Explore
MCP servers and skills: search, filter by where they run, and compare.
claude-opus-5-5-styleGODGOD126
Local九种动画视频风格的 Codex Skill：自动选风格、阅读提示词与完整样片源码，创作新的视频演示。基于 Lemo-Opuscar。
SkillMIT★ 11No key
fable-mode-kitjee599
Local
MCP servers and skills: search, filter by where they run, and compare.
九种动画视频风格的 Codex Skill：自动选风格、阅读提示词与完整样片源码，创作新的视频演示。基于 Lemo-Opuscar。
SkillMIT★ 11No key
⚡ Run Claude Opus 4.8 like Fable 5 — hooks that port Fable's conduct norms. Measured 64%→97% conduct fidelity at 0.72× the cost.
SkillMIT★ 1Few starsNo key
Turn scanned PDFs into accessible HTML and EPUB with page numbers through collaboration with agents
PythonMITFew starsNo key
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
SkillMIT★ 176kNo key
Dual-protocol prompt optimizer plugins for GPT-5.6 and Claude Fable 5, compatible with Codex and Claude Code.
SkillMIT★ 6No key
21-role multi-agent AI software company for Claude Code. CTO, backend, frontend, security, QA, SEO - each role has its own model (Opus 5 / Fable 5), tools and system prompt. Ships with a fetcher for 1
SkillMIT★ 1Few starsNo key
Audit and retune your Claude Code setup for Claude Opus 5
SkillMITFew starsNo key
Determines which LLM model to use for each agent spawn
OfficialSkillMIT★ 5.4k in collectionNo key
Route the task before you run it - surface, model and budget in one card. A Claude skill for spending tokens where they earn their keep.
SkillMITFew starsNo key
Stay on the top Claude model. Claude Code plugin for fewer false-positive safety stops on legitimate work: clean-conversation recovery, read-by-section hook, fallback hook. Eval-tested.
SkillMIT★ 2Few starsNo key
Claude Fable 5.1 prompting guide as Claude Code skills (KO/EN/ZH). Output quality goes up on Opus 5 and Sonnet 5 too.
SkillMIT★ 58No key
작업 성격에 따라 모델을 나눠 맡는 Claude Code 멀티모델 팀 플러그인 — Opus/Fable 오케스트레이터 + Opus deep-reasoner + Sonnet fast-worker + Codex 연동
SkillMIT★ 2Few starsNo key
Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet
SkillMIT★ 40No key
Claude Opus 4.7 native Plan-Execute-Verify coding harness — a Claude Code plugin that enforces a 3-phase pipeline with hook-driven verification
SkillMIT★ 3Few starsNo key
Placebo-controlled benchmark of the most-starred coding agent skills
SkillMIT★ 19No key
SkillCC0-1.0Few starsNo key
Claude Code plugin: rewrites your prompt for the Claude model you're running (Opus 5.5, Sonnet 5, Fable 5.1 and more), following Anthropic's prompting guides, then runs it.
SkillMIT★ 1Few starsNo key
Complete Kaggle integration plugin/skill for AI coding agents — competition reports, dataset/model downloads, notebook execution, and badge collection. Works with Claude Code, Gemini CLI, Cursor, Code
SkillMIT★ 106No key
Curated Claude Code skills by Inbrace, grounded in Anthropic's official docs. Install as a plugin marketplace.
SkillMIT★ 1Few starsNo key
Agent skill that upgrades LLM code to Claude Opus 5.5, GPT-6, Gemini 3.8 without breaking prod. Fixes breaking changes, then proves it with tests and evals.
SkillMIT★ 4Few starsNo key
Who stands behind it
