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
9,032 results · page 233 of 302
- View details
scaffold-github-cloud-agent-environmentSkillAI & models
Audit and scaffold `.github/workflows/copilot-setup-steps.yml` for GitHub Copilot cloud agent environments. Use for missing or broken setup workflows, runner/firewall/dependency/LFS/proxy issues, or Copilot setup repair. Do NOT use for generic GitHub Actions.
Ready to connect
- View details
scaffold-hooksSkillAI & models
Run /scaffold-hooks to audit, create, or refresh shared repository hooks for Claude Code, Codex, GitHub Copilot, Devin CLI, and OpenCode, together or individually. Skip Git hooks and Husky.
Ready to connect
- View details
agent-reviewSkillAI & models
Conducts independent, read-only code reviews of branches, diffs, commits, working trees, or pull requests using external CLI agents (Codex, Claude, agy) or a synthesized review workflow. Focuses strictly on actionable defects and evidence-based findings. Use when reviewing code changes, requesting a
Ready to connect
- View details
appstore-ppp-pricingSkillAI & models
Bulk-sets App Store in-app purchase and subscription prices across 175+ countries by purchasing power parity, using the appstore-ppp-prices CLI. Use whenever the user wants to localize, bulk-update, lower, raise or review regional App Store pricing — "set regional prices", "PPP pricing", "make my ap
Ready to connect
- View details
better-promptSkillAI & models
Use when the user explicitly asks to "optimize a prompt", "improve a prompt", "polish an instruction", "convert a rough prompt into a best-practices version", or asks to "rewrite a prompt as pseudocode" or "translate it into a program structure / programmable natural language". Supports two output m
Ready to connect
- View details
criticSkillAI & models
A collection of Claude Skill to mirror https://mgifford.github.io/ACCESSIBILITY.md
Ready to connect
- View details
domain-mlSkillAI & models
Use when building ML/AI apps in Rust. Keywords: machine learning, ML, AI, tensor, model, inference, neural network, deep learning, training, prediction, ndarray, tch-rs, burn, candle, 机器学习, 人工智能, 模型推理
Ready to connect
- View details
everrunsSkillAI & models
Route Rust applications to the Everruns Framework, or compose advanced execution hosts from everruns-host and focused crates. Use for in-process agents, custom host backends, providers, MCP, or capability authoring.
Ready to connect
- View details
hello-worldSkillAI & models
A simple example skill that demonstrates the Agent Skills format. Use this as a template for creating new skills.
Ready to connect
- View details
markifact-overviewSkillAI & models
Reference — what Markifact is, what the MCP server exposes, and the discover→inspect→run pattern. Always loaded into the performance-marketer agent.
Ready to connect
- View details
plannerSkillAI & models
A collection of Claude Skill to mirror https://mgifford.github.io/ACCESSIBILITY.md
Ready to connect
- View details
port-python-paritySkillAI & models
Port features from the official Python claude-agent-sdk to this Ruby gem for parity. Use when syncing with a new Python SDK release, running a gap analysis, or batching parity fixes.
Ready to connect
- View details
safe-write-operationsSkillAI & models
Reference — rules for safely executing write/destructive operations against ad accounts. Always loaded into the performance-marketer agent.
Ready to connect
- View details
solSkillAI & models
Use Sol to review work or rewrite prompts. Use when the user invokes /sol or wants the Sol utility.
Ready to connect
- View details
workspace-toolsSkillAI & models
Configures workspaces for agent-assisted development. Manages agent skills (untracked symlinks), workspace tool permissions (allow/deny/ask rules for Claude Code and Antigravity), git hook profiles, and .envrc configurations. Use when configuring a workspace, discovering or installing skills, settin
Ready to connect
- View details
agent-developmentSkillAI & models
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or
Ready to connect
- View details
agent-governanceSkillAI & models
Use when designing or reviewing an AI agent system that needs policy-based access controls, intent classification, tool-level rate limiting, trust scoring for multi-agent workflows, or append-only audit trails.
Ready to connect
- View details
bsl-queryingSkillAI & models
Construct and debug Boring Semantic Layer queries through Data Bridge. Use for semantic model discovery, dimensions, measures, filters, grouping, ordering, dates, limits, and BSL query errors.
Ready to connect
- View details
build-mcp-serverSkillAI & models
This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", or discusses building something with the Model Context Protocol. It is the entry point for MCP server development
Ready to connect
- View details
cordis-plugin-sofagentSkillAI & models
Mount the full sofagent capability suite in one go — 6 capabilities delivered at once (injection · audit & acceptance · experience · retrospection · inspection · FDE three domains) (seam: non-seam:plugin-suite) — orchestration only, no reimplementation — the sofagent constraint layer in plugin form
Ready to connect
- View details
cordis-plugin-sofagent-auditSkillAI & models
Machine review of changes + hard acceptance gate — 24 rules + git diff hard evidence + turn-stopping acceptance verdict (blocks release if acceptance fails; independently toggleable switch) (seams: tools/result + tools/pre-execute + fs/write-intent + agent/turn-stopping) — bridges @sofagent/audit ru
Ready to connect
- View details
cordis-plugin-sofagent-evolveSkillAI & models
Experience accumulation — think.md reflection + Dream Cycle + evolve + instinct→skill + refine (seam: session/event) — bridging @sofagent/think generateThinkEntry — a DSH (DeepSeek Harness) cordis plugin. The plugin form of the sofagent constraint layer within the DeepSeek Harness ecosystem.
Ready to connect
- View details
cordis-plugin-sofagent-fdeSkillAI & models
FDE onboarding and capability flow — organize enterprise business into AI capabilities, and have those capabilities published, discovered, invoked, evaluated, and retired within the enterprise (seam: non-seam:tool-set) — bridging @sofagent/orchestrator publishCapability / @sofagent/ontology generate
Ready to connect
- View details
cordis-plugin-sofagent-injectSkillAI & models
Startup constraint injection — four-layer loading chain (seam: agent/pre-step) — bridges @sofagent/inject buildConstrainedSystemPrompt — a DSH (DeepSeek Harness) cordis plugin. The sofagent constraint layer in plugin form for the DeepSeek Harness ecosystem.
Ready to connect
- View details
cordis-plugin-sofagent-rollbackSkillAI & models
Reverse-order rollback on error — git snapshot → effect disposer (seam: agent/error) — bridges @sofagent/core getHistoryFilePath — a DSH (DeepSeek Harness) cordis plugin. The plugin form of the sofagent constraint layer in the DeepSeek Harness ecosystem.
Ready to connect
- View details
cost-auditSkillAI & models
Use when AI inference costs are growing unexpectedly, when comparing model choices by cost/quality ratio, or when optimizing token usage across a multi-model pipeline — produces an actionable cost reduction plan
Ready to connect
- View details
deep-brainstormingSkillAI & models
Use when brainstorming a product or feature where multiple valid technology choices exist and the wrong one is costly, when the user asks for 'objectively best' or 'highest quality', or when the domain has tools/frameworks where marketing or popularity biases could mislead research agents. Also use
Ready to connect
- View details
enterprise-fde-identify-AI-nodesSkillAI & models
Use this Skill when an FDE needs to make an AI classification decision about a workflow node — not "what it does", but "when to use it". A wrong description = the Skill will never be triggered.
Ready to connect
- View details
example-commandSkillAI & models
An example user-invoked skill that demonstrates frontmatter options and the skills/<name>/SKILL.md layout
Ready to connect
- View details
freeshard-change-controlSkillAI & models
How changes get accepted into the Freeshard shard_core repo: issue triage on the Dev Board, agent pickup/handback signals, branch & PR conventions, the non-negotiables (Max-merge-only, stay on Traefik v2, no shell on shards, DO-NOT-MODIFY synced types), and release discipline (merged is NOT shipped)
Ready to connect
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.
54,855 of the 55,286 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.