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
8,868 results · page 221 of 296
- View details
goalproSkillAI & models
Use when the user wants to write a high-quality Goal Prompt, or a Loop Prompt for continued evolution after delivery—turning vague, strategic, multi-step, evidence-lacking, ongoing/automated, or error-prone requests into an executable, verifiable, pausable goal contract with time parameters. Suitabl
Ready to connect★ 56
- View details
im-humanSkillAI & models
A voice-control and de-AI-flavor editing skill for Taiwan Traditional Chinese and English, with two modes. Voice mode: activates when the user says 「我是人」「開啟我是人」「說人話模式」 or asks Claude to 「用我是人講話」; afterwards every line of Claude's own output is rewritten in everyday Taiwanese Traditional Chinese (or
Ready to connect★ 56
- View details
implement-and-checkSkillAI & models
Runs the hard gate that has to pass before any optimization budget is spent. Use right after intake. Walks the agent through implementing the 3 required adapter methods plus any defaulted hooks that need overriding (and any selected skill's abstract methods), then runs `cap-evolve check` on the proj
Ready to connect★ 56
- View details
qualification-scorerSkillAI & models
Use when scoring leads, qualifying prospects, prioritizing pipeline, deciding which accounts to pursue, or building a lead scoring model. Triggers: 'score this lead', 'qualify this prospect', 'is this a good lead', 'lead scoring', 'prioritize my pipeline', 'qualification framework'.
Ready to connect★ 56
- View details
reSkillAI & models
Explicit extra-research mode. Use only when the user says `/re` or clearly asks for a research-heavy pass before coding. This skill should bias Codex toward more source-checking and justification without replacing its normal orchestration.
Ready to connect★ 56
- View details
reapSkillAI & models
Report how much of the context this agent loads is never used - unused skills, MCP servers, subagents, hooks and always-loaded prose - measured from real session transcripts. Use when asked why the context window is full, what is wasting tokens, or what is safe to remove.
Ready to connect★ 56
- View details
rpa-helperSkillAI & models
Performs desktop automation workflows via YingDao RPA MCP, such as opening apps, filling forms, and batch operations. Before use, confirm that YingDao RPA is installed and environment variables such as RPA_MODEL and SHADOWBOT_PATH are configured.
Ready to connect★ 56
- View details
skill-packageSkillAI & models
Optimize an Agent Skill package itself — its SKILL.md (frontmatter + body), its references, and its bundled scripts. Use when the capability under optimization IS a skill, you want the downstream agent to trigger it correctly and follow it without wasted steps, or you want a step the agent keeps ski
Ready to connect★ 56
- View details
toolsSkillAI & models
Optimize an agent's OWN tool surface (tools it implements, not an external MCP server). Use when the agent mis-selects tools, fills arguments wrong, calls the same tool N times in a row, or has a confusing, redundant, or oversized toolset. Covers tool names and descriptions, parameter docs, tool sch
Ready to connect★ 56
- View details
agency-healthSkillAI & models
Fleet health check across three dimensions — workstream, agent, worktree. Reports severity (healthy/attention/warning/critical) and sets exit codes for CI integration. Run this when you want to know "is the fleet OK right now?" — at session start, before a release, or after any disruption.
Ready to connect★ 55
- View details
ai-read-docsSkillAI & models
Use when the work depends on versioned or external behaviour — adding a package, writing setup or config, integrating an SDK or a paid API, debugging a framework change — or on anything involving third-party APIs, libraries, frameworks, CLIs, cloud services, model/provider SDKs, fast-moving product
Ready to connect★ 55
- View details
ai-writing-behaviorSkillAI & models
Authors and revises Agent Behavior BEHAVIOR.md specs that capture recurring, judgeable agent conduct. Use when creating, reviewing, splitting, grouping, or calibrating behavior specs, or when translating trace failures and runtime guidance into durable behaviors. Trigger for "write a behavior spec",
Ready to connect★ 55
- View details
goal-writerSkillAI & models
Writes the /goal condition that loops one feature. Sets the feature up first by running new-feature if it doesn't have a spec yet, then produces the goal command to paste into Claude Code or Codex. Use when the user says "write the goal for this", "loop this feature", "make this a goal", or describe
Ready to connect★ 55
- View details
pr-captain-landSkillAI & models
Captain-only. Land an agent's prepared branch LOCAL-FIRST — integrate and validate in a scratch worktree cut from origin/<default>, then bump agency_version, sign a landing receipt, open the PR, confirm CI, merge, release, notify. The single-writer serialization point for agency_version and PR creat
Ready to connect★ 55
- View details
pr-submitSkillAI & models
Agent-side signal to captain that your branch is ready for PR landing. Runs preconditions (clean tree, pushed, matching QGR receipt) then dispatches captain with a structured payload. Captain's /pr-captain-land picks it up. Replaces the distributed "agent creates PR" model with a captain-owned PR li
Ready to connect★ 55
- View details
principal-createSkillAI & models
Onboard a new principal to the current repo — scaffold sandbox, register agent, write CLAUDE-PRINCIPAL.md, mutate agency.yaml, bootstrap captain handoff. The discoverable end-to-end command for adding a person to an agency repo.
Ready to connect★ 55
- View details
sandbox-activateSkillAI & models
Activate a sandbox item by symlinking it to the Claude Code discovery location
Ready to connect★ 55
- View details
self-improvementSkillAI & models
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude rea
Ready to connect★ 55
- View details
workstream-createSkillAI & models
Create a new workstream with scaffolded artifacts, agent registrations, and optional worktree
Ready to connect★ 55
- View details
agent-autonomy-kit-zhSkillAI & models
Stop waiting for prompts and keep working autonomously
Ready to connect★ 54
- View details
agent-surface-forgeSkillAI & models
Use when the user asks to audit or repair agent surfaces — plugin configs, agent definitions, skills, CLAUDE.md/AGENTS.md, docs, prompts, commands, or hooks. Produces a certainty-graded breadth report and applies only HIGH auto-fixable findings with --apply. Not for deep one-skill improvement — use
Ready to connect★ 54
- View details
agile-v-behavioralSkillAI & models
Anti-pattern prevention guidelines for Agile V agents. Prevents common LLM coding mistakes while maintaining Agile V traceability. Use when implementing requirements to avoid overcomplication, silent assumptions, scope creep, and verification failures.
Ready to connect★ 54
- View details
agile-v-coreSkillAI & models
Foundational values, directives, and context engineering rules for all Agile V agents. Load first in every Agile V session.
Ready to connect★ 54
- View details
agile-v-pipelineSkillAI & models
Orchestration pipeline, wave execution, handoff protocols, and checkpoint types for the Agile V 5-stage workflow. Load when orchestrating multi-agent pipelines or managing stage transitions.
Ready to connect★ 54
- View details
agile-v-quality-gatesSkillAI & models
Quality validation gates for Agile V agents. Adds interface validation, test quality checks, data type awareness, and time allocation guidance to prevent common failure patterns identified in comprehensive testing.
Ready to connect★ 54
- View details
audit-projectSkillAI & models
Use when the user says "audit my code", "find all the bugs", "review until clean", or "grill my changes". Runs an iterative multi-agent review that resolves every finding at or above a configurable severity floor to zero, or stops at a gate or cap. Not for remote, credential, or irreversible changes
Ready to connect★ 54
- View details
build-agent-dartSkillAI & models
Dart/Flutter build agent for mobile apps, Flutter widgets, and Dart packages. Extends build-agent with Dart-specific conventions. Use when building Flutter apps, Dart packages, or mobile (iOS/Android) features.
Ready to connect★ 54
- View details
build-agent-embeddedSkillAI & models
C/C++ build agent for embedded systems, firmware, and MCU projects. Extends build-agent with embedded constraints. Use when building firmware, bare-metal code, or resource-constrained systems.
Ready to connect★ 54
- View details
build-agent-jsSkillAI & models
JavaScript/TypeScript/Web build agent for web apps, Node backends, and frontend components. Extends build-agent with JS/Web conventions. Use when building web apps, APIs, or frontend/backend features.
Ready to connect★ 54
- View details
build-agent-pythonSkillAI & models
Python build agent for scripts, backends, data pipelines, and ML projects. Extends build-agent with Python conventions. Use when building Python applications, APIs, data processing, or automation.
Ready to connect★ 54
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.
53,585 of the 54,017 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.