Agents
Agents d’IA i automatització
ap2
Tyler-R-Kendrick
Use when implementing the Agent Payments Protocol (AP2) for secure, compliant AI-driven commerce. Covers intent mandates, cart mandates, payment flows, and merchant integration. USE FOR: agent-driven purchases, secure commerce mandates, user-authorized shopping flows, payment credential verification DO NOT USE FOR: API micropayments (use x402), agent communication (use a2a), tool integration (use mcp)
terraform
Tyler-R-Kendrick
Use when writing Terraform configurations for multi-cloud infrastructure. Covers HCL resources, modules, state management, providers, and plan/apply workflow. USE FOR: multi-cloud provisioning, HCL configuration, Terraform state management, provider modules, plan/apply workflow DO NOT USE FOR: imperative infrastructure code (use pulumi), Azure-only deployments (use bicep), AWS-only stacks (use cloud-formation)
daggr
gradio-app
Build DAG-based AI pipelines connecting Gradio Spaces, HuggingFace models, and Python functions into visual workflows. Use when asked to create a workflow, build a pipeline, connect AI models, chain Gradio Spaces, create a daggr app, build multi-step AI applications, or orchestrate ML models. Triggers on: "build a workflow", "create a pipeline", "connect models", "daggr", "chain Spaces", "AI pipeline".
reviewing-prs
Ataraxy-Labs
"Agent-powered GitHub PR reviews with smart semantic triage. Categorizes changes as MECHANICAL (skip), NEW LOGIC (read), or BEHAVIORAL (verify) — so agents never waste tokens reading lock files or formatting diffs. Includes remote file reading, text/AST search across PR or full repo, and comment posting. No local clone needed. Use when asked to review a PR, check a pull request, look at PR changes, or given a PR number/URL to review."
create-hook
richfrem
Interactive initialization script that generates a compliant lifecycle Hook for an AI Agent or Plugin. Use when you need to automate workflows based on events like PreToolUse or SessionStart.
verification-before-completion
mrtolkien
Use when about to claim work is complete, fixed, or passing, before committing or
audio-editing
guia-matthieu
"Master the essential audio post-production techniques—normalization, compression, EQ, and noise reduction—using the correct processing order to achieve professional-quality audio. Use when: Editing podcast episodes or video soundtracks; Cleaning up recorded voiceovers; Improving audio quality for marketing content; Preparing audio files for distribution; Troubleshooting common audio issues"
SKILL.md
SENTRY-Security
請以此為最高指導原則。
task-management
joelhooks
"Manage Joel's task system in Todoist. Triggers on: 'add a task', 'create a todo', 'what's on my list', 'today's tasks', 'what do I need to do', 'remind me to', 'inbox', 'complete', 'mark done', 'weekly review', 'groom tasks', 'what's next', or when actionable items emerge from other work. Also triggers when Joel mentions something he needs to do in passing — capture it."
gateway-setup
joelhooks
"Set up a persistent AI agent gateway on macOS with Redis event bridge, heartbeat monitoring, and multi-session routing. Interactive Q&A to match your intent — from minimal (Redis + extension) to full (embedded daemon + Telegram + watchdog). Use when: 'set up a gateway', 'I want my agent always on', 'event bridge', 'heartbeat monitoring', 'agent notifications', or any request to make an AI agent persistent and reachable."
beads
metalagman
Use this skill to manage work in Beads (bd), a git-backed issue tracker for AI agents, including issue lifecycle, dependencies, sync, and agent hooks.
skill-writer
metalagman
Use this skill to design, document, and structure AI agent skills for Gemini, Claude, and Codex. It provides architectural rules, directory standards, and writing best practices.
go-adk
metalagman
Use this skill to build, run, deploy, evaluate, and troubleshoot Go agents with Google's Agent Development Kit (google.golang.org/adk), including llmagent config, tools/integrations, callbacks/plugins, sessions/state/memory, workflows, streaming, MCP/A2A, and runtime/deployment patterns.
dashboard
zylos-ai
Read-only Zylos observability dashboard for agent state, costs, tools, communication, scheduler, and PM2 service health. Full features on Claude runtime. PM2, system health, communication, and scheduler monitoring on all runtimes.
delaware-franchise-tax
open-agreements
File your Delaware annual franchise tax and annual report. Guides you through tax calculation (Authorized Shares and Assumed Par Value Capital methods), the eCorp portal filing process, and payment. For Delaware C-Corps (March 1 deadline) and LLCs/LPs/GPs (June 1 deadline).
m365-agent-developer
sebastienlevert
Designs, implements, and deploys Microsoft 365 Copilot agents using TypeSpec and ATK CLI. Provides architectural guidance, capability configuration, security patterns, and lifecycle management. Use when developing M365 Copilot agents, working with TypeSpec, or managing agent deployments. For creating new projects, use the m365-agent-scaffolder skill.
m365-agent-scaffolder
sebastienlevert
Quickly scaffolds new Microsoft 365 Copilot declarative agent (M365 agent, copilot agent, agent, declarative copilot, copilot) projects using ATK CLI. Collects project information and creates the initial project structure. Use only when creating a new empty M365 Copilot agent project from scratch.
custom-agent-definitions
laurigates
Write and configure custom agent definitions in Claude Code's agents/ directory. Use when you want to create a new agent .md file, define a specialized agent with its own system prompt and tools, set up an agent with isolated context, or configure agent capabilities and restrictions in your project's .claude/ configuration.
agents-analyze
laurigates
Analyze all plugins for sub-agent opportunities. Identifies skills with verbose output, gaps in agent coverage, and model selection improvements.
meta-audit
laurigates
Audit Claude subagent configurations for completeness, security, and best practices
mcp-code-execution
laurigates
Design and scaffold the code execution pattern for MCP-based agent systems. Use when building agents that interact with many MCP tools, when intermediate data is too large for model context, when you need loops/conditionals across tool calls, or when PII must stay out of the model context. Based on Anthropic's engineering guidance.
blueprint-development
laurigates
"Generate project-specific rules and commands from PRDs for Blueprint Development methodology. Use when generating behavioral rules for architecture patterns, testing strategies, implementation guides, or quality standards from requirements documents."
team
leodearden
"Run a piece of work as an agent team — decompose it into seats, route every seat to the model tier (haiku / sonnet / opus / fable) and reasoning effort (low → max) its brief actually rewards, dispatch through the Workflow tool (or the Agent tool for small, adaptive teams), then integrate and verify the results as the lead. ALWAYS use this for: /team commands (/team --fable pre-authorises fable seats for the run), 'use an agent team', 'fan this out to agents', 'parallelise this with subagents', 'run this as a team and use cheap models where you can', 'put haiku/sonnet on the grunt work', or any request to do work with several agents at task-appropriate model and effort levels. NOT for: single-chain work you can do inline, the purpose-built multi-agent surveys (/hotspot-survey), handing a decision to a fresh context (/do), or the dark-factory orchestrator (/orchestrate)."
continuous-learning-v2
JochenYang
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.