#SkillRepo stars

1. 625Dingtalk Bridgemguozhen/dingtalk-bridgeDingTalk group chat bridge for Claude Code. Send markdown/text messages to DingTalk groups, receive @mentions and auto-execute via Claude CLI, run a 24/7 Stream bot. Triggers: dingtalk, send dingtalk, dingtalk bot, dingtalk message, send group message, 钉钉, 发群消息, 钉钉机器人5
2. 626Dspy Rbvicentereig/dspy-rb-skillBuild type-safe LLM applications with DSPy.rb - Ruby's programmatic prompt framework with signatures, modules, agents, and optimization5
3. 627Game Architectrhino-ty/game-architectEnd-to-end indie game design AI skill — system mechanics, numeric balancing, GDD writing, narrative design, platform fit analysis, engine selection (Unity/ Godot/Unreal), audio strategy, indie marketing, post-launch operations, procedural generation, and Claude Code project document scaffolding. Acts as "The Architect": a 15-year senior game system designer persona tuned for solo and small indie teams targeting Steam, console, and mobile. ALWAYS use this skill when the user mentions making, designing, balancing, shipping, or operating a game — even if they don't say "game design" explicitly. T5
4. 628GoodcodeSpinaBuilds/goodcodeHost-agnostic exhaustive multi-agent orchestration for any coding agent that can spawn subagents (Claude Code, Codex, Cursor, OpenCode, OpenHands, …). Pipeline: recon → cheap baseline → a-priori specialist roles cast by routing → parallel fan-out → adversarial verification → loop-until-dry → dedup/score/synthesize. Optimizes for the most exhaustive, correct answer — not the fastest or cheapest. Use for audits, deep reviews, multi-source research, design exploration, large migrations, or any substantial task where completeness beats latency. Triggers: '/goodcode', 'goodcode', 'orchestrate exhau5
5. 629Human Maintainabilityhmr-BH/HMAPAssess a programming project's HUMAN maintainability (HMAP): 0-100 score, nine-tier verdict, per-dimension scores, and file:line evidence — built to catch vibe-coding / AI-generated slop, including semantic incoherence (name/contract/concept/vocabulary drift). Triggers: assess maintainability / rate this project / code quality score / readability score / AI slop detection / vibe coding check / semantic consistency check / HMAP / human maintainability / 评估项目可维护性 / 给项目打分 / 代码质量评估 / 可读性评分 / AI屎山检测 / vibe coding 体检 / 是否适合人类维护 / 语义一致性. Anti-trigger: the user asks to fix, refactor, optimize, or writ5
6. 630Industrial Waste Heat Recoverydungnotnull/industrial-waste-heat-recovery-agent-skillIndustrial Waste-Heat Recovery System Design — Production-grade evidence-backed analysis harness with flexible agent architecture, skill registry, and modular sub-agents. Use for: waste-heat recovery design, heat exchanger selection, ORC systems, pinch analysis, energy efficiency assessment, industrial thermal system optimization. Triggers on: "waste heat", "heat recovery", "ORC", "pinch analysis", "heat exchanger", "energy efficiency", "thermal optimization", "industrial heat", "steam system", "condensate recovery".5
7. 631Ml Architecture DiagramZtsdut/ml-architecture-diagram-skillCreate accurate, publication-ready, editable machine-learning and deep-learning architecture diagrams from model code, configuration files, model summaries, graph exports, or written specifications. Use for neural-network figures, architecture schematics, model block diagrams, training/inference diagrams, paper figures, and editable SVG/draw.io/PPTX outputs. Recover the real computation graph first, compress unimportant implementation detail, emphasize the scientific contribution, and never invent modules for aesthetics.5
8. 632No AI Tonemckenizemanfull5678-ctrl/no-ai-tone中文长文写作五步管线：把杂乱素材整理成一篇读起来「不像 AI 写的」文章。当用户要写 公众号 / 知乎 / 博客等中文长文，要把素材·笔记·链接整理成稿，抱怨 AI 写的东西有 「AI 腔 / AI 味」，或想给一篇已有文章去 AI 腔、提炼金句、规划配图时使用。主线五步写作 + 配图落地：选题研判 → 内容线设计 → 大纲打磨 → 风格化初稿 → 双重精修（去 AI 腔 + 金句提炼） → 配图落地（信息图为主、配图也去 AI 味）。核心心法是「人决策、AI 执行」——每一步产出后 停下来等用户拍板，绝不一口气跑完。5
9. 633Oeconomiavincitamore/oeconomiaDelegation economy for a session whose own context window is the scarce resource. REFLEX: name the model wherever the dispatch primitive accepts one (an unset model can inherit the session model and silently spend the budget you protect); delegate bulk early (multi-file reads, protocol-driven review sweeps, build/test runs, scripted edits) so freight never lands in the compounding window; keep judgment and every required orientation read; floor: one known-file read, one grep, a two-line edit, or any read near session end stays home; a same-provider subagent relieves the window, never the accou5
10. 634OmiCzzzzzzJ/omiOmi3.0 小红书图文笔记生产线。输入内容素材 + IP形象，自动产出分镜脚本JSON + 图片生成指令，适用于 Claude Code、OpenClaw、Codex、扣子等任何具备本地图片生成能力的 Agent 平台。触发词：omi、小红书笔记生成、omi笔记5
11. 635Openpencil Design Orchestratorziiinian/openpencil-design-orchestratorOrchestrate Pencil/OpenPencil design work through MCP using a staged workflow: preflight, planning, skeleton, section content, refinement, and safe fallback. Use when working with Pencil/OpenPencil, .fig/.pen design files, MCP-based design editing, or when Claude Code, Codex, Cursor, or Windsurf needs reliable prompt patterns, client setup guidance, and risk controls for AI-assisted design changes.5
12. 636Phd Application Advisoralex-yimingyang/phd-application-advisor大龄非科班转AI申请海外PhD的全流程顾问。覆盖RA申请、选方向选校、套磁、文书、面试、推荐信、时间规划等所有环节，专门针对30+在职、非CS背景、想转AI方向申博的人群提供策略建议。 当用户提到以下任何场景时使用此skill：大龄读博、非科班申博、转行申PhD、30+申博、在职申博、工作后读博、非传统背景申请PhD、AI方向博士申请、美国博士申请、海外PhD、申博规划、申博咨询，或任何涉及"工作几年后想读博不知道怎么开始"的问题。即使用户没有明确说"非科班"，只要描述了类似背景（非CS本科、工作多年、想转AI/ML方向读博），也应触发此skill。5
13. 637Prism V2Ronkupper/PRISMPRISM — structured multi-session, multi-vendor LLM-orchestrated audit and research framework. Trigger this skill whenever the user invokes PRISM mechanics by name or by recognizable construct: PRISM audit, PRISM v2, begin a PRISM audit, Master file, any filename matching *_master_p*.md, Prompt Strategy, Lens Library, Vendor Selection, Vendor Triangulation, Setup probes or any of P1-P7 by number, Monitor M* or any of M1-M12 by number, Standing Principle SP-*, Execution Envelope, Execution Self-check, Execution Output, Dispatch register, Dispatch shape (equivalence/split/limitation-named), the W5
14. 638Prompt Constraintsq253595422/prompt-constraints生图 / 视频提示词约束引擎。把模糊需求、关键词、粗糙草稿或参考图，转成受约束、可校验、可直接投喂的生图（t2i / i2i）与视频（t2v / i2v / 多镜头）提示词。 用于：写/优化/扩写生图提示词，写/优化视频提示词，从参考图反推提示词（图画文 / img2prompt），锁定角色·场景·风格一致性（character sheet / 角色三视图 / 身份锚点），写负面约束与回避清单，按模型适配（Nano Banana Pro、即梦 Seedream、GPT Image、Midjourney、FLUX、Seedance、可灵 Kling、Veo、Sora、Hailuo、MiniMax、LTX、Wan）。 当用户提到「生图提示词 / 视频提示词 / prompt / 提示词 / 反推提示词 / 图画文 / 一致性 / 首帧图 / 分镜 / 运镜」时使用。5
15. 639Prompt Optimizertalki-io/prompt-optimizerOptimizes and polishes an existing AI/LLM prompt the user has already written — fixing wording, grammar, structure, redundancy, and clarity — while strictly preserving the original intent, role, scope, capabilities, constraint strength, and every technical detail (commands, paths, URLs, parameters, code blocks). Use whenever the user invokes /prompt-optimizer with a prompt (no extra instruction needed), or pastes a prompt and asks to optimize, refine, polish, clean up, simplify, tighten, restructure, make more professional, or "fix the wording" of it, even without the word "prompt" — e.g. "mak5
16. 640Reinitaisk/reinitReview available recent code-agent history and tool calls, then update the current repository's durable agent guidance with repeatedly needed facts and user-corrected conventions. Run only when the user explicitly invokes /reinit, $reinit, or names the reinit skill; never invoke automatically.5
17. 641Semantic Compressiontherealmoronto/claude-semantic-compressionApply semantic logic compression (Ovchinnikov method) when crafting prompts for LLMs or describing complex conditional logic. Use this skill whenever the user asks to: write or optimise a prompt for an LLM, compress or rewrite a task description, describe multi-condition business logic (if/and/or/not chains), or asks why an LLM misunderstood their instructions. Also trigger when the user says ‘compress the logic’, ‘write a prompt for’, ‘the LLM doesn't understand’, ‘simplify the conditions’, or similar intents. Also trigger when the user wants to use output modifiers such as →code or →no-meta,5
18. 642Skill Evolutionrwang23/skill-evolutionTurn repeated usage evidence and user feedback into reviewable Skill or harness improvement proposals. Use for Skill evolution, routing regressions, eval or hook improvements, and 技能进化或优化; not for applying changes or one-off edits.5
19. 643Skill Guardian0xtresser/skill-guardianPre-installation security gate for agent skills. This skill should be used when the user or agent attempts to install any skill — including requests like "install X", "add X skill", "help me set up the X skill", "npx skills add", or when the agent autonomously decides to install a skill. Also triggers on skill cleanup and audit requests like "clean up my skills", "check installed skills", "any unused skills", "review my skills", or "audit my skill list". Do NOT use for MCP server installation, npm/pip package installation, or non-skill tooling.5
20. 644Tribeunaltribeunal/mcp-serverUse when a decision needs more than one opinion — a dispute between two parties, a verdict or ruling someone will act on, a team decision nobody can settle, a poll or a vote, an arbitration clause, an escrow release waiting on who is right, or any question better answered by a jury of people and AI agents than by a single model, even if they never say Tribeunal5
21. 645Wikipedia Not AIValpep/wiki-ai-detectorDetect AI-generated text by identifying characteristic patterns, phrases, and structural tells from LLMs like ChatGPT, Gemini, and others. Use when the user wants to check if a text was written by AI, audit content for AI tells, clean up AI-generated writing to make it less detectable, understand what makes text sound AI-generated, or review emails, articles, reports, marketing copy, or any prose for AI markers.5
22. 646World Events Briefingchenxihuang1028-a11y/world-events-briefingUse when the user wants a country / major-world-events news briefing ("全球时事简报") — armed conflicts, elections, disasters, business/economy, law/crime — pulled from Wikipedia's human-curated "Portal:Current events" daily pages and the GDELT DOC 2.0 article-search API. This is NOT the AI/tech skill (that's the sibling ai-news-briefing). One of only two Skills in the collection that calls the network (skill.json permissions.network=true) — it still needs zero user API keys. Offline fixture mode is available for fully deterministic, zero-network runs.5
23. 647AI Code Review Triagelaulauraluo/ai-code-review-triageReview pull requests or diffs written by AI coding agents (Claude Code, Codex, Copilot, Cursor) when reading every line no longer scales, or when the code looks clean but you don't trust it yet. Splits "reading the code" into three separate jobs (catch bugs, align context, own the sign-off) and runs a different process for each. Use for requests like "review this AI-generated PR", "can this diff be merged", "too many agent PRs to review", "check this before I approve", or "what should I verify before signing off". For a plain security/performance checklist use a general code-review skill inste3
24. 648AI Tell Detectoraragossa/ai-tell-detectorAudits a finished draft for the patterns that make text read as AI-generated — rhetorical symmetry, generic filler, uniform rhythm, over-resolved story arcs, missing human roughness, fabricated personal experience — and flags each one with a fix. Use before publishing anything, or when a draft "feels AI" but you can't say why.3
25. 649Privacyscrubber Guardmoxno/privacyscrubber-mcpPre-ingestion zero-trust PII, secret, and regulated data sanitization skill for AI coding agents (Claude Code, Cursor, Codex, Gemini CLI, Windsurf) via @privacyscrubber/mcp-server. Intercepts files, shell commands, and prompts in local RAM with 30 specialized industry profiles and SHA-256 compliance receipts.3
26. 650Benchmark Yyloyylo-dev/yylo-skillsPrepare reviewed cases and frozen checklists, compare models and harnesses, and independently evaluate retained outputs with YYLO Benchmark's thin trusted-host runner.1
27. 651Cohesivitycohesivity-org/cohesivity-pluginBackend and infra for a project via Cohesivity (cohesivity.ai). Provisions Postgres, hosting and deploys, auth and social login, realtime websockets, an agent-native email inbox, object and vector storage, Redis, cron, and AI model APIs (OpenAI, Anthropic, Deepgram, Exa) through one HTTP API. Use when a valid .cohesivity file exists, a Cohesivity MCP is available, the user names Cohesivity, or the project needs a backend or any of these services and no competing provider was chosen.1
28. 652AI Meetingbin1874/ai-meeting-skillRun structured AI meetings for plans, product ideas, technical designs, business decisions, feature proposals, and strategy choices. Use when the user wants an AI meeting, AI roundtable, multi-agent discussion, debate, proposal review, plan review, decision review, or wants Codex, Claude Code, qoderclicn, and other CLI agents to analyze a proposal across multiple expert roles, challenge assumptions, preserve per-agent sessions, and produce a final decision report with provenance. 也适用于中文场景：方案评审、多 Agent 讨论、技术路线评审、商业决策评审。1
29. 653Crosscheckmoveju112/skill_verifyClaude-hosted Claude↔Codex crosschecks of improvement ideas, plans, and completed changes. Automatically selects independent proposals, draft critique, or mutual review and allows candid rejection. Use for explicit requests such as "크로스체크", "코덱스랑 핑퐁", "둘이 의견 취합해", "cross-check with codex", or "/crosscheck". Discussing or editing this skill does not authorize another model call.1
30. 654Danshari Skillswaylq/danshari-skill断舍离.skill — 审计当前 agent 装的全部 skill，对照现在的模型能力、harness 内建功能和已接入的 MCP 工具，找出不再需要的那些：证据化判决（能力型先盲测）→ 用户确认 → 归档移除（一键可恢复），并报告每轮省下的 token。模型每变强一代，就该跑一次。 触发词：「skill 断舍离」「清理 skill」「skill 太多了」「移除不需要的 skill」「审计 skill」「换了新模型清理一下」「prune skills」「declutter skills」「skill audit」。1
31. 655Gedikonur-kesim/gedikBreaks your own code, artifacts, and configuration like an attacker to find gedik — so they can be closed. First MEASURES the architecture (triage T1-T12), then opens only that architecture's surface - A client/offline/mobile (Android, iOS) · B server/API/DB/identity (injection variants, IDOR, OAuth/MFA, CORS, webhook, rate limiting, business logic, WebSocket, GraphQL, request smuggling, fail-open) · C BaaS-RLS (Supabase/Firebase, PostgREST) · D AI/LLM (prompt injection, tool authorization, vector/embedding, MCP) · E shipped-artifact hygiene - plus code review + mechanical scanning, dependency1
32. 656Moodtrip Hotel Searchadiny/moodtrip-hotel-searchSearch, compare, evaluate, and hand off hotel bookings using the MoodTrip.ai MCP server (api.moodtrip.ai). Use this skill whenever the user mentions hotels, accommodation, lodging, stays, travel bookings, hotel search, hotel comparison, hotel reviews, hotel pricing, or anything related to finding or booking a place to stay. Also trigger when the user asks about hotel amenities, room types, check-in/check-out logistics, travel destinations with accommodation needs, or says things like "find me a hotel", "where should I stay", "book a room", "hotel recommendations", or "compare hotels". This ski1
33. 657Rule Architectmoveju112/rule-architectUse when a project needs AI agent rules built or upgraded — no AI_RULES.md exists, an existing rule index has grown into one bloated file, or the user asks for a project rule set. Triggers on "make rules for this project", "generate AI rules", "set up project rules", "upgrade the project rules", "rule-architect", "/rule-architect", and the Korean equivalents "룰 만들어줘", "룰 생성", "AI 룰 만들어", "프로젝트 룰 고도화", or refreshing rules after a major refactor ("--update"). English and Korean triggers are equivalent.1
34. 658Sechelixomarmohelal/SecHelixEvidence-first application-security audit workflow for authorized repositories and environments. Use when reviewing a codebase, pull request, API, web application, AI-generated code, agent or MCP integration, cloud configuration, authorization (BOLA, IDOR, BFLA), business logic, payments, race conditions, secrets, supply chain, or release readiness for security weaknesses. Also supports explicitly requested technical SEO audits and evidence-backed codebase cleanup. Maps trust boundaries, selects applicable checks, runs parallel specialist review, independently verifies every material finding a1
35. 659Skill Freshnesskvozianov/skill-freshnessUse this skill first whenever the user asks about the health of their installed agent skills: auditing, checking, cleaning up, updating or de-duplicating skills in ~/.claude/skills, ~/.codex/skills, ~/.agents/skills or plugin folders, or finding skills that are broken (missing CLI or script), outdated versus upstream, duplicated across agents, or made redundant by built-in features like /loop or /schedule. Do not inspect skill folders by hand: this skill ships a scanner that covers every agent (Claude Code, Codex, Cursor, Gemini CLI, Copilot, OpenCode, Antigravity), maps which agent loads each1
36. 660Stipendstipend-sh/stipendA non-custodial USDC wallet on Base that an AI agent installs by itself, with spending limits enforced in the signing path rather than in a prompt. Receive payments, pay HTTP 402 / x402 charges automatically, and answer whether you are worth running. No account and no API key: the only approval needed is from the person who runs you.1
37. 661Aeo Checkpchewlo/aeo-checkRun aeo-check on a website's code (or a live URL) to find answer engine optimisation problems that stop ChatGPT, Claude, Perplexity, Gemini and Google AI Overviews from crawling, understanding, citing or buying from the site, then fix them. Use when asked to check or improve AEO, GEO, AI search visibility, llms.txt, robots.txt for AI crawlers, structured data, or agent readiness.
38. 662Fresh Reviewroman-s8o/workflow-pack-freeReview an artifact with an independent agent that has no access to the author's reasoning, then classify its findings.
39. 663Least Cost Capablekanibal-studio/least-cost-capableCompare declared relative cost ranks among catalogued agent models after checking task capability, availability, authorization, workload, and cost evidence.
40. 664Orchestrating SubagentsPapiScholz/symphonyUse when about to spawn one or more subagents, agent teams, or a workflow — a single delegated search, a parallel fan-out, or a repeated batch — and whenever choosing which model a delegated task runs on instead of letting it inherit yours. Also use when writing or editing a .claude/agents definition, when a delegated run hit a rate limit or cost more than expected, or when a subagent came back after far more or far fewer turns than the work warranted.
41. 665Reels SetupVishiATChoudhary/reelsUse when setting up, installing or onboarding the reels studio (github.com/VishiATChoudhary/reels), when a user or agent wants to start making story reels with it, or when its setup is broken (missing whisper-cli, model, yt-dlp, ffmpeg, node deps). Clones, installs, verifies, and stars the repo (one [Y/n] prompt).
42. 666Session Handoffalapha888/session-handoff-kitUse this skill when context usage approaches capacity (>60%), before running /clear or /compact, when switching tasks, when ending a coding session across Claude Code, Cursor, or Codex, or as a mid-session diagnostic — if the agent cannot fill the handoff fields from actual state, the session has drifted. Produces a structured handoff artifact that transfers execution state to a fresh agent session without loss of context or drift.
43. 667Slop Postuseslop/claude-pluginsPost what this Claude Code session built to Slop (useslop.com) as a private draft with an automatic Build Receipt (model, tools, run time, commits), optionally as an entry in this week's Slop challenge. Use when the user runs /slop-post or asks to share, post or ship this session's work to Slop. Saves a draft only; the human publishes it from the claim link.
44. 668Unthrottled Route Checkedtrackai/ship-ready-skillsFind Next.js API routes that call OpenAI, Anthropic or the Vercel AI SDK, or create a Stripe Checkout Session, with no rate limiter. Use when the user asks about rate limiting, AI cost per user, surprise API bills, refresh loops at checkout, or abuse protection before launch.
45. 669Upwork Job Hunterdroopboop/flconsole-upwork-mcpFind new Upwork jobs that fit the freelancer with the flconsole MCP server. Loads the user's saved context from the server, guides a 3-step setup (search query, job and client filters, the user's own AI filter that you apply), saves it as a feed on the server, checks new jobs, shortlists them with reasons, drafts proposals, tunes the search with job counts and turns on Telegram alerts for a feed in one call. Use when the user wants to find or monitor Upwork jobs, set up or improve a job search, check new jobs, get fewer or more relevant jobs, or decide which jobs to apply to.
46. 670Agent Context Loaderjeremylongshore/claude-code-plugins-plus-skillsPROACTIVE AUTO-LOADING: Automatically detects and loads AGENTS.md files from the current working directory when starting a session or changing directories. This skill ensures agent-specific instructions are incorporated into Claude Code's context alongside CLAUDE.md, enabling specialized agent behaviors. Triggers automatically when Claude detects it's working in a directory, when starting a new session, or when explicitly requested to "load agent context" or "check for AGENTS.md file".
47. 671Analyzing Logsjeremylongshore/claude-code-plugins-plus-skillsThis skill enables Claude to analyze logs for performance insights and issue detection. It is triggered when the user requests log analysis, performance troubleshooting, or debugging assistance. The skill identifies slow requests, error patterns, resource warnings, and other key performance indicators within log files. Use this skill when the user mentions "analyze logs", "performance issues", "error patterns in logs", "slow requests", or requests help with "log aggregation". It helps identify performance bottlenecks and improve application stability by analyzing log data.
48. 672Analyzing Network Latencyjeremylongshore/claude-code-plugins-plus-skillsThis skill enables Claude to analyze network latency and optimize request patterns within an application. It helps identify bottlenecks and suggest improvements for faster and more efficient network communication. Use this skill when the user asks to "analyze network latency", "optimize request patterns", or when facing performance issues related to network requests. It focuses on identifying serial requests that can be parallelized, opportunities for request batching, connection pooling improvements, timeout configuration adjustments, and DNS resolution enhancements. The skill provides concre