MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Agent skill + CLI/library that routes agentic AI tasks to the right reasoning effort (minimal→xhigh) while keeping the model fixed — for Codex CLI and the OpenAI Responses API, with auditable escalati
SkillMIT★ 2Few starsNo key
Codex plugin guardrails for suspicious shallow reasoning turns
SkillMIT★ 7No key
针对DSH：添加第三方API时无法调节思考强度问题（DeepSeek Harness小完善计划其二）· Agent Skill 维修手册
SkillCC-BY-4.0★ 1Few starsNo key
A portable, documentation-first AI skill for security engineering reasoning — adversarial thinking, evidence over assumptions, temporal trust boundaries, and structured findings.
SkillMIT★ 1Few starsNo key
Structured reasoning exploration: map claims and the inferences between them, then explore them visually.
SkillMIT★ 2Few starsNo key
Nature-style AI peer reviewer for scientific manuscripts. 我把Nature期刊审稿人蒸馏了。
SkillMIT★ 51No key
An AI skill that is inspired by "The Ballad of LLM Agents: Philosophical Reasoning for Chemistry."
SkillMIT★ 4Few starsNo key
💭 Lightweight version of Clear Thought MCP as agent skills
SkillMITFew starsNo key
SkillAGPL-3.0★ 1Few starsNo key
Durable guidance for professional Unreal Engine development reasoning with Codex
SkillMIT★ 2Few starsNo key
SkillMIT★ 36No key
SkillMIT★ 3Few starsNo key
A rigorous Codex Skill suite for communication research and computational communication studies.
SkillApache-2.0★ 3Few starsNo key
SkillMIT★ 2Few starsNo key
SkillMIT★ 1Few starsNo key
A CLI that attempts to suppress visual hallucinations in VLMs.
SkillMIT★ 3Few starsNo key
Turn your yes-man LLM into a direct and honest partner. I run this as my defaul Skill that loads on conversation start. Updating your system prompt to load this Skill is recommended. 290 lines.
SkillMIT★ 3Few starsNo key
Audit Codex session timing across reasoning, compaction, tools, messages, and execution gaps.
SkillLink only★ 3Few stars
AI-powered wireless network intelligence using SAC-LTC for agentic AI systems. Autonomous Wi-Fi/hotspot management with RF explainability, presence detection, and navigation guidance.
SkillMIT★ 2Few starsNo key
Claude Code skill for balanced AI code & writing review — a preserve-first protocol + multi-model critic panel (Ollama, Codex CLI, or cloud) for a genuinely independent second opinion. Measured: cuts
SkillMITFew starsNo key
Adaptive pre-execution reasoning skill for Codex: isolate framing, challenge assumptions, and converge on testable decisions.
SkillLink onlyFew stars
Who stands behind it
