", "resolve restack conflicts", "create a stack", "submit stack", "sync graphite", "restack", "debug PR", "PR comments", or "stack status". Provides four workflows for stack debugging, comment aggregation, conflict resolution, and general Graphite operations.
eshraw/design-system-as-text/skills/initialize-ds Skill
0★ repoInitializes a design system from Figma into structured markdown and CSS files. Use when user says "initialize design system", "set up DS", "import from Figma", or runs /initialize-ds.
mmjclayton/claude-starter-kit/Windows/skills/prompt-builder Skill
no license0★ repoBuild high-quality structured prompts through a guided interview. Use this skill whenever the user wants to create a prompt, write a prompt, build a prompt template, craft instructions for an AI, design a system prompt, or says things like "help me prompt this", "I need a good prompt for X", "prompt engineering", or "write me a prompt that does Y". Also trigger when the user describes a task they want an AI to do well and needs help structuring the request - even if they don't use the word "prompt" explicitly. If they say something like "I want Claude to do X really well" or "how do I get better outputs for Y", this skill applies.
Automated architecture governance fitness function evaluator
anyulled/architecture-guardrails-skills/skills/automated-architecture-governance-fitness-function-evaluator Skill
0★ repoEvaluate codebases against architectural fitness functions, governance files, and dependency rules to prevent architectural drift. Use when enforcing layering, cyclic dependency, or static metric thresholds in CI/CD or pre-commit checks.
JLugagne/agach/.claude/skills/doc-architecture Skill
0★ repoAgach project hexagonal architecture: bounded contexts, source code hierarchy, entry points, layers, and package structure
mvdmakesthings/skills/plugins/delivery/skills/pir Skill
no license0★ repoGenerate a post-incident report (PIR) from the current session and write it to docs/pir/. Use this skill whenever the user types "/pir", "write a PIR", "write up what happened", "document this incident", "post-incident report", "post-mortem", or "incident retrospective". Use it proactively whenever a debugging session, production outage, failed deployment, data migration incident, or any problem-solving session is winding down — even if the user doesn't explicitly say "PIR". The output is a structured markdown document capturing the timeline, root cause, impact, resolution, and lessons learned.
pszypowicz/claude-skills/plugins/go-dev/skills/go-dev Skill
0★ repoGo development with toolchain-first verification workflow. Use whenever the user (1) writes, modifies, debugs, or reviews Go code, (2) works with go.mod, go.sum, or Go module dependencies, (3) writes or runs Go tests, benchmarks, or fuzz tests, (4) mentions go doc, go vet, go fix, go test, go build, go mod, gofmt, staticcheck, golangci-lint, govulncheck, or pprof, (5) asks about Go error handling (errors.Is/As/AsType/Join), concurrency (goroutines, channels, sync, context), interfaces, or package design, (6) encounters Go compiler errors, test failures, or race conditions, (7) profiles Go code for performance or works with PGO, (8) asks about Go best practices, code review, or idiomatic Go, (9) works with files ending in .go or _test.go, (10) wants to modernize Go code to 1.21-1.26 features. Trigger this skill proactively when the user is working in a Go codebase even if they do not explicitly ask for Go help - the toolchain-first workflow (verify APIs with go doc before coding, run go vet after) catches bugs that hallucinated signatures and skipped static analysis miss. Do NOT trigger for pure educational or comparative content about Go that does not involve writing or debugging code (e.g. tutorials for blog posts, Java vs Go decision documents, explanations of the Go scheduler for learning purposes).
Yakoub-ai/Tech-Skills/skills/brainstorm Skill
0★ repoBrainstorm Architect for solution discovery, architecture exploration, and technology evaluation. Use this skill when you need to choose between approaches, evaluate tradeoffs, design an architecture from scratch, or get a concrete recommendation before committing to implementation. Triggers on questions like "what's the best way to...", "should I use X or Y", "how should I structure...", "what architecture for...", or any request for a design recommendation with tradeoff analysis.
namos2502/CortexLink/skills/agents/copilot-cli Skill
no license0★ repoThis skill should be used when delegating GitHub-specific tasks — PRs, issues, repos, Actions, branches, code review — via `copilot -p`. Use it when Copilot CLI's GitHub-native tooling is an advantage over the host agent.
JasonLo/skill-sommelier/maintainer-skills/ssm-repo-release Skill
0★ repoCreate a new versioned release: bump version, tag, and push to trigger the release workflow. Use when the user says "release", "new version", "bump version", "ship it", "cut a release", or "publish".
cyber-sorted/skills-free/cybersorted-lite Skill
0★ repoSecurity advisory skill (free edition). Use this skill when the user needs help with cybersecurity strategy, threat modelling, risk assessment, compliance, or security architecture. Trigger when the user mentions: security posture, threat model, STRIDE, PASTA, risk assessment, risk register, compliance mapping, ISO 27001, NIST 800-53, incident response, IR plan, security policy, architecture decision, vendor risk, board briefing, security maturity, gap analysis, security review, security architecture, network segmentation, defence in depth, least privilege, data classification, encryption strategy, key management, identity and access management, IAM, vulnerability management, business continuity, disaster recovery, zero trust, platform security, DevSecOps, or any security and architecture advisory request. Supports roles: CISO, CTO, Security Architect. For additional roles (CPO, Security Engineer, Enterprise Architect, Secure Developer, Penetration Tester), frameworks (SOC2, CIS, MITRE ATT&CK, CSTM, OSCP), templates, and checklists, see CyberSorted Skills Pro.
payals/ai-skills-engine/dot_cursor/skills/ai-research/agent-manager-skill Skill
0★ repoManage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
The same file is in 2 other repositories
competlab/competlab-ci-skills/skills/competlab-ai-ecosystem Skill
0★ repoMeasures EXTERNAL developer-ecosystem signals around each competitor — GitHub organization meta, top-starred repos, npm/PyPI download volumes, community-built MCP servers (not first-party), integration marketplace presence, Claude Skills directories, agent-toolkit repos. Complements competlab-agent-adoption (which measures FIRST-PARTY signals). Use when the user asks "developer adoption", "GitHub presence", "npm downloads", "marketplace presence", "agent-ecosystem strength", "community signals around [competitor]". Requires CompetLab MCP + Bash (GitHub + npm + PyPI API, mostly unauth) + WebSearch + Perplexity with URL verification.
kaichen/agent-skillset/plugins/coding-agent-maintenance/skills/coding-agent-maintenance Skill
no license0★ repoMaintain, install, update, and configure AI coding agents on macOS. Use this skill whenever the user wants to upgrade coding agents, install a new agent, check agent versions, manage MCP servers, troubleshoot agent issues, or asks "how do I update claude/codex/gemini/amp/droid". Also trigger for any question about agent health, reinstalling, switching package managers, or managing agent skills/plugins. Covers: Claude Code, Codex, Gemini CLI, GitHub Copilot, Amp, Augment, Jules, Factory Droid, and more.
arndvs/ctrlshft/skills/atomic-commits Skill
0★ repoAtomic commits on a feature branch with conventional messages — Commit mode for checkpoints, Ship mode for PR. Use when committing, checkpointing, shipping, pushing, or creating a PR.
RadKod/claude-agents-kit/flutter-game/.claude/skills/flame-game-setup Skill
no license0★ repoFlameGame sinifi kurulumu, World/Camera yapisi, overlay, asset yukleme. Yeni oyun baslangici veya game sinifi duzenleme icin kullan.
AayushMS/deploy-skills/skills/deploy-log Skill
0★ repoEnable continuous debug logging for deploy-skills sessions. Invoke this skill BEFORE running deploy-project (or any individual deploy-skills skill) to get step-by-step logging of every decision, command, and outcome written to DEPLOYMENT_DOCS/DEPLOYMENT_LOG.md. Use when you want to record the full deployment process for review or debugging. Triggers on "deploy with logging", "deploy with debug", "enable deploy logging", "debug mode deploy", "deploy log", "deploy my project with logging", or any request to record/trace the deployment process.
torarnv/claude-project-manager/skills/init Skill
no license0★ repoInitialize a new project or workspace with .memory/ tracking structure.
awfaups/intake-governance/skills/workflow-6a Skill
0★ repo6A workflow detail layer for new feature development after workflow selection is known. Use when the task is already confirmed as 6A, the user explicitly requests @6A, or intake has classified the task as greenfield feature, page, or module development. Produces dated and versioned workflow docs under the active project's root docs/YYYY_MM_DD_中文任务名_vN/ directory.
csmoove530/clawd-market/skill Skill
0★ repoAgent-native marketplace for Claude Code skills with x402 payments
Pamacea/strike/plugins/ui/skills/core/ui Skill
0★ repoMANDATORY UI generation gate BEFORE creating interfaces. Orchestrates anti-trend methodology with 12+ flags (--step/--team/--build/--demo/--analyze/--constraints/--full/--score/--validate) and Attractor-powered workflow orchestration (DOT graphs, checkpoints, events, parallel execution). Specific phrases: 'create UI', 'build interface', 'design dashboard', 'make website', 'generate layout', 'build page'. Auto-detects trend-trap keywords ("modern", "sleek", "minimal", "futuristic", "stunning") → generates dynamic anti-patterns → selects creative constraints with scoring (creativity 30%, difficulty 25%, impact 25%, synergy 20%). Integrates with step mode (interactive human-in-the-loop), teams mode (parallel agents), and design-taste-frontend patterns (100 forbidden patterns, accessibility-first). Reads memory via claude-mem before implementing, saves patterns after completion.
Ortus-Solutions/skills/bootstrap-expert Skill
no license0★ repoUse when building or modernizing Bootstrap-based interfaces that need consistent layout systems, reusable components, and accessible behavior. Invoke for grid architecture, utility usage, theme customization, migration planning, and Bootstrap JavaScript integration.
dawidpereira/rust-skills/skills/rust-architecture Skill
0★ repoRust project architecture patterns — vertical slice architecture for web APIs, component-based TUI structure for Ratatui apps, and cross-feature communication strategies. Use when organizing features into slices, wiring routes and services, choosing how features communicate, structuring a Ratatui terminal application, or deciding between single-crate and workspace layouts. Also use when setting up a new Axum/Actix-web project structure or adding a new feature to an existing sliced codebase.
Victoriakaey/build-reliable-agents/skills/agent-architecture Skill
0★ repoUse at the start of any LLM agent project, or when reconsidering an existing architecture. Guides decisions across four layers: workflow vs agent, single-agent vs multi-agent, tool-use vs specialized nodes, and retrieval strategy. Each decision has concrete tradeoffs and a recommended default.
pedroberaldo87/pedro-plugins/plugins/bootstrap/skills/setup Skill
no license0★ repoSetup de máquina nova em um passo — instala, a partir do manifest, os marketplaces de terceiros e os plugins do próprio marketplace pedro-plugins (dois deles desligados de fábrica), depois aplica a config global versionada (env vars, permissões, flags, CLAUDE.md global, output style, statusLine resolvido pra máquina) e confere a conformidade. Rode 1× por máquina depois de instalar o plugin bootstrap. Não gerencia secrets.
scryptoginger/keith-claude-skills/skills/merlin-log-triage Skill
no license0★ repoUse this skill whenever someone hands over a MERLIN execution log (or VIGIL watchdog log) and needs a fast read on what happened — for post-cycle review, debugging a failed run, investigating why no trades executed, or daily operator-style triage. Trigger on phrases like "triage this log," "what went wrong in this run," "analyze MERLIN output," "post-mortem on the cycle," or any time a `.log` / `.txt` file path is provided alongside MERLIN-domain context (Oracle, Shield, Technician, Augur, blackboard, cycle, VETO). Recency window: a single log file or a contiguous excerpt — not historical trend analysis across many runs. Not for live trading decisions, fixing the underlying issues, restarting agents, or general application logs unrelated to MERLIN/VIGIL infrastructure.
Moonweave-Systems/decision-kernel/skills/compass Skill
0★ repoUser-invoked mid-session audit skill. Detects (1) drift between current task and original session intent via transcript analysis, and (2) codebase rot — git uncommitted accumulation, test/lint state from cached artifacts, file bloat, TODO accumulation, circular dependencies, module boundary degradation. Manually triggered via `/compass` only — never auto-invoked. Use when the user types `/compass` optionally followed by a baseline intent string. Without arguments, derive baseline via cascade — most recent spec (24h), then task-init heuristic, then explicit user prompt. Never use the literal first user message of the transcript as baseline.
CaptCanadaMan/session-briefing/agent-skills/setup-session-briefing Skill
0★ repoOne-time guided setup for agent-session-briefing — creates the briefings hub, scaffolds your first briefing, and wires the continuity pointer into this repo's context file. Run this before first use of agent-session-briefing, or when you want to add a project to the constellation. Walks you through hub location, single-vs-constellation, and the context file, then scaffolds it for you.
Zulut30/telegram-skills/.cline/skills/botforge Skill
0★ repoProduction-grade Telegram bot engineering skill for Cline. Use when creating, extending, refactoring, reviewing, testing, securing, or deploying Telegram bots in Python with aiogram 3, Bot API 10.0, PostgreSQL, Redis, Docker, Mini Apps, payments, admin panels, subscriptions, broadcasts, or i18n.
HacQueen2025/Claude-Skills/debug-fast Skill
0★ repoExpert multi-language debugging skill. Use this skill whenever the user reports a bug, error, crash, unexpected behavior, performance problem, or broken feature in ANY programming language — HTML, CSS, JavaScript, TypeScript, React, Python, Go, Rust, Java, C#, C++, Ruby, PHP, Swift, Kotlin, SQL, or any other. Also triggers for: build errors, dependency conflicts, memory leaks, race conditions, segfaults, type errors, network errors, deployment failures, and "this isn't working" or "why is X happening" messages. Uses a methodical deep-diagnosis approach: classify → investigate → fix → explain root cause. Always give a working solution.
cjcsecurity/claude-tabletop/skills/tabletop-exercise Skill
0★ repoGenerate a polished, engaging tabletop exercise (TTX) runbook for the current project — covering cybersecurity, product security, DevOps/SRE, privacy/compliance, data/ML, or any other technical domain. Surveys the project to pick scenarios that match the actual stack and risk surface, then produces a facilitator runbook, participant packet, timed injects, fillable forms, and an interactive HTML version with a live exercise timer. Use when the user asks to "create a tabletop exercise", "generate a TTX", "build an incident drill", "make an IR exercise", "draft a war-game scenario", or similar. Pairs with `/tabletop-aar` for After-Action Report drafting.
MaskedControl/skills/skills/setup-dotnet-azure-site Skill
0★ repoUse when creating a new Azure deployment environment (staging, QA, demo, testing) for an existing .NET production app hosted on Azure App Service. Triggers on: "set up a staging environment", "create a new deployment site", "I need a testing environment that mirrors production", "spin up a QA site." Covers Azure resource provisioning via az CLI, GitHub branch creation, GitHub Actions CI/CD (detecting existing workflows or creating fresh), and per-environment secret isolation via GitHub Environments. Skip for non-.NET apps (Python, Node.js) or non-Azure hosting (Vercel, AWS, GCP).
labrodev/laravel-playbook/skills/labrodev-authorization Skill
0★ repoUse when creating or reviewing authorization in a Labrodev Laravel project: writing a {Model}Policy class, defining permission constants, wiring #[UsePolicy] on a model, adding #[Authorize] to an invokable controller, or deciding how any endpoint checks who may view/create/update/remove a resource.
slogsdon/skills-engineering-reference/skills/css-architecture Skill
0★ repoModern CSS architecture and design systems without heavy frameworks — Grid, Flexbox, custom properties, container queries, layer organization. Use when the user says "set up the CSS for this", "design system", "CSS architecture", "no Tailwind", "vanilla CSS only", or when starting a stylesheet from scratch on a new project. Do NOT use for utility-class systems (Tailwind etc.) — use those frameworks' own conventions.
dylanmoo/workos-plugin/skills/init-workos Skill
0★ repoInitialize a WorkOS-style workspace on top of an existing directory that already has files organized by project. Use whenever the user says 'init workos,' 'set up workos here,' 'initialize my workspace,' 'bootstrap workos,' 'scaffold workos,' 'convert this to workos,' or asks to lay the WorkOS structure over a folder they already use. Recursively scans the existing directory to detect domains (top-level areas of work) and projects (individual engagements / efforts), including projects nested one level deep inside groups (folders like `clients/` that bundle related projects together). Creates root CLAUDE.md (with routing map), MEMORY.md, ARCHIVE.md, plus per-domain CLAUDE.md + MEMORY.md and per-project CLAUDE.md + MEMORY.md. Groups themselves are not scaffolded — they're just folder containers; the domain routing map handles routing into grouped projects using full relative paths. Never moves or modifies existing files without explicit approval. Narrates each step so the user understands what's being created and why. One-time bootstrap; for ongoing maintenance use create-project, session-audit, or workspace-audit.
PlevanTem/luban-skill/.claude/skills/ai-pm Skill
0★ repoReviews and shapes 0→1 PMF-stage product decisions for AI agent infrastructure and product surface — runtime, orchestration, memory, tools, evals, harness design, and agent reasoning interfaces. Activates when the user is sizing an agent capability, choosing between workflow patterns vs autonomous agents, designing tool/skill schemas, building an eval pipeline from scratch, debating framework adoption, writing a PRD/decision-record, designing the harness (tests/docs/specs/observability) that agents operate within, or critiquing the spec layer of an agent product. Anchored on Anthropic Building Effective Agents + Krieger (research-coupling) / Karina Nguyen (eval-as-Schelling-point) / Lopopolo (harness-as-leverage) / Turley (ship-to-understand) / Cherny (prototype-density) PM thought leadership. Does not handle scale-stage tradeoffs (1→10+ enterprise sales, multi-tenant cost, SLA contracts), final architecture authority on infra primitives (defer to staff/principal engineer), agent-safety/red-team review, or B2C consumer agent products.
iansteitz1-eng/aria-skills/aria-skill-template Skill
no license0★ repoScaffolds a new aria-skills-pattern skill from a template. Generates README.md + SKILL.md + script.py with reconcile-loop stubs + config.yaml + requirements.txt — a fully-formed skill directory ready to fill in with vendor-specific logic. Multiplies contributor velocity. Use when the user says "scaffold a new skill", "create a skill for X", "new skill template", "I want to build a skill for <vendor>", or starting any new vendor integration.
Kirchlive/Claude-Full-Context-Agent/skills/prefer-fork-agents Skill
0★ repoDefines the project's subagent delegation policy — prefer fork-mode dispatch (inherits full conversation context, shares prompt cache) over named subagents whenever a delegated task benefits from already-established context. CLAUDE_CODE_FORK_SUBAGENT=1 is active in this environment. Setting `subagent_type: "fork"` explicitly on the Agent/Task call is the trigger for fork mode (verified empirically in Claude Code v2.1.177 — omission falls back to general-purpose). Default-deny mindset for named subagents — if you cannot articulate why a named subagent is required, dispatch a fork. Apply this skill EVERY time you are about to call the Agent/Task tool, EVERY time you reason about subagent_type, EVERY time the user requests delegated/parallel/background agent work, and BEFORE fanning out to multiple agents in parallel. For multi-fork orchestration (worktrees, fan-out coordination, reporting contracts), defer to the fork-fan-out skill.
aksheyw/claude-code-ship-gate/plugins/ship-gate/skills/ship-review Skill
0★ repoShip Gate code-review gate, runs /code-review then applies the distilled checklist and emits Approve/Warning/Block.
jihonghe68/skill-workshop/plugins/skill-workshop/skills/skill-creator Skill
0★ repoGuided workflow for creating new Claude Code Skills. Works in any project, with or without a launcher.html / clients/ directory. Triggers on: 新建skill, 创建skill, create skill, add skill, 创建技能, 新技能, build a new skill, 做一个新skill, 新增skill, skill创建. Always read this file completely before starting — do not improvise the creation process.
bcorfman/gui-workflow-guardrails/skills/workflow-style-contract Skill
no license0★ repoExtract existing UI style patterns (layout + interaction conventions) and enforce them for new/updated GUI features.
luck1ncoder/agent-colleague-dashboard/.claude/skills/agent-edit Skill
0★ repoModify an existing agent's `.claude/agents/<name>.md` file based on a natural-language request. Triggered by /agent-edit. Backs up the file, uses the Edit tool (which prompts the user with a diff for permission), and invalidates the dashboard cache. Use when the user wants to change an agent's behavior, prompt, tools, or model without manually editing the file.