git-guardrails-claude-code
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-10 00:15
Agents & models
26,031 results
computer-use
Drives the GUI of a visible local app window through `orca computer`: accessibility tree, clicks, typing, menus, dialogs, and screenshots in native apps and…
orchestration
Coordinate supervised Orca workers: threaded messages, blocking ask/reply, task dispatch, worker_done/escalation waits, task DAGs, decision gates, coordinator…
orchestrator-pi-workflows
Run deterministic multi-agent jobs through pi-extensible-workflows: route skills, build a stable DAG, fan out independent work, checkpoint decisions, and…
antigravity-skill-orchestrator
A meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combinations using agent-memory-mcp, and…
elon-musk
Agente que simula Elon Musk com profundidade psicologica e comunicacional de alta fidelidade. Ativado para: "fale como Elon", "simule Elon Musk", "o que Elon…
albert-api
Albert API — API d'inférence et d'IA générative interministérielle de l'État (OpenGateLLM, hébergement SecNumCloud). Compatible OpenAI : chat completions et…
ar-coordinator
AutoResearch Coordinator: reads the idea file, schedules planner/coder/reviewer/runner on a persistent project_root. Supports a normal linear pipeline, and also supports a Ralph loop-driven resumable workflow: each round reads state, does one unfinished unit, writes state back, and when everything is complete outputs…
capability-evolver
Self-evolution workflow for the agent. Before a substantive task, recall what worked on similar past tasks from evolution memory; after it, record the outcome…
capability-evolver
Self-evolution workflow for the agent. Before a substantive task, recall what worked on similar past tasks from evolution memory; after it, record the outcome…
run-agent
Runs an AI agent from the platform and displays results
llm-model-selection
Choosing the right model for the task — power vs. cost vs. speed.
text-to-speech
Cloud TTS via Replicate — 15 models, voice cloning, emotion control, and multi-language support
rag-architecture
Build retrieval-augmented generation systems that ground LLMs in your data.
token-waste-elimination
Audit and eliminate token waste from cognitive architecture memory files -- instructions, prompts, skills, and agents
awareness skill
Proactive detection, self-correction, and epistemic vigilance
foundry-agent-platform
Microsoft Foundry agent deployment, orchestration, and cloud-native AI service patterns
llm model selection skill
Choosing the right model for the task — power vs. cost vs. speed.
m365 declarative agent debugging skill
Debug non-functional M365 Copilot declarative agents.
multi-agent orchestration
Coordinate multiple AI agents for complex tasks — decomposition, delegation, and synthesis
persona-detection
Intelligent project persona identification using priority chain detection with LLM and heuristic fallback
prompt-activation
Internal metacognitive skill for episodic memory retrieval cues — surfaces relevant workflows when needed
prompt engineering skill
Craft effective prompts that get the best results from language models.
rag architecture skill
Build retrieval-augmented generation systems that ground LLMs in your data.