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
8,992 results · page 191 of 300
- View details
portSkillAI & models
Designing web-to-iOS/Android porting strategy: feature parity matrices, native architecture maps, phased Strangler-Fig roadmaps. Not for same-language migration (Shift) or native impl (Native).
Ready to connect★ 80
- View details
radarSkillAI & models
Adding edge-case tests, repairing flaky tests, and improving coverage. Use when test gaps need filling or regressions need guarding. Supports JS/TS, Python, Go, Rust, and Java.
Ready to connect★ 80
- View details
riffSkillAI & models
Brainstorming interactively to deepen ideas via four modes (Expand/Propose/Evaluate/Subtract). Does not write code. Not for decisions (Magi), feature specs (Spark), or one-shot reframing (Flux).
Ready to connect★ 80
- View details
scoutSkillAI & models
Investigating bugs via root cause analysis, reproduction steps, and impact assessment. Investigation-only — finds why bugs occur and where to fix them, no code. Use when a bug needs RCA before a fix.
Ready to connect★ 80
- View details
siegeSkillAI & models
Verifying system resilience via load testing, contract testing, chaos engineering, and mutation testing. Use for limit verification, non-functional testing, or reliability validation.
Ready to connect★ 80
- View details
sigilSkillAI & models
Designing a repository's project-local operating layer and generating its skills, recipes, workflows, and routing map. Not for global ecosystem agents (Architect) or runtime execution (Nexus).
Ready to connect★ 80
- View details
skill-qualitySkillAI & models
Validates skill structure and invocation boundaries. Use when auditing a skill, debugging its trigger, or checking portability across agent runtimes.
Ready to connect★ 80
- View details
skillopt-sleep-learnedSkillAI & models
Preferences and procedures learned from past local agent sessions.
Ready to connect★ 80
- View details
snapSkillAI & models
Automating iOS UI via XCUITest and fastlane snapshot pipelines for App Store screenshots. Not for cross-platform E2E (Voyager), iOS feature impl (Native), or unit tests (Radar).
Ready to connect★ 80
- View details
specsfy-specialist-data-modelingSkillAI & models
Model data, entities, relationships, lifecycles, quality, and persistent contracts before implementing changes.
Ready to connect★ 79
- View details
specsfy-specialist-domain-modelingSkillAI & models
Descobrir e refinar linguagem ubíqua de domínio, invariantes, eventos, aggregates e bounded contexts a partir de cenários concretos, evitando anemic domain model. Use quando termos, regras ou ownership de dados estiverem ambíguos, dois times usarem a mesma palavra com sentido diferente, ou uma decis
Ready to connect★ 79
- View details
specsfy-specialist-laravelSkillAI & models
Implementar, revisar e operar aplicações Laravel — HTTP, Eloquent, autorização, filas, eventos, cache e testes. Use quando o projeto contém `artisan` ou `laravel/framework` e a tarefa toca rotas, controllers, models, policies, jobs, commands, migrations, Pest ou PHPUnit; não use para PHP sem Laravel
Ready to connect★ 79
- View details
specsfy-specialist-technical-researchSkillAI & models
Investigates technical questions in primary sources, source code, standards, and reproducible experiments, producing a traceable synthesis with facts, inference, and gaps separated. Use when a decision depends on real API behavior, technology comparison, or a technically uncertain fact; save the pie
Ready to connect★ 79
- View details
tbdSkillAI & models
Git-native issue tracking (beads), coding guidelines, knowledge injection, and spec-driven planning for AI agents. Drop-in replacement for bd/Beads with simpler architecture.
Ready to connect★ 80
- View details
titanSkillAI & models
Delivering working code fastest via build-first product delivery through minimum agent chains; S/M scopes skip planning and build immediately. Use when compressing time-to-first-PR.
Ready to connect★ 80
- View details
tmux-status-debugSkillAI & models
Debug and test tmux pane status detection for AI agents (opencode, claude, amp). Use when patterns aren't matching, status icons are wrong, or adding new detection patterns.
Ready to connect★ 80
- View details
trailSkillAI & models
Investigating git history, analyzing regression root causes, and performing code archaeology. Time-travels through commits to uncover truth. Use for git history investigation.
Ready to connect★ 80
- View details
vitrineSkillAI & models
Authoring Storybook stories, component catalogs, and Visual Regression integration (CSF 3.0/Factories, Storybook 10 ESM-only, React Cosmos). Use when building a component catalog.
Ready to connect★ 80
- View details
voiceSkillAI & models
Collecting user feedback via NPS surveys, review analysis, sentiment analysis, feedback classification, and insight extraction reports. Use when establishing feedback loops.
Ready to connect★ 80
- View details
voidSkillAI & models
Verifying YAGNI, cutting scope, and proposing complexity reductions. A 'subtraction' agent questioning the justification for every feature, dependency, doc, and config. Does not write code.
Ready to connect★ 80
- View details
adaptive-hint-sequence-designerSkillAI & models
Generate a cascading hint sequence for a problem type, revealing progressively without giving answers. Use when designing tutoring dialogues or scaffolded worksheets.
Ready to connect★ 77
- View details
agency-circles-for-systems-actionSkillAI & models
Map control, influence, and concern after systems analysis. Use when students need wise agency without being made responsible for everything.
Ready to connect★ 77
- View details
agent-passportSkillAI & models
View this agent's digital passport (identity + trust + allowed/forbidden actions) and verify a peer's passport against a proposed action (EXO 3.0).
Ready to connect★ 79
- View details
ai-claim-checkerSkillAI & models
After any AI-generated explanation, require the learner to identify one place it could be wrong, one thing to check, and one source to consult. Builds epistemic vigilance — treats AI output as a claim to evaluate, not truth to absorb.
Ready to connect★ 77
- View details
argument-structure-scaffold-generatorSkillAI & models
Generate argument structure scaffolds using Toulmin, PEEL, or CER frameworks for a specific claim or question. Use when teaching argumentative or analytical writing across any subject.
Ready to connect★ 77
- View details
asoSkillAI & models
When the user wants to audit or optimize an App Store or Google Play listing. Also use when the user mentions 'ASO audit,' 'app store optimization,' 'optimize my app listing,' 'improve app visibility,' 'app store ranking,' 'audit my listing,' 'why aren't people downloading my app,' 'improve my app c
Ready to connect★ 77
- View details
- View details
ce-adr-authorSkillAI & models
Compatibility shim that redirects to the canonical shared skill definition in `.claude/skills/ce-adr-author/SKILL.md`.
Ready to connect★ 79
- View details
ce-adr-consultSkillAI & models
Compatibility shim that redirects to the canonical shared skill definition in `.claude/skills/ce-adr-consult/SKILL.md`.
Ready to connect★ 79
- View details
ce-adr-gap-analyzerSkillAI & models
Compatibility shim that redirects to the canonical shared skill definition in `.claude/skills/ce-adr-gap-analyzer/SKILL.md`.
Ready to connect★ 79
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.
54,624 of the 55,055 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.