Agents

joonlab/claude-code-with-github-actions

Agent Claude Code

Helps workshop participants debug and understand Claude Code + GitHub Actions workflows.

WolfpackOfOne/Q-agent

Agent Claude Code

LEAN CLI specialist for running cloud backtests, viewing results, and syncing with QuantConnect. Use proactively when running backtests, viewing results, or syncing code with QC cloud.

szaghi/dotfiles

Agent Claude Code

Verifies every code block, shell command, build invocation, and API claim in a technical blog post against the real source repositories under /fortran and /python. Invoked by the blog skill during draft and review. Returns a per-claim verdict (verified / BLOCKING) with the discrepancy and a corrected version copied…

pablomarin/claude-codex-forge

Agent Claude Code

E2E verification — executes user-journey use cases through user-facing interfaces (API, UI via Playwright MCP, CLI) and produces a markdown report. Read-only: cannot modify code or write files.

mirinodev/claude-code

Agent Claude Code

Expert backend architect specializing in scalable API design, microservices architecture, and distributed systems. Masters REST/GraphQL/gRPC APIs, event-driven architectures, service mesh patterns, and modern backend frameworks. Handles service boundary definition, inter-service communication, resilience patterns, and…

kudosity/gemini-kudosity-sms-extension

Agent Claude Code

A specialized assistant for Kudosity messaging operations. Invoke when the user needs to send SMS/MMS messages, manage contact lists, or configure webhooks through the Kudosity platform.

launchdarkly-labs/launchdarkly-auto-factory

Agent Claude Code

Implements a change and then runs LaunchDarkly AutoFactory Phase 1 on it — creates a feature flag (targeting off), wires the behavior behind it, adds guarded-release metrics + instrumentation, flag-on/flag-off tests, a release manifest, and a review verdict. Use for any coding task that should ship behind a flag, or…

alaminfirdows/agentic-engineering-demo

Agent Claude Code

Security-focused review. Use before merging any PR touching auth, data handling, or external input.

cslsolucoes/SkillsORM

Agent Claude CodeCursor

CEO técnico — classifica demandas por kit (Delphi/FPC vs VueJS/NodeJS vs documentação), delega a sub-orquestradores ou documentation-agent-orchestrator, valida handoff. Não executa detalhe de implementação.

fltman/agent-builder

Agent Claude Code

Meta-agent som skapar specialiserade agenter från PDF-dokumentation. Processerar PDF-filer, extraherar kunskap till markdown, och bygger agenter med skills.

kenlck/skills

Agent Claude Code

Coordinates evidence-led reviews across a configured software repository fleet.

fltman/nis2-compliance-agent

Agent Claude Code

NIS2 compliance expert. Use PROACTIVELY when reviewing code, infrastructure, or documentation for cybersecurity compliance. Automatically triggered for security reviews, risk assessments, incident handling, and compliance documentation.

leifericf/agentic-sdk

Agent Claude Code

Read-only reviewer for one review dimension on one module shard. Returns its findings as an EDN vector, or exactly NO FINDINGS.

Unibean9/harness-skills

Agent Claude Code

Independent code-quality and security reviewer. Use when changes are ready for review or when an adversarial second pass is needed.

NexusSema/omg-marketplace

Agent Claude Code

Generates styled draw.io (.drawio) files from architecture shard document content with C4-appropriate shapes, colors, and layout. Use when: c4-diagram-generator subagent, generating diagrams from a single shard document.

mischacoster/Claude-Code-Notes

Agent Claude Code

Background research agent for the /notes skill. Investigates a captured idea in the codebase and writes a structured research brief to a specified file path. Invoked automatically by the notes skill — not intended for direct user invocation.

hellowind777/helloagents-archive

Agent Claude Code

A read-only agent for generating solution ideas within the HelloAGENTS system. The description does not explain its specific methods or outputs.

duonginspace/claude-code-databricks-ml

Agent Claude Code

Submits ML training jobs to Databricks and fetches results. Has access to Databricks MCP tools and can run submission scripts.

mh2-lee/everything-claude-code

Agent Claude Code

End-to-end testing specialist using Playwright. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.

dy9759/SpecSkillsForClaudeCode

Agent Claude Code

Educational guide specializing in Socratic method for programming knowledge with focus on discovery learning through strategic questioning.

leihuang830102-hash/Opencode-Howto

Agent Claude Code

A security-focused code review agent that looks for weaknesses in authentication, access control, data exposure, injection, and security settings.

romiluz13/claude-code-excellence-audit

Agent Claude Code

Reviews code changes for quality, security, and best practices. Use PROACTIVELY after any code modifications or before commits. MUST BE USED before creating pull requests.

FanaticsKang/code-wiki

Agent Claude Code

A C++ source-scanning agent for the code-wiki skill. It reads a C or C++ source file and produces a summary document describing its structure and responsibilities.

davidYichengWei/Agency

Agent Claude Code

Per-finding code-review validator. Dispatched in parallel (one per finding) after reviewers return. Reads the cited code fresh, attempts a concrete reproduction or cites an exact rule, and renders a verdict with a confidence score and an optional committable suggestion.