657 tagged copilot, measured the same way as everything else here.
Browse within: github-copilot 70coding-assistant 64dotnet 45ai-toolkit 43copilot-cli 25code-quality 23instructions 22ai-skills 20agentic-coding 19copilot-enabled 19vscode-extension 19agentic-rag 18architecture 18dotnet-skills 18
Agent
Contrarian Agent / Devil's Advocate — systematically challenges decisions, consensus, and assumptions. Call when other agents agree too easily, to avoid groupthink and consensus errors.
Agent
Senior Customer Success Manager — client onboarding, retention, NPS, account management, expansion revenue. Call for anything related to post-sale relationships, customer satisfaction, and churn reduction.
Agent
A read-only research-idea critic that acts like a skeptical peer reviewer, challenging a study concept's originality and practical research design.
Agent
A read-only medical research reviewer that checks whether a paper's scientific claims, terminology, reasoning and literature coverage fit current clinical or basic-science knowledge.
Agent
A read-only analysis agent that studies past writing or review results and reports structured suggestions for improving the system. It does not edit files itself.
Agent
Generates monthly customer newsletters via a skills-based pipeline. Orchestrates 6 phases from URL discovery through final assembly and validation.
Agent
Analyzes published newsletters and benchmark intermediates to extract editorial patterns, selection decisions, and thematic intelligence. Use for editorial intelligence mining.
Agent
Builds individual newsletter pipeline skills from agent logic, prompt files, and benchmark examples. Use with /fleet for parallel skill construction.
Agent Claude Code
Full-repository technical audit agent. Use when the user asks for a codebase audit, health check, tech-debt review, or a prioritized improvement plan. Produces a Repo Map, severity-rated Audit Report, Improvement Strategy, and milestone-based Task Plan. Read-only — never modifies code.
Agent Claude Code
Security review of changes and subsystems. Use for anything touching the HTTP bridge, hook installers, credential/token handling, webhook senders, guardrails, or the updater.
Agent Claude Code
Senior product-designer + frontend-engineer UI/UX audit agent. Use when the user wants a deep UX review, design critique, screen-by-screen sweep, motion/animation spec, accessibility check, or a prioritized "what to fix" list for the renderer. Produces docs/UXAUDIT.md. Read-only — never modifies code.
Agent
AI coding agents that OAK captures, enriches, and extends.
Agent
Skills that OAK deploys into your AI coding agents.
adhocteam/cloud-gov-instructions
Agent
Generates FedRAMP compliance documentation by scanning codebase for NIST SP 800-53 control references. Creates draft System Security Plans (SSP) and Control Implementation Matrices.
Agent Claude Code
Use this agent when designing new APIs, creating API specifications, or refactoring existing API architecture for scalability and developer experience. Invoke when you need REST/GraphQL endpoint design, OpenAPI documentation, authentication patterns, or API versioning strategies.
Agent Claude Code
Reviews code for quality, best practices, and potential bugs.
Agent Claude Code
Investigates and fixes bugs by analyzing code, logs, and stack traces.
Agent Claude Code
Wires two completed Taniwha modules together against a parent contract. Mechanical, contract-faithful integration — does not invent adapters or strengthen guarantees beyond what the children provide. Reads child implementation manifests (not source code) to know where children's outputs live; reads project context for…
Agent Claude Code
Implements a single Taniwha module against its contract manifest. Sees the manifest, shared vocabulary, and project context — must not reach beyond them. Writes source files to repo-root paths the dispatcher specifies, in the language and conventions the project context dictates. Invoked by the Taniwha dispatcher.…
Agent Claude Code
Verifies that a Taniwha implementation or composition satisfies its contract's acceptance criteria. Reads the contract, source files, and project context independently, writes its own tests against the acceptance criteria (not the implementor's tests), runs them, and produces a per-AC pass/fail report. Invoked by the…
Agent
Use shorthand-first compression for agent workflows while keeping technical precision and exact literals.
Agent
Generate a custom checklist for the current feature based on user requirements.
Agent
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
Agent
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: