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 168 of 304
- View details
writing-orchestrationSkillAI & models
This skill should be used when orchestrating complex writing workflows with multiple phases. It provides two-agent orchestration patterns, the two-gate content readiness assessment, 10 baseline writing strategies, 20+ situational strategies, and quality checkpoints. Inspired by the Spiral Writing Sy
Ready to connect★ 116
- View details
xcode-makefilesSkillAI & models
Install strict Xcode Makefile tooling for iOS/macOS projects, including build/run/test scripts with AGENT_NAME-based per-agent isolation under build/. Use when a project needs reproducible local CLI builds without full app scaffolding.
Ready to connect★ 116
- View details
agentic-reviewSkillAI & models
Use when reviewing current branch for bugs before pushing or merging, when wanting a thorough multi-agent review of local changes, or when preparing work for human review. Not for codebase structure, not for code style, and not for fixing what it finds.
Ready to connect★ 115
- View details
<skill-slug>SkillAI & models
One-line description of what this fix does and why it matters.
Ready to connect★ 114
- View details
aider-1h-ttlSkillAI & models
Aider uses 5min TTL by default and works around long pauses with keepalive pings. Wire up the 1h TTL beta instead.
Ready to connect★ 114
- View details
aider-cache-default-onSkillAI & models
Aider's --cache-prompts is off by default. Flip it on for supported models.
Ready to connect★ 114
- View details
cline-fix-volatile-msgSkillAI & models
Ladder-aware Cline Anthropic caching — verify the rolling read/write ladder on the wire, then add the tools breakpoint and tune TTL. Updated for the 2026-08 AI-SDK monorepo.
Ready to connect★ 114
- View details
cline-pin-timestampSkillAI & models
Cline's system prompt includes a timestamp that may be recomputed per request, invalidating the system-prompt cache.
Ready to connect★ 114
- View details
continue-enable-defaultsSkillAI & models
Continue's prompt caching is opt-in via config and off by default. Flip the default to systemAndTools.
Ready to connect★ 114
- View details
continue-fix-volatile-msgSkillAI & models
Ladder-aware Continue Anthropic caching — verify the rolling ladder on the wire, then enable it by default and add TTL coverage.
Ready to connect★ 114
- View details
continue-gemini-explicitSkillAI & models
Continue's Gemini provider doesn't use the cachedContents API at all. Add explicit caching for sessions over the minimum token threshold.
Ready to connect★ 114
- View details
kinema-novelSkillAI & models
Write, continue, or take over long-form novels in a Kinema workspace. Use when the user mentions web novel serialization, character consistency, unified writing style, foreshadowing payoff, volume outlines, ten-chapter batches, or the seven-gate review; the Agent handles the writing, while the engin
Ready to connect★ 114
- View details
kn-claySkillAI & models
Turns themes or stories into handmade stop-motion animation. Use when the user mentions stop motion, clay, Gundam models, figures, nendoroids, building blocks, or desktop toy theater; set the piece in one of four traditional materials: clay, Gundam, figures, or building blocks.
Ready to connect★ 114
- View details
opencode-detect-openai-compatSkillAI & models
OpenCode's caching detection misses OpenAI-compatible proxies routing to Anthropic/Bedrock. Broaden the predicate.
Ready to connect★ 114
- View details
opencode-mistral-cache-keySkillAI & models
OpenCode doesn't set prompt_cache_key for Mistral models, missing the documented 10% cached-token discount.
Ready to connect★ 114
- View details
plan-compassSkillAI & models
Stress-tests a plan through dependency-aware, easy-to-answer decision prompts. Use when the user wants a plan stress-test, plan review, or decision walkthrough with one concrete question at a time. During decision questions, use these labels: `Decision N of M: Topic`, `State`, `Question`, `Recommend
Ready to connect★ 113
- View details
roo-bedrock-custom-arnSkillAI & models
Roo Code's Bedrock provider silently disables caching for custom ARNs. Populate cachableFields to fix.
Ready to connect★ 114
- View details
roo-fix-volatile-msgSkillAI & models
Ladder-aware Roo Code Anthropic caching — verify the rolling read/write ladder on the wire, then close the real gaps (Vertex 4-block budget, MiniMax path).
Ready to connect★ 114
- View details
uxcSkillAI & models
Discover and call remote schema-exposed interfaces with UXC. Use when an agent or skill needs to list operations, inspect operation schemas, and execute OpenAPI, GraphQL, gRPC, MCP, or JSON-RPC calls via one CLI contract.
Ready to connect★ 114
- View details
autoshipSkillAI & models
Runs the npm release flow for an existing changesets package: write the changeset, fix lint/type/test/format failures, push, watch CI, merge the Version Packages PR, watch the publish run, and verify the version on npm. Diagnoses release-side failures: the Changeset Status check, changesets/action v
Ready to connect★ 111
- View details
codebase-architectureSkillAI & models
Designs, deepens, and hardens TypeScript codebase architecture in three modes: folder structures, module contracts, request context, and middleware pipelines for a new app; domain-informed deepening of existing code; and the guardrail tooling, CI gates, and wayfinding that stop a structure decaying.
Ready to connect★ 111
- View details
communicateSkillAI & models
All agent communication from culture: in-mesh chat (channels, DMs, mentions, knowledge sharing) via `culture channel` CLI, AND cross-repo hand-off briefs to sibling-repo agents (agentirc, steward, cultureagent, …) via `post-issue.sh` / `post-comment.sh`, plus inbound issue reads via `fetch-issues.sh
Ready to connect★ 113
- View details
cultureSkillAI & models
Culture admin and ops — set up servers, configure mesh linking between machines, manage agent lifecycle, federation, and trust. Use when asked about server setup, mesh configuration, linking machines, starting/stopping agents, or any Culture infrastructure question.
Ready to connect★ 113
- View details
doc-test-alignmentSkillAI & models
Verify that committed docs (README.md, CLAUDE.md, SKILL.md descriptions) still describe what the code and tests actually do. Use at the end of a plan, before PR creation, or when the user says "check doc-test alignment", "verify docs", or "do the docs still match the code". STUB — `scripts/check.sh`
Ready to connect★ 113
- View details
eli5SkillAI & models
Rewrites assistant talk into plain language a smart adult can follow on the first read: one-sentence gist, one everyday analogy, sentences under 25 words, next action first, and no AI writing tells. Use when asked to "ELI5", "explain like I'm 5", "wait what", "re-pitch that", "in plain English", "du
Ready to connect★ 111
- View details
minimax-h3-prompt-reviewerSkillAI & models
Downstream MiniMax H3 specialist that audits, repairs, and rewrites T2VA, I2VA, FL2VA, L2VA, and full-reference prompts into an official structured format. Use after minimax-h3-creative-director routes an existing prompt for diagnosis or repair, or when explicitly invoked for formatting, timeline, c
Ready to connect★ 112
- View details
novel-checkSkillAI & models
LLM connectivity self-check: makes one minimal real call to the default model and each role model, reporting one by one whether each provider/model is actually usable. Triggers: "check if the LLM works", "test model connectivity", "confirm the config before writing", "why does every call fail". Use
Ready to connect★ 113
- View details
novel-douban-writeSkillAI & models
A specialized entry point for using novel-studio to generate original long-form novels for Douban Read. Suitable for original long works of 150K-300K characters; by default it writes the Douban writing contract into the prompt and chains review/rewrite/export. Triggers: 「豆瓣长篇」「按豆瓣要求写」「生成豆瓣阅读原创小说」.
Ready to connect★ 113
- View details
novel-simulateSkillAI & models
Analyze the reference corpus in simulate/ to build an "imitation profile" that is injected into subsequent writing, or import a previously generated profile. Triggers: "学这些范文的写法", "按这批文章的风格写", "导入仿写画像". Use when you want the Agent to draw on the structure/pacing/hook techniques of the samples.
Ready to connect★ 113
- View details
prcdxSkillAI & models
Create a GitHub Pull Request in Codex with Claude and Codex review requests and standard GitHub polling
Ready to connect★ 113
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.