Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 870 files from 1 769 authors, of which 62 217 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
> 把任意图片重画成黑底像素粒子画：笔触尘沿图像自身的结构方向真实流动，长短笔触混搭、 子段错位出"脏"质感，动效按画面的物理规律分区规划（下坠/上升/旋转/外抛）， 输出静态 PNG 与无缝循环 GIF/MP4。触发：/dirty-pixels、「dirty pixels」「粒子流动效果」 「把这张图重绘成笔触」「yudho 那种风格」。风格致敬 pointillistic-noise 像素绘画美学 （参考艺术家 Satrio Yudho），实现为独立的确定性算法，不复制任何原作。
Work with Effect v4 / effect-smol TypeScript code in this repo
Use ONLY when calling the `browser_execute` tool or driving a real browser via the Chrome DevTools Protocol. Required reading before the first `browser_execute` call in a session. Covers the three connection methods (local Chrome with remote debugging, isolated debug-port profile, Browser Use cloud), the in-process `session` / `console` snippet model, attaching to a page target, common CDP commands, the per-project `.bcode/agent-workspace/` for reusable scripts, and screenshot auto-attachment.
> Korean market quotes (KOSPI / KOSDAQ / SK Hynix / Samsung) with capitulation-reversal detection. Use whenever reading the US memory/storage complex (MU / DRAM / SNDK / WDC / STX / SMH) — Korea is the SOURCE market and leads the US tape; Longbridge does not cover KRX. 存储板块见底了吗 / 洗盘结束了吗 / capitulation / Korean margin calls / has the flush ended.
> Render financial charts via the local chart web app (workspace at the repo (`flow`) and cross-symbol signed-bar comparison (`cohort`) — both Recharts — plus SEPA strategy dashboard (`sepa`) and short-term multi-timeframe prediction dashboard (`intraday`) — both TradingView Lightweight Charts. Multi-timeframe K-line review lives inside `intraday` (the standalone kline chart type was removed). The server fetches Longbridge data itself (kline / capital flow) and computes all indicators (MA, MACD, RS, trend template, volume profile, divergence/beichi detection) in TypeScript; the caller only POSTs `{type, symbol, ...}` to `/api/charts` and gets back `{id, url, technicals?}`. Charts persist as data JSON under 短线预测、多周期K线、MACD、入场判断可视化、可视化、render chart, plot, visualise, sepa dashboard, intraday prediction dashboard.
US/global macro time series from St. Louis Fed FRED — CPI, GDP, Fed funds, yields, M2, DXY, etc.
Use when reading today's US-market capital flow across multiple sectors to identify rotation direction — e.g. "今天资金流向", "板块强弱", "rotation map", "卖芯买云", "where is money moving today", "scan flows across sectors". Produces a cross-section snapshot of net inflows by cohort (indices / semis / software-cloud / mega-tech / AI applications), names the dominant narrative, and writes a dated journal file. Different from `market-session-tracker` (intraday live monitoring of a single watchlist) — this is a one-shot end-of-session rotation read.
A 股官方数据，来自同花顺（HiThink）官方 API——涨停股票池、连板天梯、龙虎榜、个股异动原因、热榜、A 股官方口径财报（利润表/资产负债表/现金流量表/财务指标）、行情快照与日 K。
Use when monitoring stocks/ETFs/indices across pre-market, open, intraday, or close — especially when the user is reading session action live and may revise their take as it unfolds. Triggers include 盘前/盘中/收盘 sessions, multi-symbol watchlists (e.g. MU/TSM/SMH semi tracking), user observations like "突破"/"冲高"/"回调"/"假突破", capital flow checks, market temperature checks, semi/AI/memory plays, and any request that bundles a position context with a live read.
Global multilingual news event stream with tone scoring via GDELT 2.0 Doc API.
> Short-term multi-timeframe (5m/15m/1h) technical read for a single symbol — pulls K-line across three timeframes, reads MACD + swing structure, writes a direction call (long/short/neutral) with an explicit anchor price, a 2–4 scenario forward read, a range-bound playbook (long tactic + short tactic; a neutral call carries a numeric low/high zone instead of an entry plan and is scored on whether the zone held), an entry/stop/target plan with dual-basis R/R (T1 + T2) for directional calls only, position sizing with a nominal cap from the live broker account, an event-risk gate (earnings / FOMC / CPI), and market/sector alignment + relvol volume checks — MACD divergence/背驰, candle patterns like Pin Bar, and 123 structures are auto-detected and drawn server-side — then renders it via the `chart` skill (type `intraday`, POST preview → PATCH prediction) and logs a journal entry. US-only, single-symbol, short horizon (intraday to a few sessions) — a companion to `market-session-tracker`, not a replacement. Pin Bar、入场点、盈亏比、short-term call, intraday prediction, entry point, risk reward ratio, multi-timeframe MACD.
Use when the user wants to release a new desktop app version (发版 / release / 发布新版本) — bumps apps/desktop version, writes user-facing release notes into CHANGELOG.md, and opens the release PR that drives the automated tag → build → publish pipeline
> 交易决策关卡——任何买入/加仓/卖出/减仓动作发生前，先过一遍写死的检查关卡， 打分给出判定，判定与实际执行不一致的记为违规，落盘 JSON 供复盘统计。三个 入口：买入漏斗（六层打分，硬门+软分）、卖出触发器（复用用户既有的 6/27 持有计划触发线、周期见顶清单、爆仓潮反向保护）、巡检（对长桥全部持仓批量跑 卖出触发器）。不拦截下单（本仓库长桥只读），约束力来自违规账单而非技术拦截。 巡检、跑一遍卖出检查、算一下违规账单、我该不该现在动这只票、trade decision gate, buy funnel, sell trigger, position patrol, violation ledger.
Use when the user asks for an end-to-end orientation on a listed company they don't yet understand, especially when the request combines two or more dimensions in one ask. Triggers on "X 是干什么的", "帮我了解 X", "X 主营 + 同行", "盘前为什么涨", "本周趋势 + 阻力支撑", "X 和其他公司的关系", "first time looking at X", "full brief on X". Skip when the user wants only a single lens — use the targeted Longbridge sub-skill instead.
> Cross-context shared trading discipline — output language, independent verification, scenarios not points, noise filtering, intent-attribution protection, verifiable reasons). Injected into both the app-side judgment agents (analyst / deepDive / chat) and the bench episode runner. Context-specific chapters live under references/ and are loaded on demand by the caller (app or bench).
US SEC EDGAR filings — list 10-K/10-Q/8-K/Form 4/S-1, fetch filing text, parse insider Form 4 transactions.
Use when monitoring or interpreting Donald Trump's Truth Social posts for market-moving events — tariff announcements, sanctions, deals with countries (China / Mexico / Canada / EU / Japan / Korea / Taiwan), specific company / CEO mentions, Fed pressure, energy / oil commentary, crypto policy, or geopolitical escalation. Triggers on "trump 发了什么", "check trump", "trump 关税", "盘前 trump 推", "trump truth social", "trump tweet impact", "trump 对 X 说了什么", or whenever a pre-market gap / intraday spike on policy-sensitive names (semis, China ADRs, autos, energy, banks, defense) needs to be explained.
Aggressive AI coding guidelines inspired by Linus Torvalds. Enforce data structure supremacy, simple code, proof over hand-waving, and a bogus-shit detector.
Manage Todoist tasks, projects, labels, filters, sections, comments, reminders, and workspaces via the `td` CLI. Use when the user wants to view, create, update, complete, or organize Todoist items, or mentions tasks, inbox, today, upcoming, projects, labels, or filters.
Guide for adding new CLI commands or subcommands to todoist-cli. Use when implementing new SDK endpoints, adding subcommands to existing command groups, or extending CLI functionality.
Guide for adding new CLI commands or subcommands to todoist-cli. Use when implementing new SDK endpoints, adding subcommands to existing command groups, or extending CLI functionality.
Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Management APIs for projects, API keys, members, invites, requests, usage, billing, models, and agent think-model discovery. Covers `client.manage.v1.*` plus `client.agent.v1.settings.think.models.list()`. Use `deepgram-js-voice-agent` when you want to run an agent live rather than administer projects or inspect models. Triggers include "management API", "list projects", "API keys", "members", "invites", "usage stats", "billing", "list models", and "manage.v1".
Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Conversational STT v2 / Flux (`/v2/listen`) for turn-aware streaming transcription. Covers `client.listen.v2.createConnection()` / `connect()`, Flux models, and turn events like `TurnInfo`. Use `deepgram-js-speech-to-text` for standard v1 ASR and `deepgram-js-voice-agent` for full-duplex assistants. Triggers include "flux", "v2 listen", "conversational STT", "turn detection", "end of turn", "EOT", and "listen.v2".
Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Text-to-Speech v1 (`/v1/speak`) for audio synthesis. Covers one-shot REST via `client.speak.v1.audio.generate` and streaming WebSocket via `client.speak.v1.createConnection()` / `connect()`. Use `deepgram-js-voice-agent` when you need full-duplex STT + LLM + TTS instead of one-way synthesis. Triggers include "TTS", "text to speech", "speak", "aura", "streaming TTS", and "speak.v1".
Use when writing or reviewing JavaScript/TypeScript in this repo that builds an interactive voice agent via `agent.deepgram.com/v1/agent/converse`. Covers `client.agent.v1.createConnection()` / `connect()`, `sendSettings`, `sendMedia`, runtime updates, event handling, and function-call responses. Use `deepgram-js-text-to-speech` for one-way synthesis, `deepgram-js-speech-to-text` or `deepgram-js-conversational-stt` for transcription only, and `deepgram-js-management-api` for project/model admin rather than live agent runtime. Triggers include "voice agent", "agent converse", "full duplex", "barge-in", "function calling", and "agent.v1".
Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram audio analytics overlays on `/v1/listen` - summarize, topics, intents, sentiment, diarize, redact, detect_language, and entity detection. Same endpoint as plain STT, different params. Covers REST via `client.listen.v1.media.transcribeUrl` / `transcribeFile` and the WebSocket-supported subset on `client.listen.v1.createConnection()` / `connect()`. Use `deepgram-js-speech-to-text` for plain transcription and `deepgram-js-text-intelligence` for analytics on already-transcribed text. Triggers include "audio intelligence", "summarize audio", "diarize", "sentiment from audio", "redact PII", and "detect language audio".
Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Text Intelligence / Read (`/v1/read`) for sentiment, summarization, topic detection, and intent recognition on text input. Covers `client.read.v1.text.analyze(...)` with `body: { text }` or `body: { url }`. Use `deepgram-js-audio-intelligence` when the source is audio instead of text. Triggers include "read API", "text intelligence", "analyze text", "sentiment", "summarize text", "topics", "intents", and "read.v1".
Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Speech-to-Text v1 (`/v1/listen`) for prerecorded or live audio transcription. Covers `client.listen.v1.media.transcribeUrl` / `transcribeFile` (REST) plus `client.listen.v1.createConnection()` / `connect()` (WebSocket). Use `deepgram-js-audio-intelligence` for summarize/sentiment/topics/diarize overlays, `deepgram-js-conversational-stt` for Flux turn-taking on `/v2/listen`, and `deepgram-js-voice-agent` for full-duplex assistants. Triggers include "transcribe", "speech to text", "STT", "listen.v1", "nova-3", "live transcription", and "websocket transcription".
Comprehensive kanban board and task management via ktui CLI. Use for project tracking, todo lists, task dependencies, workflow automation, and board management. Activates when user mentions boards, tasks, kanban, or project management. If the `ktui` command is not available, but `uv` is available utilize `uvx kanban-tui` instead.
Build DSPy evaluation harnesses with rich-feedback metrics that are essential for GEPA optimization. Use when writing a metric function, calling dspy.Evaluate, splitting dev/val sets, debugging "why is my optimizer not improving?", or designing CI-ready DSPy eval suites.
Drive a complete DSPy 3.2.x project end-to-end — spec → program → metric → baseline → GEPA optimize → export → deploy. Orchestrates the other four DSPy skills (dspy-fundamentals, dspy-evaluation-harness, dspy-gepa-optimizer, dspy-rlm-module) in the correct order. Use this for any non-trivial DSPy build from scratch.
Write idiomatic DSPy 3.2.x programs — typed Signatures, dspy.Module subclasses, Predict/ChainOfThought/ReAct/ProgramOfThought, and save/load. Use this when starting any new DSPy project or when fixing non-idiomatic DSPy code (hard-coded prompts, ad-hoc string templates, untyped outputs, non-serializable classes).
Optimize DSPy programs with dspy.GEPA — the reflective/evolutionary optimizer that is the 2026 gold standard for DSPy (beats MIPROv2 on complex tasks with far fewer rollouts when the metric returns rich feedback). Use when the user says optimize, compile, GEPA, reflective optimization, or "make this program better" and a DSPy program + metric + trainset exist.
Use dspy.RLM (Recursive Language Model) for reasoning over contexts too large to fit in an LLM's working window — entire codebases, long logs, massive documents, or multi-step data exploration that needs a sandboxed Python REPL. Use when the input is >100k tokens, needs recursive chunking, or benefits from the LLM writing and running code to probe data.
Describes the acceptance criteria and BDD tests to be used for new/existing features of the InternalReleaseImage MachineConfigDaemon manager. The manager implements the NoRegistryClusterInstall main feature for the part related to manage/monitor a single control plane node
The InternalReleaseImage controller manages the IRI resource lifecycle, generates MachineConfigs for the IRI registry, updates status by aggregating from MachineConfigNodes, and handles deletion. Use when reviewing controller implementation or validating behaviors.
Work with the QStash JavaScript/TypeScript SDK for serverless messaging, scheduling. Use when publishing messages to HTTP endpoints, creating schedules, managing queues, verifying incoming messages in serverless environments.
Analyzes and improves prompts using 31 frameworks across 7 intent categories. Use when a user wants to improve, rewrite, structure, or engineer a prompt — including requests like "help me write a better prompt", "improve this prompt", "what framework should I use", "make this prompt more effective", or any prompt engineering task. Recommends the right framework based on intent (create, transform, reason, critique, recover, clarify, agentic), asks targeted questions, and delivers a structured, high-quality result.
Use when a researcher is choosing, framing, refining, or stress-testing a research question, hypothesis, thesis topic, project idea, grant direction, paper angle, or stalled research direction.
Add new T-SQL features to ScriptDOM parser. Asks questions about SQL Server version and feature type, then guides through grammar changes, AST updates, script generation, and testing using existing instruction files. Handles syntax additions, new functions, data types, index types, and validation rules.
Verify whether an exact T-SQL script is already supported by SqlScriptDOM, then add or update the correct parser tests and baselines. Use when a user asks if syntax already works, or when adding regression coverage for a specific script.
| 한국 출판사 투고용 제안서 작성 — 출판기획서 + 샘플 챕터 1-2개 + 마케팅 플랜 통합. book-concept-planner·book-target-reader·book-outline-designer·book-author-bio 4 스킬 산출물을 결합해 출판사 편집장이 1분 안에 통과 여부 판단할 수 있는 제안서로 가공. 한빛·길벗 IT / 민음사·문학동네 문학 / 웅진·다산북스 실용 / 한국문인협회 신인공모 양식별 자동 분기. 거절 신호 검출 및 사전 보완.
| 한국 출판사 제출용 도서 컨셉서 작성 — 한 줄·30자·300자 요약, USP 3축, 타깃 페르소나, 시장 포지셔닝 매트릭스를 한 흐름으로 산출. 의도파악 → 리서치(데스크+필드) → 인사이트 도출 3단계. 실용서·인문·기술·소설 4 장르 프리셋 자동 분기. KPIPA 통계·교보문고/알라딘 베스트셀러·도서정가제 등 한국 2026 출판 컨텍스트 내장.
| 도서 저자 약력·저자의 말·SNS·강연 통합 작성 — 저자가 타깃 페르소나에게 "왜 이 사람이 이 책을 쓰는가"를 1분 안에 설득하는 핵심 문서. book-target-reader의 페르소나·JTBD를 입력받아 4 장르별 신뢰 신호(학력·실무 경력·수상·팬덤·SNS·강연)를 자동 분기. 짧은 약력(50자)·중간(200자)·긴(500자) 3 길이 + 저자의 말(500-800자) 동시 산출.
| 도서 본문 퇴고·교열 코치 — 7 단계 점검(어법·문체·논리·인용·분량·시각자료·일관성)으로 출판 직전 원고를 다듬는 스킬. 국립국어원 어문규범 기준 + 한국 출판사 편집자 관점 + book-chapter-writer의 4 장르 문체 일관성 검증. korean-spell-check(맞춤법) + humanize-korean(AI 티) + ai-slop-reviewer(최종) 체인의 첫 단계. 분량 정리·인용 정합성·문체 통일·논리 흐름 검증 후 출판사 투고 준비 완료 상태로 출력.
| 도서 본문 챕터 초고 집필 — 꼭지 단위 작성·매수 관리·인용 처리·4 장르 문체 자동 분기. book-outline-designer의 챕터 시놉시스를 입력받아 한 꼭지를 처음부터 끝까지 완결성 있게 작성. 실용서(명료·실습)·인문(서사·문체)·기술(코드·도표)·소설(묘사·시점) 프리셋. 200자 원고지 매수 자동 카운트·인용 각주 표기·도표·코드 블록 통합.
| 도서 목차 설계 — 부·장·꼭지 3 레벨 구조 + 분량 배분 + 챕터 시놉시스. book-concept-planner와 book-target-reader의 산출물(USP·페르소나·JTBD)을 입력받아 4 장르별 목차 패턴 자동 적용. 실용서(Q&A·실습)·인문(서사)·기술(실습장)·소설(플롯) 프리셋. 한국 주요 출판사 목차 양식·KPIPA 표준 분량 가이드 내장.
| 한국 출판사 매칭 — 장르·규모·계약 조건·투고 채널·평균 인세를 4 차원으로 평가해 책 컨셉서·페르소나·저자 약력에 가장 적합한 출판사 Top 5를 추천. 책의 가능성을 극대화할 출판사 선정 + 투고 우선순위 + 협상 포인트 + 거절 후 차순위 시나리오까지 일괄 산출. 30+ 한국 주요 출판사 라이브러리 내장 (IT·실용·인문·문학·아동·전문서).
| 복잡한 분석·재무·운영 보고를 경영진 1페이지(≤500단어) 요약으로 변환합니다.
| 도서 타깃 독자 페르소나·JTBD(Jobs To Be Done)·페인포인트 매트릭스를 단계적으로 작성. book-concept-planner의 페르소나 1명을 입력으로 받아 4축 페르소나 카드 → JTBD 정의 → 페인포인트 매트릭스 → 독서 행동 데이터로 확장. 실용서·인문·기술·소설 4 장르 프리셋 자동 분기. KPIPA 독서 실태조사·교보문고 독자 분석 등 한국 2026 독자 행동 데이터 내장.
| 시장 규모(TAM/SAM/SOM)·경쟁사 분석·가격 전략을 정리한 시장 분석 보고서를 만들어 드립니다. 공개 데이터로 시장 규모·경쟁 구도·가격 모델을 분석하고, 인사이트와 권고안까지 정리합니다.
| 현황 진단부터 30-60-90일 실행 계획까지 담은 전문 컨설팅 제안서(브리프)를 만들어 드립니다. Executive Summary·현황 분석·문제 정의·권고사항·실행 로드맵 구조로 작성하며, PPT 변환이나 AI 표현 다듬기로 이어집니다.
| 투자 유치를 위한 IR 피치덱과 3개년 재무 모델(매출 예측·손익·현금흐름·밸류에이션)을 만들어 드립니다. 투자 단계(Pre-Seed~Series B)에 맞춘 12슬라이드 피치덱·재무 모델·예상 질문 Q&A를 만들고, PPT/엑셀 변환으로 이어집니다.
| 업계 뉴스·시장 동향·경쟁사 소식·규제 변화·오늘 할 일을 한 장으로 묶은 아침 비즈니스 브리핑을 만들어 드립니다. 국내외 뉴스·규제·시장 지표·경쟁사 동향을 시사점과 액션 아이템으로 묶어 5분 만에 읽히는 리포트를 만듭니다.
| 국토교통부(MOLIT) 실거래가/전월세 조회는 moai-public-data 플러그인을 사용하세요.
| 나에게 맞는 정부·공공기관 지원사업을 찾아주고, 심사 기준에 맞춘 사업계획서·신청서 초안을 만들어 드립니다(Word·한글·Excel 파일까지). 창업자·소상공인·중소기업·연구자·비영리단체·개인 누구나 쓸 수 있습니다. 지원사업 탐색·신청서 작성·서류 검토·일정 관리까지 도와주며, 마지막에 AI 표현 다듬기로 이어집니다.
| AI 기반 다차원 진단 분석 스킬. 기술, 프로세스, 사람, 비즈니스 4차원 병렬 진단을 통해 근본 원인을 식별하고 우선순위별 해결책을 제시합니다.
| 소상공인365(bigdata.sbiz.or.kr)에서 받은 상권분석 PDF를 첨부하면, 유동인구·경쟁 점포·예상 매출을 분석한 창업 타당성 보고서(Word)를 만들어 드립니다. PDF를 첨부하면 업종·예산·목적을 먼저 물어본 뒤, 5대 분석과 창업 타당성 점수까지 담은 보고서를 만들고 AI 표현 다듬기로 이어집니다.
| 타겟 기업·접근 전략·이의처리 시나리오·성공 지표까지 담은 실전 영업 플레이북(전략서)을 만들어 드립니다. 타겟 분석·접근 전략·이의처리·성공 지표를 한 문서로 묶고, PPT 변환이나 AI 표현 다듬기로 이어집니다.
> 한국 취준생·재직 이직자를 위한 채용공고(JD) 분해·기업 리서치·헤드헌터 오퍼 검증 스킬입니다. "채용공고 분석해줘", "JD 분석", "이 회사 어때?", "헤드헌터 오퍼 검토"처럼 말하면 됩니다. JD에서 필수/우대 역량 추출 + 본인 경험 매칭 + DART·잡플래닛·블라인드·사람인 공고 이력 종합 분석 + 2026 핀셋 채용 시대의 회사 현재 우선순위 추출까지 지원합니다.
Claude Skills — questions
Answers built from the skills we actually parsed.