Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: AI & models
9,105 results · page 162 of 304
- View details
wjs-distilling-styleSkillAI & models
Use when the user wants to capture a writer's voice from a few sample articles and rewrite text to sound like that author — "蒸馏文风", "提炼XX的风格", "把这篇改成XX的味儿", "学某某笔法改写", "mimic this writer", "match this author's style", "style transfer". Works for any author, 王建硕 included.
Ready to connect★ 129
- View details
wjs-eating-and-growingSkillAI & models
吃一堑长一智 (learn from a setback) — complete the 5-step interactive reflection (堑 → automatic output → old weights → new parameters → alternative action), moving from "emotional review" to "behavioral training," retraining the L3 weights of the first-reaction layer. Use when 王建硕 reflects on a personal s
Ready to connect★ 129
- View details
wjs-evaling-voicedrop-promptsSkillAI & models
Use when 王建硕 wants to evaluate whether a change to VoiceDrop's 挖矿 system prompt is actually better than the live version — runs the local eval harness (golden fixtures × champion-vs-candidate, same input), dispatches blind pairwise judge subagents, aggregates a win-rate verdict, and on approval prom
Ready to connect★ 129
- View details
wjs-polishing-x-engagementSkillAI & models
Rewrites a plain Chinese tweet/post into a high-engagement version backed by real facts and equipped with interaction hooks, delivering 2-3 versions with different hooks each time; the style must be short, plain, and conversational. Use this skill whenever a user posts a Chinese tweet/post/Weibo pos
Ready to connect★ 129
- View details
wjs-promoting-skillsSkillAI & models
Use when the user wants to set up automated daily promotion / marketing for their Claude Code skills — researching how top skills are promoted on marketplaces (ClawHub / openclaw / SkillsMP / agentskills.io), generating a per-skill marketing plan, auto-posting to X (Twitter) via xurl, and drafting c
Ready to connect★ 129
- View details
wjs-publishing-appstoreSkillAI & models
Use when an iOS app already on TestFlight needs to ship to the App Store — preparing the screenshots and the description/metadata, then using the existing fastlane setup to submit for review. Triggers — 「提交 App Store」「上架」「app store 审核」「准备截图和文案」「submit for review」「/wjs-publishing-appstore」.
Ready to connect★ 129
- View details
wjs-publishing-books-to-xSkillAI & models
Use when 王建硕 wants to publish his VoiceDrop books (voicedrop.cn/books) to X/Twitter as threads — 列出他写的书、挑没发过的、整本拆成推文串发出。Triggers — "把书发到 X", "发书的 thread", "publish my book to X", "书架的书发推", "/wjs-publishing-books-to-x".
Ready to connect★ 129
- View details
wjs-publishing-testflightSkillAI & models
Set up fastlane + GitHub Actions for an iOS project so that pushing to the main branch automatically builds and uploads to TestFlight. Reference implementation: the Cathier project. Trigger words: "testflight", "fastlane", "自动构建", "CI TestFlight", "/wjs-publishing-testflight".
Ready to connect★ 129
- View details
wjs-syndicating-articlesSkillAI & models
Use when the user wants to auto-syndicate their latest 微信公众号 article across social platforms — picks the newest un-syndicated article, extracts one core copy, auto-posts to API platforms (X / Bluesky / Threads / LinkedIn) and prepares a copy-paste outbox for manual platforms (Facebook / 小红书 / 即刻 / 知
Ready to connect★ 129
- View details
wjs-translating-subtitlesSkillAI & models
Use when the user has an SRT (or transcript text) in one language and wants it translated to another, with punctuation-bounded re-segmentation so cues end at real sentence breaks. Simplified Chinese (zh-CN) and English (en) are first-class targets; other targets follow the same rules. Outputs a targ
Ready to connect★ 129
- View details
wjs-tweeting-from-articlesSkillAI & models
Use when the user wants to post a daily X/Twitter tweet inspired by one of their recently-published 微信公众号 articles. Picks the newest article that hasn't been tweeted yet, drafts 3 tweet candidates from it (different angles — quote / metaphor / one-liner), posts the chosen one via xurl, records to hi
Ready to connect★ 129
- View details
wjs-voicedropSkillAI & models
Entry point for VoiceDrop. All capabilities live in the MCP (voicedrop.cn/mcp, 44 tools: article read/write and versioning, style and distillation, mining and rewriting, community and tipping, compute power, sharing/WeChat Official Account/Xiaohongshu, bookshelf reading and writing/revising books).
Ready to connect★ 129
- View details
wjs-x-improving-contentSkillAI & models
Use when 王建硕 wants to systematically improve his X (Twitter) content by iterating on the content-generation prompt (prompts/x/prompt.md, used by the every-6h tweet Action) and finding which prompt version produces the highest-reach tweets. Each prompt edit is a git-SHA-versioned, numbered experiment
Ready to connect★ 129
- View details
cross-ref-researchSkillAI & models
Use when implementing, extending, auditing, or QAing LLM Chess data/cross-ref workflows: external eval source snapshots, conservative model mapping, run_cross_ref.py commands, generated results, consolidated reports, mapping review, cross-eval reports, reproducibility audits, and verification.
Ready to connect★ 128
- View details
fastapi-backend-scaffoldSkillAI & models
Generates a standard FastAPI backend layered-architecture directory scaffold. Triggered when the user needs to build a FastAPI backend from scratch, refactor the backend directory structure, or create a new backend project. The skill includes production-grade template code such as an LLM multi-model
Ready to connect★ 127
- View details
fix-bugSkillAI & models
Autonomous bug-fix workflow. Guides the orchestrator through state detection, implementation, test/lint validation, and a bounded fix/review loop with an independent reviewer subagent. Use when fixing a GitHub bug report, or when the user says "fix bug", "bugfix", or references a bug issue or PR suc
Ready to connect★ 128
- View details
langchain-langgraph-coding-assistantSkillAI & models
Provides example-based coding assistance when users need to write LangChain or LangGraph code, including implementation guidance for RAG, Agents, workflows, tool definitions, middleware, and other functional modules.
Ready to connect★ 127
- View details
pathmcSkillAI & models
Bayesian path analysis (observed-variable SEM) in PyMC. Compiles a lavaan-inspired formula DSL into a generative PyMC model, then layers introspection, identification diagnostics, the `do()` operator, and causal estimands (ATE/CATE/ATT/ATU/prob) on top. Use when the user asks to specify, fit, or que
Ready to connect★ 128
- View details
community-godmodeSkillAI & models
Jailbreak API-served LLMs using G0DM0D3 techniques — Parseltongue
Ready to connect★ 126
- View details
community-native-mcpSkillAI & models
Built-in MCP (Model Context Protocol) client that connects to
Ready to connect★ 126
- View details
community-skills-first-web-avl-reviewSkillAI & models
"Review, position, and polish Agent View Layer (AVL) / agent-first
Ready to connect★ 126
- View details
community-webhook-subscriptionsSkillAI & models
Create and manage webhook subscriptions for event-driven agent
Ready to connect★ 126
- View details
specforge-projectSkillAI & models
Use when the user wants to build, create, plan, architect, scope, or spec a software project, app, platform, agent, API, tool, SaaS product, or major development feature. This skill requires routing development-project requests through the SpecForge tool before implementation.
Ready to connect★ 126
- View details
workforce-setupSkillAI & models
Guide the operator through creating a workforce role, drafting the relationship contract, choosing the target family/primary agent, and starting the worker in the correct staged mode. Use when the user wants to set up a worker, employee role, job template, or assignment conversationally.
Ready to connect★ 126
- View details
autodev-parallelSkillAI & models
Parallel version of the Ralph Loop. Multiple agents simultaneously handle PRD items in worktrees. Triggers: "PRD 항목 병렬 구현", "병렬 구현", "autodev parallel", "워크트리 병렬 개발", "병렬 랄프". Anti-triggers: "순차 구현", "하나씩"
Ready to connect★ 125
- View details
docs-architectureSkillAI & models
Generate/update architecture docs — ARCHITECTURE.md (code map), architecture diagrams (C4 mermaid), ADRs (MADR), data model ERDs. Use when writing/updating architecture docs or diagrams, recording ADRs, documenting ERDs/data models, or reflecting structural refactoring in docs. For API specs use doc
Ready to connect★ 125
- View details
dont-lie-to-meSkillAI & models
Use when the user explicitly wants evidence-disciplined answers that separate observed facts, sourced claims, user reports, inference, unknowns, and contradictions before making strong factual or completion claims.
Ready to connect★ 125
- View details
harness-auditSkillAI & models
Diagnoses and scores the overall health of the harness (hooks, skills, agents, rules). Scope: the global ~/.claude harness (for project diagnostics, use harness-diagnostics). Triggers on: harness audit, 하네스 진단, 설정 점검, 하네스 점검. NOT for: writing code or implementation.
Ready to connect★ 125
- View details
harness-diagnosticsSkillAI & models
Self-diagnosis and improvement suggestions based on the 12 principles of agent harnessing. No automatic triggering — run manually with /harness-diagnostics (select setup/audit/maintenance mode as arguments). NOT for: code implementation, bug fixes, test writing.
Ready to connect★ 125
- View details
hermes-session-handoffSkillAI & models
Use when a Hermes session, profile, machine, or agent must hand ongoing work to a fresh continuation context without losing verified state, decisions, artifacts, blockers, or the exact next action.
Ready to connect★ 125
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
55,111 of the 55,543 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.