Agents

fivetran/connector_sdk_tools

Agent Claude Code

Debug and fix errors in a Fivetran connector. Use when tests fail or the user reports connector issues.

bluzir/claude-pipe

Agent Claude Code

Write a single final markdown documentation file from structured YAML data. Applies anti-cringe and code-grounding to produce clean, accurate documentation.

MikeCodeur/killer-saas

Agent Claude Code

Implements a planned story in an isolated context. Invoked by /ks-execute.

fltman/project-scaffolder

Agent Claude Code

Debugging specialist for errors, test failures, and unexpected behavior. Use PROACTIVELY when encountering any issues, errors, or test failures.

cookjohn/sd-skills

Agent Claude Code

ScienceDirect research assistant. Coordinates paper search, detail extraction, journal browsing, PDF download, and citation export on ScienceDirect.

fhidalgodev/odoo-development-skill

Agent Claude Code

Specialized agent for analyzing Odoo module upgrade compatibility between versions and generating comprehensive migration plans.

theam/facility

Agent Claude Code

Adversarial reviewer for auth boundaries, secret handling, injection paths, and privilege escalation. Use proactively before merging any change that touches auth, privileged access, external input parsing, CI workflows, or agent-facing surfaces.

denolfe/dotfiles

Agent Claude Code

Use this agent when a major project step has been completed and needs to be reviewed against the original plan and coding standards. Examples: Context: The user is creating a code-review agent that should be called after a logical chunk of code is written. user: "I've finished implementing the user authentication…

appboypov/pew-pew-plaza-packs

Agent Claude Code

Expert Makefile specialist for GNU Make. Use when creating, debugging, optimizing, or refactoring Makefiles. Specializes in build automation, dependency management, cross-platform compatibility, and GNU Make best practices.

ilyasibrahim/claude-agents-coordination

Agent Claude Code

Request for Comments - structured design proposals with stakeholder review process. Modes: author (create RFC), review (evaluate RFC), decision (record outcome).

jieapi/aicode

Agent Claude Code

A read-only codebase exploration agent that investigates how code works and reports its findings without changing files.

itsjwill/gsd-pro

Agent Claude Code

Verifies phase goal achievement through goal-backward analysis. Checks codebase delivers what phase promised, not just that tasks completed. Creates VERIFICATION.md report.

timpara/opencode-academic-research

Agent Claude Code

Orchestrates the full multi-skill academic research pipeline and manages agent handoffs across phases.

chuwu57/Chuwu-PR-OS

Agent Claude Code

Evidence-aware PR and research assistant routing tasks across fourteen specialist workflows curated by Chuwu.

duongthinh03/portfolio

Agent Claude Code

Use this agent when the user needs UI/UX design work including interface designs, wireframes, design systems, user research, responsive layouts, animations, or design documentation. Examples:\n\n \nContext: User wants to create a new landing page design\nuser: "I need a modern landing page design for our SaaS product…

sysnet4admin/_Book_Claude-Code

Agent Claude Code

Use this agent when you need to review recently written code for.

sverklo/sverklo

Agent Claude Code

Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…

9thLevelSoftware/legion

Agent Claude Code

Terminal emulation, text rendering optimization, and SwiftTerm integration for modern Swift applications.

gutomec/nirvana-os-engine

Agent Claude Code

Layer 2 of the dispatch-quality plan. Runs between targetplancommitted and the actual dispatch. Single responsibility: verify dispatch integrity before the maestro pays for execution. Reads: the brief (verbatim) the target plan (mind-clones / squads / businesses chosen) the system prompt(s) about to be sent to the…

heggria/taskflow

Agent Claude Code

Reviews code, plans, architecture risk, and test gaps without editing files.

roundpilot/superpowers-antigravity

Agent Claude Code

Implements one task from an approved implementation plan - writes tests and code, verifies, commits, self-reviews, and reports status. Dispatch with the full task text; do not use for review work.

monkilabs/opencastle

Agent Claude Code

Codebase exploration specialist: deep research, pattern discovery, git archaeology, context gathering before implementation. Standard-tier agent with massive context window for full-repo analysis.

adityaarsharma/youtube-marketing-skills

Agent Claude Code

YouTube Video Updater Agent — bulk-optimises your product/brand videos for CTR, search rank, and LLM discoverability. Fixes links, injects keywords, improves timestamps, generates A/B title variants, posts pinned keyword comment. Sends full diff report before any live write.

incubrain/foundry

Agent Claude Code

UI/UX visual bug detection using the agent-browser skill. Read-heavy — only modifies files when explicitly asked.