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
9,028 results · page 288 of 301
- View details
context-doctorSkillAI & models
Diagnose and fix context window issues. Use when Claude seems confused, forgetful, slow, or the user says "context is full", "you forgot", "you're repeating yourself", "start fresh", or "why are you ignoring my instructions".
Ready to connect
- View details
critical-net-routerSkillAI & models
RAG-backed. Plan and optionally commit one bounded critical-net or differential-pair route in DipTrace with explicit rules and post-checks. Use when the user says “Route this explicitly named critical PCB net.”
Ready to connect
- View details
de-slopifySkillAI & models
Remove AI-writing tells from README, docs, and user-facing text. Must be done line-by-line, no regex. Use after agents write any user-visible prose.
Ready to connect
- View details
decision-mappingSkillAI & models
Lets your agent map out and organize decisions while working on engineering tasks.
Ready to connect
- View details
detective-specSkillAI & models
Reverse engineering of specs for legacy systems. Use when you need to extract executable specs, business rules, module contracts, flows, and retroactive ADRs from existing code that has no prior spec. Trigger words: "legado", "engenharia reversa", "extrair spec", "documentar codigo existente",
Ready to connect
- View details
Developing Internal HooksSkillAI & models
Create, configure, and develop custom automation hooks, slash commands, event hooks, and dynamic skills under internal-hooks/
Ready to connect
- View details
diagram-validatedSkillAI & models
Skill for generating technical diagrams with conclusions backed by evidence, not assertion — generates deterministic SVG from a JSON contract, validates geometry (label collision, orphan arrow, overlapping node), and performs visual readback on PNG before declaring the diagram ready. Covers 14 UML t
Ready to connect
- View details
diptrace-board-bringupSkillAI & models
RAG-backed. Plan or guide first power-on, programming, measurements, functional acceptance, and repeatable production tests for a specific DipTrace board revision. Use for assembled boards, bring-up, fixture plans, or production test procedures; «первое включение», «проверка собранной платы». Use wh
Ready to connect
- View details
diptrace-bom-sourcingSkillAI & models
RAG-backed. Build and check a purchasable DipTrace BOM for a specified assembly variant and quantity, verify live stock, and assess substitutions. Use for BOM completeness, component sourcing, JLCPCB/LCSC selection, shortages, or procurement preparation; «подбери компоненты», «проверь BOM». Use when
Ready to connect
- View details
documenterSkillAI & models
Documentation skill by decision level. Use when you need to document features, APIs, architecture, setup, operations, or keep existing documentation up to date. Triggers on: "documentar", "documentação", "docs", "ADR", "architecture decision record", "README", "feature doc", "api doc", "setup do".
Ready to connect
- View details
Executing PlansSkillAI & models
Execute detailed plans in batches with review checkpoints
Ready to connect
- View details
feature-gap-bottleneck-analysisSkillAI & models
Triggered when the agent needs to audit, discover, and resolve missing features, architectural or functional gaps, performance/process bottlenecks, and structural complexity liabilities across a codebase, delivering lean and pragmatic improvement blueprints.
Ready to connect
- View details
ferrox-fastSkillAI & models
A trivial change you could describe in one line. Runs inline, no subagents, no planning
Ready to connect
- View details
ferrox-map-codebaseSkillAI & models
You want to understand an unfamiliar codebase. Parallel agents write .planning/codebase/
Ready to connect
- View details
ferrox-reviewSkillAI & models
You want other AI models to critique a plan before you build it. Cross-AI peer review
Ready to connect
- View details
ferrox-settingsSkillAI & models
You want to change workflow toggles and which models Ferrox uses
Ready to connect
- View details
ffmpeg-mediaSkillAI & models
Skill for mechanical video/audio editing and manipulation via ffmpeg — cutting, joining, subtitles, loudness normalization, silence detection, redaction, aspect ratio correction, speed changes, metadata extraction. Runs 100% locally via Python scripts (stdlib + subprocess), no paid API and no upl
Ready to connect
- View details
finai-tools-hubSkillAI & models
China finance AI tool catalog — query/install/integrate A-share/MCP/quant frameworks. Once this skill is loaded, the agent knows each tool's inputs/outputs/installation commands, and automatically recommends and installs the appropriate tool when users have financial data needs.
Ready to connect
- View details
flywheelSkillAI & models
Overview of Forge's Agentic Coding Flywheel methodology. Use to route between plan, bead, and code space. See FLYWHEEL.md at the repo root.
Ready to connect
- View details
fresh-eyesSkillAI & models
Reset review context when bead polishing or code review has flatlined. Requires starting a brand-new Claude / Codex session. Use when you're seeing the same small edits round after round.
Ready to connect
- View details
frontend-integrationSkillAI & models
Frontend Developer skill for implementation with React/Next.js, Zustand, React Query, and Skeleton loading. Use when you need to implement components, pages, API integration, state management, or any frontend code. Triggers: "React", "Next.js", "component", "page", "Zustand
Ready to connect
- View details
game-engine-developmentSkillAI & models
Skill for real game engine code implementation — Unity C# and Unreal C++. Covers MonoBehaviour and ScriptableObject patterns, object pooling, state machines, ECS, Unreal Actor components/UPROPERTY/UFUNCTION, and performance optimization (profiling, batching, LOD, culling, garbage collection)
Ready to connect
- View details
go-concurrency-patternsSkillAI & models
Teaches your agent Go concurrency patterns like goroutines, channels, and worker pools when writing or debugging Go code.
Ready to connect
- View details
hermes-tweetSkillAI & models
Use Hermes Tweet with Hermes Agent for X/Twitter endpoint discovery, public reads, private action-gated reads, audience analysis, thread planning, and guarded publishing. Use when a project needs Hermes-native social research or publishing workflows.
Ready to connect
- View details
hundred-minds-collectiveSkillAI & models
Triggered when the agent needs to solve complex, multi-faceted problems by simulating the collective intelligence of 100 specialized minds divided into 6 functional teams (Strategy, Domain Experts, Red Team, Empirical Testers, Consensus Council, and Execution Ops) within a single agent session.
Ready to connect
- View details
Inversion ExerciseSkillAI & models
Flip core assumptions to reveal hidden constraints and alternative approaches - "what if the opposite were true?"
Ready to connect
- View details
library-quality-auditSkillAI & models
RAG-backed. Audit DipTrace component and pattern libraries for pin, pad, mapping, geometry, and identity defects without mutating native libraries. Use when the user says “Audit these DipTrace component and pattern libraries.”
Ready to connect
- View details
litreviewSkillAI & models
Guides your agent through planning and running academic paper searches, then compiles findings into a Word research guide.
Ready to connect
- View details
lofn-orchestrationSkillAI & models
Orchestrate Lofn panels, metaprompts, assignments, and multi-agent creative pipeline handoffs. Use after core seed/research exists. Do NOT use for QA cleanup, direct song generation, or final scoring.
Ready to connect
- View details
market-sizing-analysisSkillAI & models
Lets your agent calculate market sizes like TAM, SAM, and SOM for a startup idea.
Ready to connect
Popular skills lists
- Best Claude skills for what are
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for how to use
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for how to create
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
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.
55,483 of the 55,914 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.