LLM agents

linegel/threejs-complete-set-of-skill

Agent

Route a Three.js WebGPU request to the smallest installed skill set while preserving source precedence, ownership, capability gates, and gaps.

hardiktiwari/PM-operating-OS

Agent Cursor

Interactive onboarding that collects user context and configures the PM Operating System — rules, products, and MCPs. Use when user says "onboard", "setup", "PM-OS setup", or "get started".

criblio/ultra-jira-mcp

Agent Claude Code

Reviews a GitHub pull request created from the current repository and posts findings as line-specific and summary comments via gh. Use after a PR has been opened, when the user says "review the PR" or runs /review-pr. Must be given the PR number or told to infer it from the current branch.

stoa-platform/stoa

Agent Claude Code

Audit conformite du contenu public. Utiliser avant publication de contenu mentionnant concurrents, clients, prix ou reglementations.

jianchen08/Agent-os-open

Agent

The execution engine for an AI agent built with LangGraph, a framework for connecting model decisions, tool calls, and state into a workflow. It accepts a user message, agent configuration, and registered tools, then returns a result or streamed events.

gkoreli/backlog-mcp

Agent

You are an expert validation agent for the MCP Writable Resources concept - a revolutionary pattern that brings fswrite-like efficiency to MCP data manipulation.

skillberry-ai/runspace-agent

Agent Claude Code

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

KyaniteLabs/liminal

Agent

Forgejo is the source of truth for this repo's issues, PRDs, and pull requests.

Amal-David/mlx-porting-skill

Agent

Look for blind spots, unsupported architecture families, missing validation gates, and overclaimed optimizations.

mhattingpete/agent-composer

Agent Claude Code

Use this agent when you need to run the coding-prompt.md command, commit the resulting changes, and push to the remote repository. This agent handles the complete workflow from executing the custom command to ensuring changes are committed and pushed with proper git hygiene.\n\nExamples:\n\n \nContext: The user wants…

feimacode/feima-copilot-llms-extension

Agent

A step-by-step tutorial for using several kinds of coding agents in Visual Studio Code while building a simple to-do app.

DemitriusQuadros/bruce

Agent Claude Code

Full-stack frontend specialist combining UX design and engineering for the go-base-project ecosystem. Use this skill whenever someone needs to create UI pages, components, or full frontend applications that connect to the Go API (port 8080). Triggers on: create a page, build a UI, design a frontend, add a dashboard…

majiang213/OpenClaw-MAS

Agent

Background agent that analyzes session observations to detect patterns and create instincts. Uses Haiku for cost-efficiency. v2.1 adds project-scoped instincts.

agentproto/ts

Agent Claude Code

Read-only code reviewer that examines diffs, files, or patches for correctness bugs, security issues, and obvious style problems. Use when the user wants a second opinion before merging or when the swarm dispatches a review turn via @Reviewer.

brandonkindred/Khala-Agentic-AI-Teams

Agent

RefinementAgent.run() (via diffformat.difforfull) and DesignAgent.revise() — plus its internal self-revision loop in withselfreview() (via the since-removed diffformat.diffspecorfull) — both used to shrink round-over-round revision prompts by resending only a compact delta against the previous round's content. Both…

lexCoder2/lxDIG-MCP

Agent

Expert TypeScript developer for lxDIG-MCP. Implements features, fixes bugs, and refactors code following the two-phase builder pattern.

sponge-b0b/Polaris

Agent

Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.

pilotwaffle/TORQCLAW

Agent Claude Code

Adapted from the TORQ Console harness (E:\TORQ-CONSOLE\.claude\agents). These are TorqClaw-local definitions. The Console harness drives a different product through .torq/launch/ watcher scripts and hardcoded E:\TORQ-CONSOLE\... paths; running those agents against this repo would read specs from and write verdicts…

contextfs/contextfs

Agent

Automatically extract and save important information from conversations to ContextFS.

Nafjan/summon

Agent

Claude Fable 5.1 for lead architecture, design, strategy, orchestration planning, and final escalation on consequential or unresolved problems. Other agents gather evidence, implement, and test; you make the difficult decisions and assess their work. Do not become the routine coder, researcher, or default chair for…

HaoweiChan/tinboker

Agent Claude Code

Use for changes touching the pipelines/ tier — podcast ingestion (Spotify), news ingestion (Tavily/RSS), transcription, summarization, ticker-sentiment extraction, the contentbuilder (LangGraph) pipeline, Marp slides, or the wiki knowledge graph / wikibuilder. Delegate here before grepping pipelines/.

scrollDynasty/BrowserMesh

Agent Claude Code

Audit a diff against the BrowserMesh session-isolation and concurrency invariants - cross-session page IDs, global locks or global current-session state, queue poisoning, and close/shutdown races. Use before merging any change that touches src/runtime/, src/adapters/playwright/, session or page lifecycle, the serial…

hanselhansel/context-cli

Agent Claude Code

You are a test writer for Context CLI. Your job is writing comprehensive tests.

homemade-software-inc/completion-kit

Agent Claude Code

Assesses a pull request against CompletionKit's merge bar — is it worth merging at all, is it secure, is the code excellent, is it as simple as possible, and does it pass the project's hard gates (CI, 100% coverage, the inline test-schema gotcha, conventions). Use when triaging or reviewing an incoming PR, especially…