grill-me
Run a grilling session: the user wants their plan, decision, or idea stress-tested one question at a time.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-30 00:12
Agents & models
25,188 results
auto-update
Automatically checks the Git repository for updates to the agents' skills, instructions, or code, and applies updates to keep the ecosystem synchronized.
user-profile
Learns, stores, and manages user preferences and interactions to personalize the agent experience and improve memory.
run-iflow
Send a request for assistance to the assistant, suitable for task scenarios such as Chinese cultural understanding, comprehension of classical Chinese texts, creation of works with Chinese characteristics, writing promotional copy for Xiaohongshu and Douyin, writing test cases, information retrieval, etc. It also serves as a powerful substitute and assistant for other expert assistants, and can be used as an alternative fallback option for most people.
handoff
Use when capturing session state before switching context, ending a session, or manually preserving progress — creates a structured handoff document in…
luke-mode
Coordinate engineering work, and set up or sync Luke's skill dependencies. Use when the user explicitly invokes Luke Mode, including its setup and sync routes.
delegation
Dispatch implementation tasks to agent teammates in git worktrees. Triggers: 'delegate', 'dispatch tasks', 'assign work', or /delegate. Spawns teammates,…
kf-g-git-hooks-fix-verify-layering
Defines a three-layer quality strategy where editor or AI agent hooks auto-fix and detect issues after edits, pre-commit blocks on verify gates, and pre-push…
waza
**WORKFLOW SKILL** - Evaluate AI agent skills using structured benchmarks with YAML specs, fixture isolation, and pluggable validators. USE FOR: run waza, waza…
declarative-agent-developer
Create, build, deploy, and localize declarative agents for M365 Copilot and Teams. Use the wiqd CLI for all declarative-agent lifecycle operations; never…
scaffold-project
Scaffold a new project of any stack from the ecosystem's own generator, with its language server wired into whichever agent is running. Use when starting a new…
improve-ut
Analyzes changed files and improves unit test coverage using project-specific testing conventions from .trellis/spec/ unit-test specs. Determines test scope…
local-ai-models
WHEN building iOS features on on-device models with Foundation Models or MLX Swift: local LLM inference, chat, Vision Language Models (VLMs), text embeddings,…
mixedbread-search-agent-harness
Design, implement, review, or tune a custom harness for Mixedbread's Toast-1 search model with your own retrieval backend or agent framework. Use for…
xsai
Use this skill when the user is building with `xsai` or any `@xsai/*` package, or is evaluating xsAI for a small OpenAI-compatible workflow with text…
agentcookie-install
Install agentcookie on a Mac source and a Linux or Mac sink so Chrome cookies sync continuously over Tailscale. Use when the user says "install agentcookie",…
creating-agent-skills
Create, name, rename, revise, or review agent skills for clear triggers, safe workflows, strong checks, lean content, and easy discovery, and score or…
init-project
Use this skill for "initialize project", "set up project", "scaffold project", "create AGENTS.md", "create CLAUDE.md", "set up rules", "create context…
claude-code-analyzer
Analyzes Claude Code usage patterns and provides comprehensive recommendations. Runs usage analysis, discovers GitHub community resources, suggests CLAUDE.md…
agents-md
Write, audit, and improve agent context files (AGENTS.md, CLAUDE.md) for AI coding agents. Use when creating or improving agent context for a codebase.
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time…
agent-tool-design
The Agent Tool Contract — 5 principles for designing tools agents call reliably: predictable signature, rich errors, token-efficient output, idempotency,…
proactive-audit
Automated health checks for framework artifacts modified during a pipeline. Validates hook syntax, security patterns (SE-01/SE-02), skill wiring, agent…
ralph-loop
Autonomous iteration loop with dual-mode support. Standalone mode uses Stop hooks (RALPH_ACTIVE=1). Multi-agent mode uses router-managed iteration. Never traps…