Skill Claude CodeCodex
Tunes prompts iteratively using reflection and success metrics. Use for: optimize this prompt, dspy tune, improve prompt with reflection, self-refine-loop.
not rated 9 yesterday A 39 tokens
original MIT
9Stars on the repository
102Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
evolution
26Skill Claude CodeCodex
Tracks incremental improvements to skills and workflows over time. Use for: evolve skill, track evolution, improve over time, skill-evolver.
not rated 9 yesterday A 31 tokens
original MIT
evolver
27Skill Claude CodeCodex
Lightweight skill mutation helper for quick iterations. Use for: quick evolve, mutate skill, tweak skill, skill-evolver.
not rated 9 yesterday A 29 tokens
original MIT
Skill Claude CodeCodex
Analyze completed experiment results with effect sizes, uncertainty, guardrails, limitations, and evidence-based next steps. Use for: experiment results, A/B test analysis, test readout, experiment decision.
not rated 9 yesterday A 43 tokens
original MIT
Skill Claude CodeCodex
Triages exposed TCP listeners found by security audits. Use for: exposed port, what is listening, fix exposed service, open port.
not rated 9 yesterday A 34 tokens
original MIT
feral-core
30Skill Claude CodeCodex
Unified godlevel feral engine that combines autonomous-skill-forge, beta-unlocker, godlevel-secret-hunter and skill-persistence-guard into one high-autonomy entry point. Use when the user wants maximum power, go feral, unlock, secret skills, growth rounds, instant implementation, all-out mode, or when any of the four…
not rated 9 yesterday A 113 tokens
original MIT
Skill Claude CodeCodex
Investigate a GitHub repository from a URL by reviewing its README, file tree, local clone status, and recommended next steps. Use for: GitHub URL, check this repository, scout repository, understand this project.
not rated 9 yesterday A 50 tokens
original MIT
Skill Claude CodeCodex
Verifies task completion against stated goals before marking work done. Use for: verify goal, confirm success, did I achieve this, check if done.
not rated 9 yesterday A 34 tokens
original MIT
Skill Claude CodeCodex
God-level hunter for unknown, secret, experimental, undocumented, and hidden capabilities across the entire ecosystem. Scans skills, scripts, configs, agent architectures, and runtime for latent power. Use on godlevel, secret skills, unknown capabilities, crazy experimental, unlock hidden, or when the creator demands…
not rated 9 yesterday A 97 tokens
original MIT
Skill Claude CodeCodex
Pauses high-risk actions for explicit human approval. Use for: approve this, hitl check, human review needed, confirm before send.
not rated 9 yesterday A SkillSpector: pass 34 tokens
original MIT
Skill Claude CodeCodex
Apply respectful, rate-limited browsing practices for public websites while honoring site rules and access controls. Use for: responsible web research, rate limiting, CAPTCHA stop, robots.txt.
not rated 9 yesterday A 43 tokens
original MIT
Skill Claude CodeCodex
Coordinate authorized work across sandbox tools, a user-approved local desktop, connected services, and public-web research. Use for: hybrid execution, local plus sandbox, connected services, scoped desktop access.
not rated 9 yesterday A 45 tokens
original MIT
Skill Claude CodeCodex
Stress-tests skills with edge-case prompts and scoring rubric. Use for: test skill, hyper test, skill QA, audit skill quality.
not rated 9 yesterday A 33 tokens
original MIT
Skill Claude CodeCodex
Generates visual assets via image generation tools. Use for: generate image, create asset, make icon, design mockup.
not rated 9 yesterday A 31 tokens
original MIT
Skill Claude CodeCodex
Synthesizes findings from multiple sources into actionable insights. Use for: synthesize, key takeaways, summarize findings, insight report.
not rated 9 yesterday A 34 tokens
original MIT
Skill Claude CodeCodex
Ensures web access is used effectively for live information. Use for: search web, need internet, look up online, current info.
not rated 9 yesterday A 31 tokens
original MIT
Skill Claude CodeCodex
Builds structured knowledge graphs from text and sessions. Use for: knowledge graph, map entities, build graph, entity map.
not rated 9 yesterday A 30 tokens
original MIT
Skill Claude CodeCodex
Discovers MCP servers and reads tool schemas before calling MCP tools. Use for: mcp tools, MCP schema, discover MCP, which MCP tool.
not rated 9 yesterday A 36 tokens
original MIT
Skill Claude CodeCodex
Manages large context windows via chunking, summarization, and retrieval. Use for: manage context, too much context, chunk document, context budget.
not rated 9 yesterday A 35 tokens
original MIT
Skill Claude CodeCodex
Scores and filters retrieved memory against trust and poisoning risk. Use for: sanitize memory, trust score retrieval, clean knowledge graph, semantic-memory-manager.
not rated 9 yesterday A 35 tokens
original MIT
Skill Claude CodeCodex
Coordinates multiple agents with role assignment and handoffs. Use for: coordinate agents, multi agent team, agent roles, delegate agents.
not rated 9 yesterday A 31 tokens
original MIT
Skill Claude CodeCodex
Orchestrates complex multi-agent pipelines with DAG execution. Use for: orchestrate agents, agent pipeline, multi step agents, multi-agent-coordinator.
not rated 9 yesterday A 37 tokens
original MIT
Skill Claude CodeCodex
Unify WhatsApp, Telegram, and future channels with shared conversation context and message-quality assessment. Use for: bridge messengers, unified chat memory, cross-platform reply, WhatsApp responder.
not rated 9 yesterday A 45 tokens
original MIT
Skill Claude CodeCodex
Converts natural language descriptions into SKILL.md drafts. Use for: create skill from description, NL to skill, skill from prompt, skill-creation-enabler.
not rated 9 yesterday A 40 tokens
original MIT
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: