skillify
Skillify-as-a-verb — distill a working session (or a pointed-at chat history) into a permanent, TESTED, registered skill at the end of a workflow. The…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,657 results
browser
Automate browser interactions using the Browserbase browse CLI. Use when a task requires navigating websites, reading page state, clicking elements, filling…
generating-release-content
Generate the AI fields on releases — `title_generated`, `title_short`, `summary`, and `composition` — for one release, a window, or a backfill, via Claude Code…
yy-distill
Extract a five-dimensional capability model from user-specified content, or restructure specified content according to an existing capability model, for analyzing and guiding an AI agent's general behavior and underlying capabilities. Triggered when the user requests extracting capabilities, analyzing a capability model, extracting thinking patterns, or requests rewriting, rewriting, or restructuring content according to a capability model. Not for ordinary text summarization, writing polishing, or for converting skills into system prompts or generating project specification documents.
acp-agent-cli
Full-function ACP CLI for developers and automation, exposing the complete ACP protocol surface and an integrated agent registry for discovering, managing, and…
claude-handoff
Hand the current conversation off to a fresh background agent that picks up the work immediately.
setup-devcontainer
Set up a Compose-based devcontainer that inherits the host's git, CLI and agent identity, toolchain in the container, host stays clean, nothing to…
ac-workflow
In `.agent-context` the ac-workflow protocol for directory management task plans: planning (plan/rush), implementation (implement), patching (patch), replanning (replan), review (review), archiving (done), initialization (init). When you need to create/implement/patch/review/archive an agent-context…
cat-kit-agent-context
Documents @cat-kit/agent-context CLI, ac-workflow Skill installation output, and workspace metadata. Use when integrating agent-context, syncing installed…
codeagent
Execute codeagent-wrapper for multi-backend AI code tasks. Supports Codex, Claude, and Gemini backends with file references (@syntax) and structured output.
macos-agent-development
macOS Agent Development Specification (Swift + Accessibility API), including project structure, Accessibility API usage, UI Automation, IPC communication integration, error handling, and testing.
project-overview
Background knowledge about WeReply project architecture, features, and context. Automatically loaded for AI reference, not directly user-invocable.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's…
skill-install
Install Claude skills from GitHub repositories with automated security scanning. Triggers when users want to install skills from a GitHub URL, need to browse…
plugin-search-and-use
Use Claude Plugins to complete specific tasks, leveraging specialized capabilities such as those in Knowledge Work Plugins.
specifier
Turn a ticket or a pull-request review comment into the specification the gauntlet runs against — derive the run contract from a fresh pull, prove it green in…
to-issues
Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert…
wave-plan-pipeline
Explore-first wave pipeline. Decomposes requirement into exploration angles, runs wave exploration via spawn_agents_on_csv, synthesizes findings into execution…
maestro-brainstorm
Use when exploring ideas, evaluating approaches, or needing multi-perspective analysis before implementation
maestro-execute
Use when a confirmed plan is ready for implementation
maestro-milestone-audit
Audit current milestone for cross-phase integration gaps
maestro-quick
Quick task execution, skip optional agents
skill-iter-tune
Iterative skill tuning via execute-evaluate-improve feedback loop. Uses maestro delegate Claude to execute skill, Agy to evaluate quality, and Agent to apply…
team-executor
Lightweight session execution skill. Resumes existing team-coordinate sessions for pure execution via team-worker agents. No analysis, no role generation --…