m365-agents-ts
Microsoft 365 Agents SDK for TypeScript/Node.js. Build multichannel agents for Teams/M365/Copilot Studio with AgentApplication routing, Express hosting,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-12 00:15
Agents & models
26,151 results
analyze-prompt
Runs Chat Customizations Evaluations analysis for the active customization file and summarizes the findings from the Problems panel.
review-agent-corrections
Review locally captured corrections to agent edits and propose reusable repository guidance. Use when asked to review agent corrections, learn from feedback,…
creating-skills
Create custom agent capabilities when discovering novel tools, receiving task-agnostic tips from reviewers, or after researching specialized workflows not…
wiqd
Orchestrator for building, testing, deploying, and managing Microsoft 365 Copilot declarative agents via the wiqd CLI. Triggers: open devui, debug agent, test…
pnp-copilot-pr-review
How GitHub Copilot runs its automated pull request review of an Azure Architecture Center article. USE only as part of GitHub Copilot's agentic PR review…
debug-reproduced
User confirms the bug was reproduced. Analyze logs and iterate on hypotheses.
managing-claude-code-meta
MUST be loaded when setting up, installing, migrating, reviewing, auditing, or checking CLAUDE.md files in projects. Covers installing the promode CLAUDE.md…
managing-skills
Install, update, list, and remove Claude Code skills. Supports GitHub repositories (user/repo), GitHub subdirectory URLs…
cc-explorer
Comprehensive Claude Code documentation researcher for brainstorming and project planning. Use when the user asks about Claude Code capabilities, how to set up…
creating-subagents
Expert knowledge on creating Claude Code subagents. Use when designing or creating subagent .md files, understanding subagent structure, tool restrictions, or…
3devkit
Use when the user is unsure which of OpenSpec, gstack, or Superpowers to use next; wants a phase checkpoint in product work; asks "three stacks", "which step" or "3devkit"; or…
forge-skills
Design, create, update, and validate Codex skills in local .codex/skills folders. Use when the user wants to create a new skill, improve an existing SKILL.md,…
behavior-coach
Distills the observable working behavior of a stronger source model into a portable, spec-compliant skill any target model can load — process transfers…
inner-demon
Cultivation — recognizing the irrational impulses that arise within (fear, sloth, arrogance, chaos, malice, emptiness), coexisting with them, and transforming them into strength. Applicable to any AI agent with a decision loop.
implement
Multi-Agent Supervised Implementation Framework - TDD-driven, real-time review, quality guardian
memory-commit
Intelligently commit changes in the .claude/memory/ directory (including task tracking)
plan
Multi-Agent Parallel Planning Framework - Multi-perspective simultaneous design, consensus-driven implementation plan
status
Workflow Status Viewer - Displays execution progress, task list, DAG visualization
tasks
Multi-Agent Task Decomposition Framework - Transform plans into executable DAG task lists
verify
Multi-Agent Parallel Verification Framework - Multi-perspective test verification, acceptance criteria confirmation
ok-i-go-with-your-recommendations
Proceed with the agent's prior recommendations without re-asking.
tooluniverse-ml-inference-utility
Generic ML/NLP/vision inference against any HuggingFace-hosted model (serverless hf-inference provider) — text classification/sentiment, dense text embeddings…
github-label-agent-issues
Scan open GitHub issues and label those suitable for autonomous Agent execution with `Agent`; flag unclear candidates with `Needs-Spec`, enforce milestone…