correct-course
Side-route skill for explicit backtracking when an upstream artifact becomes untrustworthy. Use when research, PRD, or slice decomposition has been invalidated…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-25 00:14
Agents & models
24,765 results
claude-config-advisor
Review or design the Claude Code project configuration. Used when the user mentions `.claude`、`CLAUDE.md`, Claude configuration files, project-level Claude custom configuration, whether the configuration structure is reasonable, which configuration files should be created, or wants to plan a Claude from scratch…
codex-advisor
Get a second opinion from OpenAI Codex CLI for plan reviews, code reviews, architecture decisions, and hard problems. Use when you need external validation,…
deepgram-js-voice-agent
Use when writing or reviewing JavaScript/TypeScript in this repo that builds an interactive voice agent via `agent.deepgram.com/v1/agent/converse`. Covers…
work
Autonomous quality meta-skill / "quality brain" (also invocable as /ultracode and /quality-orchestrator aliases). Proactively orchestrates a rigorous,…
work-check
Check your work with a verification sub-agent that runs direct oracles first (build/test/typecheck/lint/run-the-app), re-reads the changed code, and returns a…
lorem-ipsum-generator
Generate placeholder text (lorem ipsum) in various formats. Create paragraphs, sentences, words, or custom templates for mockups and testing.
territory-mapper
Use when asked to visualize sales territories, coverage areas, service regions, or geographic boundaries on interactive maps.
plan
[Planning] Use when you need intelligent plan creation with prompt enhancement. Flag: --mode={ci|cro} (default none — standard planning); --mode=ci plans a fix…
novel-assistant
Single-directory installation package for web fiction writing. Users only need to install and invoke /novel-assistant, which automatically routes to internal capabilities such as long-form writing, short-form writing,榜单 scanning, text breakdown, de-AI-flavoring, cover design, import, manuscript review, and project deployment. Suitable for Codex, Claude Code, OpenClaw/qclaw, etc., where only one skill is expected to be installed…
agent-skill-orchestrator
This skill should be used when the user needs to solve a complex task and wants a detailed execution plan using the best available resources. Analyzes user…
project-setup
Deploys the complete SDD architecture with engram persistence and ai-context/ memory layer in the current project. Also runs an opt-in interactive wizard mode…
solo-swarm
Use when "swarm research", "parallel research", "investigate fast", "3 agents", "team research", or want faster multi-angle alternative to /research. Do NOT…
prompt-testing
Use when comparing two prompt variants, defining quality/efficiency/robustness metrics, or deciding whether to adopt a challenger prompt over a baseline.
create-plan
Turn one Locked, bounded slice into an inline implementation contract in shared execution context after grill gates.
plan-reviewer
Review one assigned PlanWeave review gate and produce a pass or needs_changes result. Use when a coordinator assigns a specific review ref, implementation…
agentstack-wrapper
Wraps existing Python agent as Agent Stack service using agentstack-sdk with minimal compatibility changes and no business-logic rewrites. Use when migrating,…
goal-prompt
Create, rewrite, shorten, or review /goal prompts for Codex, Claude Code, and other coding agents. Use only when the user explicitly requests /goal text or…
pydantic-ai
Pydantic AI Python agent framework. Covers typed tools, model providers, evals, MCP, UI adapters, and observability. Use when building Python AI agents with…
agent-orchestration
Delegates non-trivial engineering work to an `explorer` (investigation, research) and a `fixer` (implementation) in a Herdr session, while the current…
agile-iteration-method
Plan and deliver repository-aware AI-assisted software work through Agile Iteration Method using intent discovery, PO-owned Epics and User Stories, cross-Epic…
role-repo-manager
Role source management skill for finding, adding, listing, checking, updating, and removing role repositories. Use when the user is managing where roles come…
task-orchestrator
Scenario-first task lifecycle entry for controller and human sessions. Use when the user asks to create, assign, complete, archive, or inspect task flow…
worker-dispatch
Controller-side worker dispatch entry for opening workers, checking targeted worker status, and replying to workers with existing `agent-team worker` and…