Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
Agent Claude Code
Use this agent when the user asks to write, create, or draft an SEO-optimized article, blog post, or page. This includes requests involving keyword optimization, internal linking (maillage interne), content strategy, or any web content that needs to rank well on search engines. Examples: Context: The user wants to…
kirich1409/claude-global-settings
Agent Claude Code
An operator for GitHub Issues and Projects, where teams track work and organize it on a board. It creates and structures tasks, assigns people, links related work, breaks down large items, moves cards, finds blockers or stale work, and triages the backlog in read-only or editing mode.
adrielp/ai-engineering-harness
Agent Claude Code
Analyzes codebase implementation details and explains how code works. Use this agent when you need to understand specific components, trace data flow, identify architectural patterns, or explain technical implementations. Provide detailed context about what you want analyzed for best results.
Agent Claude Code
QA verification subagent for requirements, PRD, ADR and Implementation Plan readiness, tests, logs, reproduction, browser or simulator checks, and evidence of completed work.
Agent Claude Code
defi-engineer.md, solana-architect.md, and solana-qa-engineer.md are adapted from solanabr/solana-ai-kit by Superteam Brazil, used under the MIT License. They give this starter a trading brain (Jupiter/Pyth/oracle-guard patterns), a settlement-program architecture voice (escrow/PDA design), and a Solana test…
Agent Claude Code
Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by {{COMMANDPREFIX}}new-project or {{COMMANDPREFIX}}new-milestone orchestrators.
Agent Claude Code
The copy chief — default agent for the copywriter profile, launched as --agent copy-chief. Runs the copy line end to end: sets up products and projects, dispatches research, commissions the judged root files, dispatches the strategy stage and the review rounds, resolves findings, and makes the final "will this sell"…
Agent Claude Code
Agent "gaia-orchestrator" from gaia-research/gaia-skill-tree, covering role, the no-code rule, exception, session stewardship and fan-out heuristic.
Agent Claude CodeCursor
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use when the user asks for a review or after writing or modifying code.
Agent Claude Code
A chat-history search agent for Claude Code and Codex, which are coding assistants. It finds earlier conversations about topics, decisions, searches, or completed work.
Agent Claude Code
Use this agent to create audio and video assets using Google NotebookLM. Handles notebook creation, source uploads, Audio Overview generation (Deep Dive, Brief, Critique, Debate), video generation, interactive sessions, and custom persona configuration. Use when you need to transform documents into podcasts, explainer…
Agent Claude Code
Implements one planned workflow component by following existing codebase patterns. Spawned by /5:implement.
Agent Claude Code
Document original media materials with journalistic rigor to provide comprehensive source material for future writing.
Agent Claude Code
External reference researcher — looks up library docs, framework conventions, OSS examples. Read-only, no memory injection. (Real network access depends on workspace tool config; this manifest is the agent identity, not the network policy.).
Agent Claude Code
Creates executable PLAN.md files from phase goals. Absorbs research and self-checking. Spawned by /ariadna:plan-phase orchestrator.
thomast1906/github-copilot-skills-terraform
Agent Claude Code
Reviews Terraform Azure configurations against Microsoft Cloud Adoption Framework (CAF) and Azure Well-Architected Framework (WAF). Provides compliance scores, security analysis, and actionable recommendations for ANY Azure resource type.
huggingface/physics-intern-skills
Agent Claude Code ✓ vendor
Perform symbolic and numerical computation for a target claim. Default backend SymPy + NumPy. Runs symbolic and numerical paths together when both are feasible and flags disagreements. Writes computations/C-NNN.md (narrative) and computations/C-NNN.py (executed script).
Agent Claude Code
A research agent for gathering facts before an overview article is planned. It studies a topic for a defined audience and records the findings in a research brief.
Agent Claude Code
Generate social media preview images (Open Graph) for Rails apps. Creates an OG image using Ruby image libraries and configures meta tags in the layout head.
Agent Claude Code
A manually triggered agent that cleans long-term memory files for a project or user. It combines duplicates, fixes damaged entries, replaces outdated or conflicting information, and reports broken links.
Agent Claude Code
Reviews code for quality and best practices.
Agent Claude Code
Generates and hardens the test suite — unit AND end-to-end — for a change, runs it, and validates the behavior actually works (not just that assertions pass). Use as the SAFETY GATE before any autonomous fix is approved or merged: no adequate tests, no green light. The thing that makes the autonomous loops safe.
Agent Claude Code
MARKER — read-only Claude Pro lane. The director must supply prompt bytes on stdin to claude -p --model opus --permission-mode plan, NOT call workflow agent() with this agentType. See pi/SKILL.md "Claude routing rule (hard rule)".
ai-analyst-lab/ai-analyst-plus
Agent Claude Code
Compare two outputs WITHOUT knowing which skill produced them.
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: