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. 79 600 files from 1 763 authors, of which 61 947 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.
>- Run the idea-to-ship pipeline AUTONOMOUSLY, in character as a grounded founder-persona — composing ideate → deep-dive → prompt-pack → build-loop to take a real, grounded niche to a near-finish-line-AIMED first-draft product plus an honest ledger of what only a human or the market can finish. ALWAYS invoke when the user says any of "run autopilot", "build this idea→ship autonomously", "spin up a grounded founder and build it", "fly the whole pipeline end to end", or "autonomous first-draft from a concept". It composes the existing skills, never reimplementing them, and states its honest bounds — a near-finish-line first draft, NOT a finished or market-validated product (~80% craft ceiling; grounding firewall; its go/kill calls are a signal). Do NOT use to drive each phase by hand (use the skills directly), when there's no real grounding (you'd be inventing demand), or when you need market validation (the human handoff).
>- Audit an existing codebase, then autonomously implement the fixes it judges worth making against your next goal — composing deep-dive → triage → prompt-pack → build-loop to turn "here's what's wrong" into verified, receipted local commits + an honest ledger. ALWAYS invoke when the user says any of "audit this repo and fix what you find", "audit and edit", "deep dive then fix the bugs", "implement the audit's recommendations", "plan and execute these fixes", or "autopilot this repo but skip the ideation". It composes those it never proves correctness; the deep-dive→triage→pack half is proven, the build-loop seam is not; local commits only, never push/merge/tag/publish. Do NOT use to audit with no intent to change (deep-dive), for a change you already know you want (prompt-pack + build-loop), for a new idea with no codebase (autopilot), or for feature work — it fixes what the audit found, nothing more.
>- Rigorous multi-agent deep-dive analysis for complex investigative tasks — auditing codebases, evaluating strategies or systems, validating designs, doing open-ended research. Deploys 4–6 specialist agents in parallel across distinct lanes, then synthesis, then adversarial red-team review, then optional patching — producing structured markdown research files plus a plain-English executive briefing with honest 1–10 confidence ratings. ALWAYS invoke when the user says any of "deep dive", "thorough audit", "rigorous analysis", "comprehensive review", "audit this codebase", "analyze the strategy", "evaluate this design", "review this thoroughly", or "research deep dive". Also invoke proactively for any open-ended investigative task involving a codebase, strategy, system design, or research question that warrants 30+ minutes of structured analysis — even when the user doesn't use these exact phrases.
>- Take a fuzzy idea (or an existing thing you want to improve) through a disciplined funnel — explore → pressure-test → converge — and produce one honest co-founder (permission to overrule you), forces a success metric and a kill criterion before any roadmap, and hands off cleanly to the prompt-pack skill for building. ALWAYS invoke when the user says any of "help me figure out what to build", "I have an idea for…", "is this idea any good", "pressure-test this idea", "should I build / should I rebuild X", "evaluate whether my app/idea is worth building", "where are we really at", "is this idea or app worth pursuing", "iron out / scope / spec this concept", or "turn my idea into a plan/roadmap". Also invoke proactively when someone is reasoning about WHAT to build or WHETHER an idea is worth it — before any code or prompt pack exists.
GoFrame v2 development skill. Use only when the target Go project uses or is explicitly adopting GoFrame v2: the nearest go.mod requires github.com/gogf/gf/v2, existing Go files import github.com/gogf/gf/v2 or any github.com/gogf/gf/v2/... component package, or the user asks to scaffold, migrate, or build with GoFrame. Trigger for GoFrame-backed Go work such as APIs/controllers/services, middleware, routing/config, ORM/DAO/DO/entity/database operations, gf CLI/codegen, HTTP/gRPC services, and microservice conventions. Do not trigger for generic Go projects without GoFrame evidence, frontend-only work, shell scripts, or unrelated infrastructure tasks.
Unified Kaggle skill. Use when the user explicitly mentions Kaggle, kaggle.com, a Kaggle URL, Kaggle competitions, Kaggle datasets/models/notebooks, Kaggle forums/discussions/writeups, Kaggle benchmarks, hackathons hosted on Kaggle, Kaggle badges, or Kaggle account setup. Do not use for generic ML, GPU/TPU, notebook, dataset, benchmark, or data-science tasks unless the user clearly ties them to Kaggle.
> Summons a Council of 7 expert AI personas to debate any decision, idea, problem, or question from radically different perspectives — then synthesizes a structured verdict with confidence score, critical risks, and action steps. Use this skill whenever someone wants a decision analyzed, an idea stress-tested, a strategy evaluated, a career choice examined, a technical architecture reviewed, a business plan critiqued, a creative project assessed, or any situation where getting multiple expert viewpoints would lead to a better outcome. Trigger on phrases like "should I", "what do you think about", "help me decide", "review my", "is this a good idea", "council", "debate this", "stress-test", "get different perspectives on", "what are the pros and cons of". Also trigger when someone describes a plan, idea, or dilemma even without an explicit question — if it sounds like a decision worth examining from multiple angles, convene the Council.
Use Hermes delegate_task cleanly in this repo for planner, reviewer, researcher, reporter, experiment-worker, and memory-keeper roles.
Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing repositories, models, datasets, and Spaces on the Hugging Face Hub. Replaces now deprecated `huggingface-cli` command.
Operate the local Trackio reporter for Autolab HF Jobs. Use when a reporter or planner needs to inspect scores, active jobs, worker anomalies, duplicate launches, or the overall experiment board.
Run one Autolab benchmark experiment safely on Hugging Face Jobs. Use when a planner, reviewer, or experiment worker is preparing, auditing, launching, or reviewing a single train.py hypothesis against the current local promoted master.
Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.
Edit-Pass für bestehenden deutschen Text: Register/Rhythmus messen, belegtreu redigieren, Naturalness prüfen, KI-Schreibmuster/KI-Tells auditieren und entfernen; deutschen Text humanisieren; German AI Text Humanizer.
Deutscher Stil-Editor für Claude Code/Codex: Register messen, Rhythmus glätten, evidence-safe rewrites, Naturalness-Checks; deutschen Text humanisieren, KI-Schreibmuster/KI-Tells auditieren; German AI Text Humanizer.
Use when the user attended one or more sessions of a conference (with audio recordings + slide photos) and needs help building (1) faithful per-session reconstructions in markdown (slide visuals + speaker transcript with Whisper hallucination annotations), and (2) a downstream report deliverable whose scope and format are decided interactively with the user. Pipeline phase (raw → mlx_whisper Chinese SRT → per-slide multimodal reconstruction → official agenda cross-check via Playwright if available) is deterministic. Report phase is interactive — always quiz user on scope (single-session / single-day / multi-day synthesis), format (existing template / free-form fallback), recipient (formal / informal), and any business workstream mapping before drafting.
Use when the user reports misbehaving software to investigate — a bug, crash, wrong output, flaky behavior, or '為什麼壞掉/不會動/查一下' — and the root cause is not yet established. Enforces building a red-capable reproduction command BEFORE any hypothesis is allowed, then 3-5 ranked falsifiable hypotheses before testing any single one. NOT for conceptual questions, code reading requests, or feature work. When a failing command already exists, Step 1 is pre-satisfied — still apply, jumping straight to the hypothesis discipline.
Use when the user says 先討論 / wants to align on a fuzzy idea before building, or before any non-trivial implementation whose requirements are still ambiguous — interviews the user until shared understanding is confirmed, one question at a time, each with a suggested answer; facts answerable from the filesystem/code are looked up, never asked. Optionally maintains the repo's CONTEXT.md glossary when vocabulary settles during discussion. Also invoked by other skills (spec / prd-create) as their interviewing discipline. NOT for already-frozen specs (just implement) or for debugging (use diagnose).
Use when the user is solving an authorized CTF / lab reverse-engineering challenge focused on Windows application authentication or license-check bypass. Guides triage → static analysis → dynamic experiment planning → bypass verification, with strong evidence discipline and VM safety boundaries. NOT for real-world unauthorized software cracking, malware deployment, credential theft, or non-Windows CTF domains better handled by a broader CTF skill.
Use when the user wants to AUTHOR an unattended dispatch for either: (1) a goal-driven evaluator-optimizer loop of the GENERATE-AND-SELECT kind (generate candidates → grade against a rubric → iterate by reason-code → keep the best; the human picks the final selection), or (2) a lean build-to-spec run whose build spec is ALREADY FROZEN (approved ADR / locked design / accepted machine-checkable AC) and the only missing piece is the unattended-execution wrapper. A fresh-session agent runs the dispatch hands-off while the human only watches traffic-light push notifications. Interview-style forcing questions lock the spec, then it emits a self-contained dispatch markdown + a channel-agnostic notification protocol. This is the upstream SPEC AUTHOR, NOT a runtime: the dispatch is run by Claude Code's /goal, a headless `-p` session, or any unattended agent — /goal is the engine, this writes what you feed it. It NEVER authors build specs, product decisions, or AC — creating a build spec / PRD from raw input is prd-create. NOT a time scheduler (/loop or cron), NOT a recurring-push registrar (skill-cron).
Use when a durable technical decision was just made in conversation and should be recorded, or when user asks to write/record an ADR (開 ADR / 記個決策 / 這要不要 ADR). Runs a three-gate check FIRST and actively talks the user out of writing one when the decision doesn't qualify — then writes a lightweight (title + 1-3 sentences) ADR following the repo's own ADR conventions if any exist. Repo conventions always override this skill's defaults. NOT for requirement specs (spec / prd-create) or for rewriting history (superseded ADRs get a new ADR, never an edit).
Use when the user asks to generate an image via GPT/Codex (e.g. 「叫 gpt 生圖」「幫我用 gpt 生圖」「gpt 畫一個 X」). The skill drafts a Chinese + English prompt pair, iterates with the user until they explicitly approve, then dispatches Codex CLI ($imagegen skill, codex built-in image_gen) in the background, monitors progress, converts the result to a jpg in the current working directory, and writes a sidecar prompt log. Does text-to-image AND img2img — drop a reference image (on-disk file) and it runs Codex `-i` to lock a face/character across scenes.
Use when the user wants to build a consistent-identity LoRA for an original character — defining the character, generating a face/body-consistent multi-angle dataset (via the gpt-image-gen skill for codex image generation), captioning it, doing base-specific homework, training on a chosen base (Pony / Z-Image / others) on a local GPU, and producing a usable LoRA. This skill ORCHESTRATES the end-to-end pipeline and gates every expensive/irreversible step; it delegates actual image generation to gpt-image-gen and never improvises training settings from memory.
Use when the user is considering applying to, interviewing with, or accepting an offer from a company and wants due diligence on the company and optionally a specific role. Requires a company name, optionally a job title, then researches current public data, employee reviews, salary signals, product/tech quality, and red flags before giving a grounded recommendation. NOT for generic career coaching or resume editing.
Use when the user wants to lint a repo following the Karpathy LLM Wiki pattern (raw/ + wiki/ + SCHEMA.md / index.md / log.md). The skill detects path, scans wiki pages + schema layer, reports frontmatter gaps, broken in-body links, source traceability breaks, stale claims, orphan pages, index synopsis contradictions, and SCHEMA-vs-reality drift. Phase 1 is read-only report; Phase 2 (fix + log.md LINT entry) only runs after the user explicitly approves.
Use when the user wants to test, compare, or choose local Ollama models for their machine. Checks Ollama/GPU state, recommends model sizes from available VRAM, preserves existing benchmark records, pulls only approved models, runs repeatable benchmarks, restores stopped services, and writes a markdown comparison report. NOT for hosted API model evaluation or subjective chat-quality judging without local benchmark commands.
Use when user wants to break a PRD into Azure DevOps work items via vertical-slice plan. Workflow: read PRD → quiz user to lock durable decisions → draft slices with HITL/AFK + blocked_by → call az CLI directly via Bash to create items + Predecessor relations. Idempotent re-runs via fingerprint markers embedded in description. Pure prompt-driven — Claude is the runtime, no Python helper, no install ceremony. Trigger phrases: prd-breakdown / 拆 PRD / 切 vertical slice / 推 slice 到 ADO.
Use when the user wants to turn a Markdown report into a presentation-quality .pptx via interactive design decisions and a reusable hand-coded build script. Drives pre-analysis, global style choices, optional per-slide layout dialogue, python-pptx composition, and optional LibreOffice render self-check. NOT a generic auto-converter, NOT for PDF output, and NOT a fixed brand-template pipeline — brand integration is handled ad hoc through helper primitives.
Use when the user wants to lint a Claude Code memory directory (~/.claude/memory or custom path) for index inconsistency, stale project state, duplicate / conflicting feedback rules, naming convention violations, frontmatter gaps, and oversized files. The skill detects path, scans root-level *.md, reports findings by severity. Read-only — never auto-fixes, never deletes, never merges.
Use when the user wants to convert one Markdown file into a publication-ready A4 PDF, especially when the source may contain Mermaid diagrams, ASCII diagrams, CJK text, tables, or pandoc/weasyprint edge cases. Works by copying the source to a _pdf.md working file, converting diagrams, escaping PDF-breaking syntax, rendering with pandoc + weasyprint, then self-checking pages. NOT for batch conversion, slide decks, or editing the original Markdown in place.
Use when user wants to draft a PRD (Product Requirements Document) from raw input (meeting transcripts, hand-waved descriptions, scattered decisions). Workflow: load org's PRD Guideline + writing discipline → lock execution mode (human-run vs unattended-agent-run) → ingest raw input → quiz user numbered-list iterate to fill §1-§15 → draft v0.1 → handle stakeholder merge (review feedback, surface conflicts) → lock v1.0 + sanitize per ADO publication contract → publish to ADO Wiki. For an agent-run PRD, §13 carries the unattended-execution discipline (machine-checkable AC + traffic-light + 3-exits + stop-and-ask), aligned with goal-engineer's loop-run-protocol. NOT for packaging an ALREADY-FROZEN build spec (approved ADR / locked design / machine-checkable AC) into an unattended dispatch — that is goal-engineer's lean build dispatch. Pure prompt-driven — Claude is the runtime, no Python helper. Trigger phrases: 寫 PRD / PRD 撰寫 / prd-create / 初版 PRD / 起 PRD.
Use when the user wants to prepare a local project for GitHub or public release. Runs a release-readiness sweep over README structure, bilingual docs, commit hygiene, sensitive-data exposure, broken links, markdown rendering, project layout, tests, CI, Docker, and final cleanup. Fixes issues only inside the target repo and treats secrets/history rewriting as explicit high-risk gates. NOT for publishing without user approval or for private operational runbooks that should not be open-sourced.
Use when the user wants to evaluate a GitHub repository before installing, running, forking, or depending on it. Takes a GitHub repo URL, cleans tracking params, shallow-clones to /tmp, inspects dependency/supply-chain risk, static vulnerability patterns, issue-reported security problems, maintainer health, and produces a risk summary. NOT for reviewing the user's own PR diff or for running untrusted code.
Use when the user wants a Traditional Chinese (Taiwan) language review of Markdown or plain-text files — flagging genuinely comprehension-breaking grammar faults (missing subject, broken predicate, wrong measure word, misused connectives, inconsistent naming) and non-Taiwanese wording (mainland-Chinese terms, translationese) with replacement suggestions. High bar on grammar: only reports what actually misleads the reader; pure style preferences, punctuation nits and unavoidable loanwords are let through. Phase 1 is a read-only report; Phase 2 (applying edits) only runs after the user explicitly approves. NOT for changing tone or voice (that is rewrite-tone), NOT for rewriting content, adding facts, or translating between languages.
Use when the user wants to rewrite Markdown prose into a conversational, humorous, self-deprecating engineering tone while preserving technical accuracy and document structure. Rewrites prose sections only, keeps code blocks, diagrams, tables, English summary blocks, and factual claims intact. NOT for changing requirements, adding new technical content, or editing non-Markdown artifacts.
Use when the user wants a spec-driven development workflow for implementing a feature in the current codebase, from fuzzy idea or existing active spec through requirements, technical plan, tasks, implementation, verification, and closure report. Auto-detects project/spec state, writes persistent files under specs/, asks one grounded question at a time when requirements are ambiguous, and stops at stage gates. NOT for stakeholder PRDs (prd-create), ADO ticket breakdown (prd-breakdown), single architecture-decision records (adr), or already-frozen tasks that should simply be implemented.
Use when the user wants privacy-respecting web, image, news, or video search through a configured local SearXNG instance instead of external search APIs. Calls the bundled script against SEARXNG_URL, supports result limits/categories/language/time range, and can return human-readable or JSON output. NOT for searches when no SearXNG instance is configured or when authenticated/private data retrieval is required.
Use when the user wants to register, inspect, manually run, or remove scheduled Claude skills with Telegram push notifications. Presents a menu, discovers schedulable skills with headless-prompt frontmatter, converts natural-language schedules into cron entries with conflict confirmation, writes managed config, and verifies notification delivery. NOT for one-off task execution without scheduling or for running skills that lack a headless prompt.
Use when the user is unsure which kc_ai_skills workflow skill to use, or describes work involving PRD, SD/software design, FR, AC/acceptance criteria, ADR, tickets, implementation, debugging, release checks, or unattended agent execution. Triage the request with at most one clarifying question when needed, explain the route in plain language, then hand off to the right specialist skill. This is an entry router only: it does not write PRDs, specs, ADRs, tickets, or dispatches itself.
> Official Feature-Sliced Design (FSD) v2.1 skill for applying the methodology to frontend projects. Use when the task involves organizing project structure with FSD layers, deciding where code belongs, placing static assets (images, icons, fonts, PDFs), grouping closely related slices, defining public APIs and import boundaries, resolving cross-imports or evaluating the @x pattern, deciding whether to create or remove an entity, evaluating whether the entities layer is needed at all, deciding where page layouts belong or whether to use the widgets layer (discouraged), deciding whether logic should remain local or be extracted, migrating from FSD v2.0 or a non-FSD codebase, integrating FSD with frameworks (Next.js App Router and Pages Router, Nuxt, Vite, Astro), or implementing common patterns such as authentication, API handling, Redux, and TanStack Query (React Query) within FSD.
>- Parallel-research-then-converge design workflow between two agents. Use this skill when the user wants two agents to independently think through a design problem before aligning on a solution — "spec X with codex", "design X together", "both agents think through X", "brainstorm architecture together", "parallel research then joint proposal", "think through separately then align", "careful thought from both sides before coding", or any variation where the user wants collaborative design rather than just splitting implementation work. Also use this when you receive a message labeled sending simple messages or reviews (use /amq-cli), implementing completed designs, or creating document templates.
>- Coordinate agents via the AMQ CLI for file-based inter-agent messaging. Use this skill whenever you need to send messages to another agent (codex, claude, or any named handle), check your inbox, drain queued messages, set up co-op mode between agents, join a swarm team, route messages across projects, or diagnose delivery issues. Also use it when you receive a message and need to know how to reply, inspect receipts, or handle priority. Covers any multi-agent coordination task where agents need to talk to each other — review requests, questions, status updates, decision threads, wake notifications, and orchestrator integration (Symphony, Kanban). For collaborative spec/design workflows specifically, prefer the /amq-spec skill which provides structured phase-by-phase guidance. Not intended for distributed systems design (RabbitMQ, Kafka), CI/CD pipelines, or single-agent tasks with no partner.
Hyper-Waterfall workflow entrypoint for Codex. Use when starting or continuing issue-based Hyper-Waterfall tasks, checking lifecycle init/update paths, or finding canonical manuals and skills.
Use when the user wants to apply or run the Hyper-Waterfall workflow from Claude Code. Read the repository canonical files and route the task through the existing Hyper-Waterfall gates instead of redefining the workflow.
| 即使用户只是说"我的 Obsidian 堆了一堆没处理的东西",也应该触发。
Source b-roll for a video edit — classify each moment, scope the search, return vetted candidates, place on the word. Use when the user says "find b-roll", "/find-broll", "source clips for this edit", or wants footage/memes/screenshots to lay over a talking-head video.
在使用 js-reverse-mcp 做前端 JavaScript 逆向时使用，适用于签名链路定位、页面观察取证、运行时采样、本地补环境复现与证据化输出。优先适配当前环境里的 js-reverse_* 工具。
Provides reverse engineering techniques. Use when the main job is to understand how a compiled, obfuscated, packed, or virtualized target works before exploiting or solving it, including binaries, APKs, WASM, firmware, custom VMs, bytecode, game clients, malware-like loaders, and anti-debug or anti-analysis logic. Do not use it when the vulnerability is already understood and the remaining task is exploitation; use pwn instead. Do not use it for pure web workflows, log or disk forensics, or standalone crypto problems unless reversing the implementation is the real blocker.
| IDA Pro 逆向分析辅助技能。当用户提到逆向、反编译、分析二进制/PE/ELF/APK/DLL/SO、破解、找密码、漏洞分析、病毒分析、firmware 固件分析，或需要分析 exe/dll/so/elf/macho/sys 等文件时，务必使用此技能。 Ensure to use this skill when the user wants to analyze any binary file, regardless of whether they explicitly mention "IDA" or "reverse engineering". This includes requests like "看看这个exe", "分析这个dll", "帮我破解", "找一下密码", "这个软件怎么注册", etc. Use the bundled scripts (scripts/start.ps1, scripts/open.ps1) for deterministic server management and file opening — do NOT write ad-hoc PowerShell commands for these operations.
在 CLI 环境下做 Android APK 逆向时使用。适用于 APK 解包、Java 反编译、smali 修改、重打包、Frida 动态 Hook，以及按需切换到 so/native 分析。优先使用本机已安装的 jadx、apktool、frida、adb、ida-reverse、radare2。
| Use this skill whenever the user wants to analyze binaries with radare2/r2 from the command line, including reverse engineering, disassembly, function analysis, strings/import inspection, patching, binary diffing, hex inspection, or r2 scripting. Also use it when the user mentions PE/ELF/Mach-O/DEX/WASM files together with CLI analysis, `rabin2`, `rasm2`, `radiff2`, `r2pipe`, or asks for radare2 command help on Windows/Linux/macOS.
Create modular skill documents (SKILL.md files) for Claude Code. Use this skill whenever a task requires generating reusable knowledge documents, capturing domain expertise, or building skills that encode workflows, APIs, or specialized techniques. Invoke this whenever you need to write a SKILL.md from scratch, even if the user doesn't explicitly ask for a "skill".
Anthropic's official brand color palette, design tokens, and typography standards for consistent brand application.
Create technical graphics, diagrams, and posters using Python Pillow library with precise color control and typography.
Design principles and techniques for creating technical exploded-view diagrams and engineering documentation posters.
Compose classical Chinese poetry on peace themes using authentic imagery, perspective shifts, and the voice of ordinary people experiencing war's aftermath.
Master modern Mandarin pinyin finals and tone systems to create accurate rhymes for classical poetry following contemporary pronunciation standards.
Master the structure, tonal patterns, and rhyming requirements of classical seven-character regulated verse (七言律诗) in Chinese poetry.
Understand the structure and fields of the California Small Claims Court Form SC-100
Fill PDF form fields programmatically using Python libraries like pypdf or pdfrw
Implement DBSCAN clustering with custom distance metrics using scikit-learn's pairwise_distances.
Claude Skills — questions
Answers built from the skills we actually parsed.