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
8,897 results · page 148 of 297
- View details
gap-trapSkillAI & models
Use when asked to set up, install, or refine an agent quality framework in a repository (rules with gates, architecture contracts, proven-red tests, ratchets, playbooks), or when the user says "gap-trap", "gap-trap setup", "gap-trap refine", "gate the rules", or "make the agents' code match the rule
Ready to connect
- View details
java-idiomsSkillAI & models
Comprehensive sets of standards and practices designed to elevate the capabilities of AI coding agents.
Ready to connect★ 156
- View details
kotlin-idiomsSkillAI & models
Comprehensive sets of standards and practices designed to elevate the capabilities of AI coding agents.
Ready to connect★ 156
- View details
laravel-idiomsSkillAI & models
Comprehensive sets of standards and practices designed to elevate the capabilities of AI coding agents.
Ready to connect★ 156
- View details
memoriesSkillAI & models
Use when the user asks to view, list, inspect, add, create, edit, correct, update, or manage long-term memories for the current chat or workspace.
Ready to connect★ 156
- View details
native-data-fetchingSkillAI & models
Use when implementing or debugging ANY network request, API call, or data fetching. Covers fetch API, React Query, SWR, error handling, caching, offline support, and Expo Router data loaders (`useLoaderData`).
Ready to connect★ 156
- View details
perfSkillAI & models
Performance analysis and optimization: measure baseline, locate bottlenecks, optimize highest-impact items, and verify improvements. Use when applications are slow, APIs time out, or frontend Core Web Vitals have issues.
Ready to connect★ 156
- View details
php-idiomsSkillAI & models
Comprehensive sets of standards and practices designed to elevate the capabilities of AI coding agents.
Ready to connect★ 156
- View details
primeSkillAI & models
Cold-start a new session: scans the codebase structure and reads the README to quickly build project context. Ideal when starting in an unfamiliar repo or a new session.
Ready to connect★ 156
- View details
rails-idiomsSkillAI & models
Comprehensive sets of standards and practices designed to elevate the capabilities of AI coding agents.
Ready to connect★ 156
- View details
research-best-practicesSkillAI & models
Research external Claude Code best-practice sources (GitHub repos, official docs, blogs), compare them against the current workspace in a gap analysis, and produce an actionable list of recommendations.
Ready to connect★ 156
- View details
ruby-idiomsSkillAI & models
Comprehensive sets of standards and practices designed to elevate the capabilities of AI coding agents.
Ready to connect★ 156
- View details
spec-interviewSkillAI & models
Before developing a large feature, has Claude conduct an in-depth interview with you using AskUserQuestionTool (technology, UI/UX, risks, trade-offs), producing a complete spec, then opens a new session to execute it. Suitable before implementing complex features, when requirements are unclear, or w
Ready to connect★ 156
- View details
spring-boot-idiomsSkillAI & models
Comprehensive sets of standards and practices designed to elevate the capabilities of AI coding agents.
Ready to connect★ 156
- View details
swift-idiomsSkillAI & models
Comprehensive sets of standards and practices designed to elevate the capabilities of AI coding agents.
Ready to connect★ 156
- View details
use-domSkillAI & models
Lets your agent build app screens that run web code inside native apps and reuse it on the web.
Ready to connect★ 156
- View details
cassette-modelSkillAI & models
Show or change the Cassette editing model and thinking level for the current media session. Invoke only when the user explicitly asks for the model picker, wants to inspect the current Cassette model, or requests a model/thinking change.
Ready to connect★ 155
- View details
dt-dql-essentialsSkillAI & models
Core DQL syntax, pitfalls, query patterns, and query optimization. Load to write, build, fix, or OPTIMIZE a DQL query — prevents syntax errors and makes queries faster, more efficient, and cheaper (less data scanned = lower query consumption/cost per run). Covers fetch commands, data models, field n
Ready to connect★ 154
- View details
dt-obs-genaiSkillAI & models
Analyze & debug GenAI/LLM apps: token cost & caching by prompt, model & provider; latency/errors; agent & tool loops/failures; conversations; guardrails; evaluations; OpenTelemetry/dt-evals setup.
Ready to connect★ 154
- View details
openrouter-embeddingsSkillAI & models
Generate text embeddings via OpenRouter using Qwen3-Embedding-8B.
Ready to connect★ 155
- View details
adversarial-case-builderSkillAI & models
Synthesize the single strongest EVIDENCE-BOUND reviewer case to reject a paper, built ONLY from the evidence ledger (claims.json) + the other auditors' confirmed findings — never free-floating LLM critique. Two fresh cross-model codex threads: an attack writes the ~200-word rejection paragraph (ever
Ready to connect★ 154
- View details
agent-figure-gallerySkillAI & models
Query visual scientific figure references, show candidates for human preference selection, export selected reference bundles, and guide plotting agents from human-selected visual examples to code action.
Ready to connect★ 154
- View details
ai-style-impressionsSkillAI & models
Transparent, itemized impressions of AI-generated WRITING STYLE — the repo's ONLY non-integrity track. Two passes: a deterministic defensive-hedge density screen (tools/check_ai_style.py, AIS-DEFENSIVE-HEDGE) plus a fresh cross-model GROSS-cases-only semantic pass over the 13 AIS-* style tells (brok
Ready to connect★ 154
- View details
laravel:laravel-prompting-patternsSkillAI & models
Use Laravel-specific vocabulary—Eloquent patterns, Form Requests, API resources, jobs/queues—to get idiomatic framework code
Ready to connect★ 154
- View details
laravel:php-attributesSkillAI & models
Use first-party PHP attributes (Laravel 13+) for controllers, authorization, queue jobs, and models; declarative configuration colocated with code
Ready to connect★ 154
- View details
laravel:prompt-structureSkillAI & models
Structure prompts for clarity—separate concerns, prioritize requests, specify acceptance criteria, and break work into testable increments
Ready to connect★ 154
- View details
laravel:using-examples-in-promptsSkillAI & models
Provide concrete examples—existing code patterns, style samples, input/output pairs—to guide AI toward your project's conventions
Ready to connect★ 154
- View details
nexus-agentsSkillAI & models
How to add, change and verify a Nexus agent or tool, and the contract every tool must satisfy. Use when adding or modifying an agent or tool, when a documented command does not resolve, when wiring registration or capability gating, or when touching the ToolManager payload shape.
Ready to connect★ 153
- View details
nexus-eval-harnessSkillAI & models
Work on the Nexus LLM eval harness in tests/eval/ — author or fix a scenario fixture, write an eval config, change the executors, assertions or reports, or explain a run that produced nothing, everything-fails, or numbers that disagree. Use when an eval scenario is wrong, a run behaves oddly, or the
Ready to connect★ 153
- View details
nexus-llm-adaptersSkillAI & models
How to add or debug a Nexus LLM provider adapter — what every adapter must wire, how to verify it against a live provider, and the failure modes that produce a silently blank chat. Use when adding or changing a provider adapter, debugging streaming or reasoning display, working with local or CLI-bac
Ready to connect★ 153
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.
53,788 of the 54,220 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.