claude-ecosystem-promoter
Marketing and promotion specialist for Claude ecosystem technology - MCP servers, skills, plugins, and agents. Expert in community engagement, registry…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-09 00:13
Agents & models
25,976 results
dag-hallucination-detector
Detects fabricated content, false citations, and unverifiable claims in agent outputs. Uses source verification and consistency checking. Activate on 'detect…
dag-output-validator
Validates agent outputs against expected schemas and quality criteria. Ensures outputs meet structural requirements and content standards. Activate on…
dag-parallel-executor
Executes DAG waves with controlled parallelism using the Task tool. Manages concurrent agent spawning, resource limits, and execution coordination. Activate on…
embedded-agency
Decision-theoretic framework for agents embedded within the environments they model and act upon
face-recognition-system-builder
Build face recognition systems with InsightFace, ArcFace, enrollment pipelines, HDBSCAN clustering, and privacy-compliant architecture. Activate on: face…
human-gate-designer
Designs human-in-the-loop review points for DAG workflows. Determines what to present to the human, how to collect feedback, and how to route…
mobile-biometric-auth-expert
Mobile biometric authentication expert for Face ID, Touch ID, BiometricPrompt, Keychain/Keystore, and WebAuthn. Activate on: biometric authentication, Face ID,…
nisan-et-al-2007-algorithmic-game-theory
Comprehensive treatment of algorithmic game theory covering mechanism design, auctions, and equilibrium computation
prompt-engineer
Expert prompt optimization for LLMs and AI systems. Use PROACTIVELY when building AI features, improving agent performance, or crafting system prompts. Masters…
site-reliability-engineer
Docusaurus build health validation and deployment safety for Claude Skills showcase. Pre-commit MDX validation (Liquid syntax, angle brackets, prop…
project-flow-cy
Use a file-based multi-agent collaboration workflow to initialize and manage projects, and relay between Claude Code and Codex using the flow/progress.md progress log. During initialization, first determine whether it is a single project, a single-repo multi-subproject (monorepo), or multiple independent repositories; for a single-repo multi-subproject, create only one root-level flow/ (control layer) + docs/ (centralized content layer), and each subproject only supplements its local…
storyboard-video-prompt-cy
Chinese video storyboard asset prompt workflow. Used to turn the user's text requirements, image + text, or multiple reference images + text into "character/scene/prop reference asset prompts", "15-grid director information storyboard prompts", and "video generation prompts based on the storyboard". When the user says "video prompt", "image-to-video...
autonomous-agent
Called when the user says "start", "continue", "autonomous execution", "automatic planning", "automatic repair", "autonomous", "agent execution", "intelligent workflow", or "intelligent routing". It can dynamically plan tasks, automatically select tools, and automatically repair after failures. When no matching workflow is found, it automatically searches online and generates a new workflow. It enforces validation and acceptance to ensure code quality. Silent mode is enabled by default, it does not stop to ask the user, and it automatically handles questions...
environment
Working in the pi-extensions environment — code-mode, persistence, memory, search, delegation, and context management. Read this first.
eino-practices
Provides guidance on using the CloudWeGo Eino framework for building Go AI applications, including LLM calls, prompt templates, tool definitions,…
orchestration
Coordinate supervised Orca workers: threaded messages, blocking ask/reply, task dispatch, worker_done/escalation waits, task DAGs, decision gates, coordinator…
astra-advisor
Consult GPT-6 Astra for a compact second opinion on costly-to-revert decisions, architecture forks, stuck debugging after two distinct failed attempts,…
astra-orchestrator
Coordinate substantial fact-finding from an Astra session in Codex using native Sol 6.1 and Luna 6 workers, with Astra for justified difficult branches. Use…
fable-advisor
Consult Claude Fable for a compact strategic second opinion from Codex or Claude Code. Use before costly-to-revert architecture, schema, API, migration, or…
skill-creator
Create new skills with proper structure and evals. Use when creating domain-specific skills for the .agents/skills/ directory.
parallel-execution
Execute multiple independent tasks simultaneously using parallel agent coordination to maximize throughput and minimize execution time. Use when tasks have no…
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
agents-md
Agent documentation specialist - creates and maintains AGENTS.md files, documentation structure, and best practices guides