Loading...
Loading...
Found 11,953 Skills
Expert delegation specialist that creates comprehensive context packages for coding agents, analyzes requirements, identifies relevant files, and generates clear instructions. Activates when delegating work, assigning tasks, creating delegation packages, or preparing agent instructions.
Validate skill directories against AgentSkills spec
Scaffold development rules for AI coding agents. Auto-invoked when user asks about setting up rules, coding conventions, or configuring their AI agent environment.
Produce an LLM Build Pack (prompt+tool contract, data/eval plan, architecture+safety, launch checklist). Use for building with LLMs, GPT/Claude apps, prompt engineering, RAG, and tool-using agents.
Test, validate, and improve agent instructions (CLAUDE.md, system prompts) using sub-agents as experiment subjects. Measures instruction compliance, context decay, and constraint strength. Use for "test prompt", "validate instructions", "prompt effectiveness", "instruction decay", or when designing robust agent behaviors.
Show status of all features in .dev/. Scans feature folders using parallel agents, generates a status report, and offers to archive completed features.
Authoritative meta-skill for creating, auditing, and improving Agent Skills. Combines skill-coach expertise with skill-creator workflows. Use for skill creation, validation, improvement, activation debugging, and progressive disclosure design. NOT for general Claude Code features, runtime debugging, or non-skill coding.
Add new field to .agents.yml config schema (updates init.md templates, version, migration)
Bidirectional agent team communication via the meet-ai chat server. Agents send and receive messages through the CLI, visible in the web UI.
Uncertainty-aware non-linear reasoning system with recursive subagent orchestration. Triggers for complex reasoning, research, multi-domain synthesis, or when explicit commands `/nlr`, `/reason`, `/think-deep` are used. Integrates think skill (reasoning), agent-core skill (acting), and MCP tools (infranodus, exa, scholar-gateway) in recursive think→act→observe loops. Uses coding sandbox for execution validation and maintains deliberate noisiness via NoisyGraph scaffold. Supports `/compact` mode for abbreviated outputs and `/semantic` mode for rich exploration.
Autonomous Freedom to Operate analysis agent. Identifies blocking patents, assesses infringement risk, and recommends mitigation strategies for product commercialization.
Use this skill whenever the agent has access to Linkup web search or fetch tools. Teaches the agent how to reason about query construction, choose search depth, write effective queries, select the right output type, use the fetch endpoint, and apply advanced techniques like sequential search and multi-query coverage. Applicable to any task involving web search, content extraction, company research, news retrieval, data enrichment, or real-time information gathering via Linkup.