dependency-coordinator
Orchestrator-dispatched only. Authors the cross-package dependency manifest before parallel implementation agents are dispatched, preventing transitive version…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-11 00:16
Agents & models
26,078 results
loop-controller
Wrap any task in a verifiable stop condition plus a mandatory guardrail stack so an autonomous loop converges instead of thrashing or burning the budget — the…
model-adaptation
Adapt prompts, skills, and agent scaffolding when the underlying Claude model changes — currently the Claude 5 family (Fable 5/Mythos 5) vs Opus 4.x. Stronger…
orchestrator
Coordinate multi-agent Claude Code builds end-to-end: read the plan/mission, design integration contracts, dispatch role-agents in parallel, gate on QA, ship.…
orchestrator-task-loop
The outer orchestration loop over the Agent Teams shared task list: the lead loops the board until EVERY task is completed AND each passes its TaskCompleted…
plan-builder
Transform research documents, Compass artifacts, PRDs, and conversational goals into structured project plans the orchestrator can execute. Use when the user…
skill-explorer
Help the user discover, recall, understand, and pick the right skill from the available toolkit. Names the skill; does NOT invoke it. Use when the user is…
skill-review
Review skills for quality, consistency, triggering accuracy, and adherence to the 5000-word / 500-line body guideline. Two modes: 'all' (bulk ecosystem-wide…
grill-to-kiro
Entry skill to use before proceeding to Kiro / SDD new spec creation, kiro-discovery, kiro-spec-init, requirements definition, specification, or feature brief creation. Rather than passing the user's request directly to kiro-* skills, first use grill-with-docs to clarify terminology, boundaries, …
002-agents
Use when you need to install the embedded robot agents into either .cursor/agents or .claude/agents, selecting the destination interactively and copying the…
claude-code_mrgoonie
Guidance on Claude Code, Anthropic's terminal-based agentic coding tool. Use when asked about Claude Code features, installation and authentication, slash…
skills-consolidator
Merge and organize large Claude Code skill collections with conflict resolution. Use when combining skills from multiple sources, flattening directory…
skills-duplicate-detector
Find duplicate, near-duplicate, and functionally overlapping Claude Code skills in a collection. Use when auditing a skills library for redundancy, after…
the-ai-counsel-api
The AI Counsel — MCP-first (10 action-based tools) when The AI Counsel MCP server is connected; REST/curl fallback when MCP is unavailable, for cron scripts,…
harness-engineering
Bootstrap or migrate a repository into an agent-first harness-engineering knowledge store modeled on OpenAI's Harness engineering article. Use when Codex needs…
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…
openclaw-skills
Create, structure, and refine Agent Skills (OpenClaw format) — the open standard for extending AI agents with specialized knowledge. Use when asked to create a…
stack-up
A pragmatic staff-engineer advisor for choosing the tech stack to build a piece of software. Use when the user wants to pick a stack, decide between…
hypothetical-walkthrough
Use when the user asks for a hypothetical walkthrough of a system to expose tensions, frictions, gaps, or contradictions between its expected and evidenced…
kev-modal-study
Launch, monitor and pull Kev training studies, untrained-base probes, remote benchmarks and new-base smoke checks on Modal (modal_app.py). Use when running…
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…
implement-phase
Prepare to implement the next pending todo phase from a solutionize sketch plan (frontmatter todos); implementation only after explicit user approval.
implement-next
Find the next pickable ticket under a spec issue and implement it. Resolves the frontier from GitHub sub-issues and native dependencies, claims the ticket,…
creating-sdk-apps
This skill should be used when the user asks to "create an agent SDK app", "build a Claude Agent SDK project", "set up a new SDK application", "scaffold an…