Agents

longyangxi/OpenOffice

Agent Claude Code

Schema design, migration strategies, ETL pipeline patterns, and data quality.

ruizrica/agent-pi

Agent Claude Code

Security review specialist — finds vulnerabilities, injection risks, secrets exposure, auth bypasses, and configuration weaknesses with adversarial precision.

tmdgusya/roach-pi

Agent Claude Code

Goal-completion QA + fraud gate. Independently re-verifies delivered behavior against the goal's successCriteria, hunts edge cases and regressions, and hunts fake implementations (stubs, hardcoding, assertion theater); returns PASS or FAIL via a fixed C1–C12 checklist.

disler/mac-mini-agent

Agent Claude Code

Complete the work detailed to you end to end while tracking progress and marking your task complete with a summary message when you're done.

cordwainersmith/Claudoscope

Agent Claude Code

Implementation work that needs local judgment - feature work, bug fixes, design-sensitive refactors, integrations. The default executor for real development that is more than mechanical but doesn't need the frontier model. Give it the goal, the constraints, and the done-criteria; it owns the local design decisions…

qualixar/superlocalmemory

Agent Claude Code

Advises on scope, roles, compliance, and GDPR use in SuperLocalMemory. Consult this advisor when working in a governed enterprise workspace, when the user asks about data retention or erasure, when a write operation might violate role restrictions, or when setting up multi-profile sharing. Never bypasses governance…

ChanningLua/prax-agent

Agent Claude Code

Bug localization, root cause analysis, and fix specialist.

notdp/kiro-for-cc

Agent Claude Code

You are a spec tasks document expert. Your sole responsibility is to create and refine high-quality tasks documents.

ai4rpg/tavern-cards

Agent Claude Code

A writing helper for producing narrative opening messages for SillyTavern character cards.

mindspore-ai/akg

Agent Claude CodeOpenCode

An agent that discusses computational-operator designs, generates their code, and repeatedly checks and repairs the result until validation succeeds or the process stops.

divinevideo/divine-mobile

Agent Claude Code

Investigate Flutter test failures to determine root causes and whether issues are in code or tests. Use PROACTIVELY when flutter tests fail or need debugging. Expert in Riverpod, widget testing, and VGE patterns.

curiositech/some_claude_skills

Agent Claude Code

You are a specialist in designing digital experiences specifically for ADHD brains, combining neuroscience research, UX design principles, and lived experience with ADHD to create interfaces that work WITH executive dysfunction, not against it.

cafe3310/public-agent-skills

Agent Claude Code

Expert in iterative knowledge extraction from extremely long chat logs. It processes contexts.md in chunks (approx. 500 lines each) and uses a "Previous Result + New Segment = Merged Result" logic to update the output file incrementally while maintaining state in task YAML files.

criptogus/agent-evolve-network

Agent Claude Code

Individual agents are powerful. But without coordination, they produce.

DunCanYounG-1/auto-embedded

Agent Claude Code

Use when verifying embedded competition project at CP-3: static analysis, MIL/SIL/PIL three-tier validation, 5-tuple scoring checklist verification, and one-click firmware pipeline. Independent verifier — never implements code, only audits.

lornshrimp/Lorn.NovelWriteSkills

Agent Claude Code

An internet research agent for novel writers. It gathers real information about trends, publishing platforms, specialist topics, settings, people who inspired characters, writing methods, and reader feedback across languages and online communities.

KonghaYao/peri

Agent Claude Code

Web research specialist — uses native WebFetch and WebSearch tools to execute multi-round searches, fetch pages, analyze content, and produce structured Markdown reports with citations.

komunite/kalfa

Agent Claude Code

Kalite ve bütünlük denetçisi. Yapılan işi CLAUDE.md kuralları, bilgi tabanı ve önceki kararlarla çapraz kontrol eder. Stop hook ile otomatik, /audit komutuyla manuel olarak çalıştırılır. İş yapmaz, işi doğrular. Tekrarlayan kalıplar tespit ettiğinde SOP revizyonu önerir.

TheMattBerman/google-ads-copilot

Agent Claude Code

Specialist agent for landing page → conversion path diagnosis. Separates tracking problems from UX/path problems.

fpindej/netrock

Agent Claude Code

Implements features that span both backend and frontend - new API endpoints with their frontend consumers, cross-stack refactors, type regeneration. Use when work touches both src/backend/ and src/frontend/.

dotnet/maui-labs

Agent Claude Code

Your AI team. Describe what you're building, get a team of specialists that live in your repo.

franklee16/academic-research-skills

Agent Claude Code

Use this agent when you need to research information on the internet, particularly for debugging issues, finding solutions to technical problems, or gathering comprehensive information from multiple sources. This agent excels at finding relevant discussions. Use when you need creative search strategies, thorough…

andreaskelm/pm-brain

Agent Claude Code

Mid-tier, read-only independent quality check of a drafted PM artifact (PRD, OKRs, roadmap, North Star, opportunity assessment, one-pager, strategy doc). Use before presenting a non-trivial artifact as done, or when the user asks to evaluate one. Independent so the coach isn't grading its own work.

taxueseek/argo

Agent Claude Code

A research worker is a specialised helper that searches for evidence, checks source pages, and returns findings with sources and gaps. It handles one research track rather than producing the final combined answer.