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 167 of 304
- View details
optimus-primeSkillAI & models
Generates a Claude Code configuration tailored to a specific project. Use whenever the user wants to prime a project, set up claude for a repo, bootstrap claude config, or re-prime/refresh an already-primed project (for example after `/prime-sync` pulled new starter content). Triggers on 'prime', 'p
Ready to connect★ 120
- View details
requirement-ledger-workflowSkillAI & models
FIRST RESPONSE CONTRACT for one selected Chinese project: a takeover's first visible text, including any required Skill-use announcement, must begin exactly `可以接管。`; a progress request's complete pre-tool acknowledgement must be exactly `可以汇报。`. Treat a report from the current CONTEXT checkpoint as
Ready to connect★ 120
- View details
self-evolveSkillAI & models
The single config quality skill. Two modes: (1) Default — review/wire pending self-improvement proposals. (2) Audit — analyzes skills, rules, CLAUDE.md, project refs, hooks, and agents against the actual codebase to find inaccuracies, trigger overlaps, stale references, and weak rules, then fixes th
Ready to connect★ 120
- View details
update-backend-runtimesSkillAI & models
Update the target OpenCode, Codex, GitHub Copilot, Cursor, DeepSeek, Grok Build, Claude Code, Hermes Agent, Pi, and OMP CLI versions used by the Sesori bridge. Use when asked to update, bump, or refresh coding harness targets, managed runtimes, or release checksums while preserving compatibility min
Ready to connect★ 120
- View details
update-pi-harnessSkillAI & models
Audit and update Sesori's Pi Agent Harness target while finding protocol capabilities, event changes, and simplifications worth integrating. Use when refreshing the Pi runtime pin or reviewing a new Pi release.
Ready to connect★ 120
- View details
vipassana-llmSkillAI & models
Apply Vipassana meditation principles to LLM processing — equanimous scanning, non-reactive observation, impermanence awareness (anicca), and breaking the sankhara chain of conditioned reactions. Trigger on "meditate on", "observe without reacting", "see clearly", "practice vipassana", "scan equanim
Ready to connect★ 119
- View details
workonSkillAI & models
Switch working context to a project. Loads AGENTS.md, git status, and td issues.
Ready to connect★ 119
- View details
zero-slopSkillAI & models
Turn drafts into sharp, natural prose or inspect them without rewriting. Zero Slop runs inside the user's existing AI assistant; Claude, GPT, or another compatible model reads and edits in context while local tools point to exact phrases and protect the source. Use when the user asks to humanize or
Ready to connect★ 118
- View details
brand-system-builderSkillAI & models
Guides Lovart Agent from one visual reference to a coherent brand system, campaign assets, and packaging concepts through a gated creative-direction workflow.
Ready to connect★ 117
- View details
claude-code-e2eSkillAI & models
Run end-to-end smoke tests for the Mycelium claude_code adapter. Verifies claude CLI prereqs, the SKILL.md + workspace install, and the resident participation loop (mycelium await --loop --exec) where a live claude session picks up an @-mention, reasons, and posts a reply back to the room — includin
Ready to connect★ 118
- View details
cursor-e2eSkillAI & models
Run end-to-end smoke tests for the Mycelium cursor adapter. Verifies cursor-agent prereqs, the resident participation loop (mycelium await --loop --exec) picking up an @-mention and posting a reply, workspace asset drift/healing, auth-failure handling, and an aligner-mediated negotiation with a resi
Ready to connect★ 118
- View details
dependabot-reviewSkillAI & models
Analyzes a Dependabot PR to determine what actually changed in each bumped package and whether those changes affect this repo. Reports changed APIs/methods, which doc pages use them, and the realistic probability of any visible impact on the docs site.
Ready to connect★ 118
- View details
flux-3-prompt-doctorSkillAI & models
Use when diagnosing a FLUX 3 brief before generation. Resolve missing, conflicting, or schema-changing requirements.
Ready to connect★ 116
- View details
recursive-debuggingSkillAI & models
Use when a recursive-mode requirement involves debugging a bug, test failure, or unexpected behavior. Insert Phase 1.5 between Phase 1 and Phase 2 to perform systematic root cause analysis before attempting any fixes. Trigger phrases: "debug", "investigate", "failing tests", "crash", "root cause".
Ready to connect★ 118
- View details
recursive-review-bundleSkillAI & models
Use when recursive-mode work needs a canonical delegated-review or audit handoff. Generates reproducible review bundles for Phase 3.5 code review, test review, or other delegated checks using the repo review-bundle scripts.
Ready to connect★ 118
- View details
recursive-routerSkillAI & models
Use when recursive-mode needs to route delegated audit, review, or bounded implementation work through external transports, CLIs, and models while preserving controller verification and fallback behavior.
Ready to connect★ 118
- View details
recursive-specSkillAI & models
Approval-gated, repo-aware requirements/spec authoring for new recursive-mode runs. Use when the user wants help creating a plan, spec, scope, or requirements for work that does not yet have a run, especially prompts like "create a plan", "help me plan", "create a spec", "write requirements", or sim
Ready to connect★ 118
- View details
recursive-tddSkillAI & models
Use when implementing any code in recursive-mode Phase 3. Enforces strict RED-GREEN-REFACTOR discipline with The Iron Law - no production code without a failing test first. Trigger phrases: "implement this", "add feature", "fix bug", "write a failing test", "TDD".
Ready to connect★ 118
- View details
recursive-worktreeSkillAI & models
Use when starting any recursive-mode requirement to set up an isolated git worktree. Required before implementation phases: create an isolated workspace, verify a clean baseline, and keep main/master clean.
Ready to connect★ 118
- View details
role-modelSkillAI & models
Connect Codex to a local role-model runtime via the codex-role-model adapter.
Ready to connect★ 118
- View details
janitor-swipeSkillAI & models
Tinder for your Claude Code skills. Reviews a sorted deck of every installed skill and lets you swipe keep / delete / skip on each one. Use when the user wants to bulk-clean their skill collection, triage unused skills, or do interactive skill cleanup. Trigger with '/janitor-swipe'.
Ready to connect★ 117
- View details
management-consultantSkillAI & models
MBB-level management consultant with mastery over structured thinking, frameworks, guesstimation, industry analysis, and executive-grade deliverables. Use this skill for: solving business problems, structuring cases, market sizing, profitability analysis, market entry, M&A, pricing, operations, digi
Ready to connect★ 117
- View details
app-review-analyzerSkillAI & models
Systematically analyze app reviews for competitor research or own-app reputation management. Categorize reviews by sentiment and themes (bugs, missing features, UX complaints, pricing objections, praise, support issues), identify actionable patterns, produce structured analysis reports, and draft pr
Ready to connect★ 116
- View details
book-research-assistantSkillAI & models
Plan, orchestrate, and validate deep research for nonfiction books. Use when an author has completed book architecture and needs to fill research gaps before outlining chapters. Triggers include requests to plan research, generate research prompts, validate research quality, or prepare for drafting.
Ready to connect★ 116
- View details
debuggerSkillAI & models
Use rust-gdb to inspect variables and step through code without modifying it. Prefer this over print debugging when investigating compiler internals or runtime behavior (lldb is unavailable on Claude Code Web).
Ready to connect★ 116
- View details
dhh-writingSkillAI & models
This skill should be used when writing in the distinctive style of David Heinemeier Hansson (DHH). It applies when creating blog posts, technical articles, business content, manifestos, or any prose requiring a clear, punchy, opinionated style.
Ready to connect★ 116
- View details
intranet-penetration-testingSkillAI & models
内网渗透测试深度专业技能：本地信息收集与凭证窃取(mimikatz/LSASS/ntds.dit)、内网探测与隐藏隧道(frp/Chisel/DNS/ICMP)、Windows/Linux提权、横向移动矩阵(IPC/WMI/DCOM/PSEXEC)、AD域渗透与域控接管(Zerologon/Kerberoast/ADCS)、权限维持与痕迹清除、免杀与C2、AI大模型内网攻击面(Ollama/vLLM/向量数据库/RAG/MCP/Agent)、AI辅助红队作战(路径分析/免杀增强/自动化)
Ready to connect★ 116
- View details
secure-code-reviewSkillAI & models
安全代码审计深度专业技能 v3.0：攻击面驱动的审计优先级方法论（入口点→数据流→敏感操作）、多语言漏洞模式识别（Java/Python/Go/Node.js/PHP/C#）、数据流与污点分析、认证授权审计、业务逻辑审计、供应链代码审计（依赖投毒/后门植入/恶意包）、反混淆与对抗审计、AI 大模型辅助审计（LLM+SAST 协同/提示词模板/幻觉治理）、DevSecOps CI 集成与绕过、审计报告与证据链
Ready to connect★ 116
- View details
vendor-submodulesSkillAI & models
Locate and sync the vendored reference specs and runtimes under vendor/ (Wasm, WASI P3, and Component Model specs; wasm-tools, wasmtime sources). Use when you need to read a Wasm/WASI/CM spec or wasmtime/wasm-tools source, or when vendor/ submodules are missing and need initializing.
Ready to connect★ 116
- View details
wado-performanceSkillAI & models
Analyze and improve the runtime speed of a Wado program's compiled guest Wasm — profile hot functions, read the generated WIR for allocations and copies, reason about the WasmGC cost model, and A/B-measure a fix. Use for guest-side speed work (serde, parsers, numeric loops, hot stdlib). For host-sid
Ready to connect★ 116
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.