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
9,019 results · page 89 of 301
- View details
workbench-creationSkillAI & models
Creation-area AI assistant for writing, rewriting, screenwriting, prompt generation, and shot-list drafting. Returns documentAction proposals for user confirmation before any write.
Ready to connect★ 507
- View details
workbench-fixation-plannerSkillAI & models
Character/scene fixation planner. Identifies main characters and key scenes from a script, creates a card node for each, injects "character board/scene board" prompt text (script-driven, verbatim annotation, identity lock), and writes them to the generation canvas.
Ready to connect★ 507
- View details
pr-delivery-loopSkillAI & models
Deliver implementation PRs across Avibe, avibe-backend, avibe-docs, avault, and vault-sandbox. Required for branch and scope discipline, Codex review, CI, circuit breaking, and user-facing close-out, regardless of agent backend.
Ready to connect★ 505
- View details
agentic-actions-auditorSkillAI & models
Audit GitHub Actions that run AI agents for prompt injection, unsafe interpolation, sandbox gaps, and permissive actor rules. Use for agentic CI workflows, not general application code review.
Ready to connect★ 504
- View details
code-qualitySkillAI & models
Agents should invoke this skill for code reviews, linting/formatting setup, maintainability checks, complexity concerns, warning cleanup, coding standards, or quality gates in Rust, TypeScript, Python, shell, and mixed repos.
Ready to connect★ 504
- View details
hf-cloud-sagemaker-iam-preflightSkillAI & models
Verify or select a SageMaker execution role before creating models, endpoints, or training jobs. Use when a role ARN is missing or IAM access fails; inspect existing roles before proposing role creation.
Ready to connect★ 504
- View details
huggingface-community-evalsSkillAI & models
Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.
Ready to connect★ 504
- View details
ordering-modifier-chainsSkillAI & models
Use this skill to diagnose and fix Jetpack Compose Modifier ordering bugs — wrong paint region for background, wrong click area for clickable, wrong clipping for clip, wrong measurement for padding/size, surprising graphicsLayer scope. Covers the wrap-the-next-modifier mental model, the canonical pi
Ready to connect★ 503
- View details
paper-summarizerSkillAI & models
Agents should invoke this skill for academic or technical papers, arXiv/PubMed/IEEE/ACM links, PDFs, methodology review, limitations, practical implications, or extracting findings for engineering decisions.
Ready to connect★ 504
- View details
trl-trainingSkillAI & models
Lets your agent train and fine-tune transformer language models using methods like SFT, DPO, and reward modeling.
Ready to connect★ 504
- View details
understanding-hot-reload-limitsSkillAI & models
Use this skill to teach Claude exactly which Kotlin and Compose changes hot-reload under Compose HotSwan and which trigger a full incremental rebuild fallback. Root cause is Android Runtime (ART) class schema immutability; only method bodies are mutable at runtime, so any change to fields, signature
Ready to connect★ 503
- View details
understanding-stability-inferenceSkillAI & models
Use this skill to explain why the Compose compiler classified a class or composable parameter as stable, runtime, unknown, or unstable. Covers the 12-phase inference algorithm, the five compiler-level stability types (Certain / Runtime / Unknown / Parameter / Combined), the generic bitmask encoding
Ready to connect★ 503
- View details
decideSkillAI & models
Make a technical decision with structured reasoning and create an Agent Decision Record (AgDR).
Ready to connect★ 501
- View details
extract-featuresSkillAI & models
Six-axis Feature Inventory (routes / models / jobs / tests / UI / docs) — a "what we must preserve" spec for greenfield rewrites.
Ready to connect★ 501
- View details
feature-diagramSkillAI & models
Per-feature Mermaid flowchart — routes / models / jobs / screens. Consumes /extract-features inventory.
Ready to connect★ 501
- View details
gsd-project-researcherSkillAI & models
Researches domain ecosystem for project initialization. Spawned by /gsd:new-project orchestrator (4 parallel agents).
Ready to connect★ 490
- View details
gsd-research-synthesizerSkillAI & models
Synthesizes research outputs from parallel researcher agents into SUMMARY.md. Spawned by /gsd:new-project after 4 researcher agents complete.
Ready to connect★ 490
- View details
- View details
livekit-agentsSkillAI & models
Build voice AI agents with LiveKit Cloud and the Agents SDK. Use when the user asks to "build a voice agent", "create a LiveKit agent", "add voice AI", "implement handoffs", "structure agent workflows", or is working with LiveKit Agents SDK. Provides opinionated guidance for the recommended path: Li
Ready to connect★ 490
- View details
opencli-autofixSkillAI & models
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
Ready to connect★ 485
- View details
opencli-usageSkillAI & models
Use at the start of any OpenCLI session — this is the top-level map of what `opencli` can do, how to discover adapters, what flags and output formats are universal, and which specialized skill to load next. Point here when an agent asks "what can opencli do?" or "how do I find the right command?".
Ready to connect★ 485
- View details
dart-setup-ffi-assetsSkillAI & models
Guides agents in compiling and packaging C/C++ source code into dynamic or static libraries (Code Assets) using Dart's Native Assets hook system (via hook/build.dart and hook/link.dart utilizing package:hooks and package:native_toolchain_c). Use when a user asks to: 'setup native assets', 'compile C
Ready to connect★ 484
- View details
reticleSkillAI & models
AI agents can generate code, but they still struggle to understand what they build. Reticle gives them runtime perception of web & desktop applications.
Ready to connect★ 479
- View details
genomic-inquirySkillAI & models
Default entry for natural-language DNA questions. The host agent resolves intent, reads focused skills, calls narrow evidence tools, and adapts after inspecting tool output.
Ready to connect★ 482
- View details
agentic-quality-engineeringSkillAI & models
Use when orchestrating QE agents, understanding PACTS principles, configuring the AQE v3 fleet, or leveraging AI agents as force multipliers for quality work.
Ready to connect★ 478
- View details
aqe-researchSkillAI & models
Conduct evidence-first technical research for Agentic QE, Ruflo, related ruvnet projects, or external tools. Use when Codex must investigate a repository, compare current upstream changes, trace dependencies and history, distinguish verified facts from inference, or synthesize findings into actionab
Ready to connect★ 478
- View details
holistic-testing-pactSkillAI & models
Apply the Holistic Testing Model evolved with PACTS (Proactive, Autonomous, Collaborative, Targeted, Structured) principles. Use when designing comprehensive test strategies for Classical, AI-assisted, Agent based, or Agentic Systems building quality into the team, or implementing whole-team quality
Ready to connect★ 478
- View details
qe-agentic-jujutsuSkillAI & models
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination
Ready to connect★ 478
- View details
qe-agentic-quality-engineeringSkillAI & models
AI agents as force multipliers for quality work. Core skill for all 19 QE agents using PACTS principles.
Ready to connect★ 478
- View details
qe-learning-optimizationSkillAI & models
Optimizes QE agent performance through transfer learning, hyperparameter tuning, and pattern distillation across test domains. Use when improving agent accuracy, applying learned patterns to new projects, tuning quality thresholds, or implementing continuous improvement loops for AI-powered testing.
Ready to connect★ 478
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.
54,764 of the 55,196 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.