MCP servers and skills: search, filter by where they run, and compare.
中国留学生在美国的证据驱动型 AI 生存副驾驶 | Evidence-first AI copilot for housing, credit cards, cars, healthcare, F-1/OPT and everyday decisions.
SkillMIT★ 3Few starsNo key
Evidence-first project diagnosis for Codex and Claude Code: find the primary contradiction, act, and validate.
SkillMIT★ 5No key
Zero-infrastructure, local-first memory for AI agents. One SQLite file — no Postgres, Neo4j, or cloud. Bi-temporal supersession (updates, never deletes), four-channel hybrid retrieval, and a drop-in M
PythonApache-2.0★ 14No key
Evidence-first entity and knowledge graph MCP server for AI agents to verify claims, trace cryptographic provenance, and retrieve 90% less context.
Node.jsMIT★ 1Few starsNo key
Evidence-first agent skill for auditable statistical analysis, diagnostics, publication figures, tables, and teaching reports from real research data.
SkillMIT★ 5No key
Evidence-first Codex, Claude plugin for bugs, security, and 10k-to-1M-user scale readiness.
Node.jsMIT★ 18No key
Evidence-first AI agent skills for reliable data analysis, machine learning, model validation, and reproducibility.
SkillMIT★ 13No key
Evidence-first AI agent workbench for vendor API integrate & contract heal — real production edits, multi-lang surfaces, live PRs (not a runtime SDK).
SkillMIT★ 8No key
Evidence-first long-term experiment memory skill for AI coding agents, with optional Jev decision-model layers
SkillMIT★ 10No key
数学建模竞赛全流程 AI Skill：以证据优先的 mmflow 运行时为唯一事实来源，12 阶段状态机（P0–P11）逐阶段 fail-closed 门禁，哈希链账本不可变、结果可复现、隐私扫描、heal_mismatch 规范恢复。38 个 CLI 命令、56 个模板（7 类目）、15 份手册、46 种证据类型；LaTeX 论文真实编译、退化测试与反证、多角色独立评审闭环。23 项契约校验、2
SkillMIT★ 19No key
Evidence-first agent skill and Obsidian-friendly career operating system.
SkillMIT★ 4Few starsNo key
Evidence-first vulnerability research workspace and Skills for Claude Code and Codex.
SkillMIT★ 4Few starsNo key
对话式产品需求讨论 Agent Skill（Claude Code / Codex CLI 通用）：需求先于方案、竞品现实、结构化反方，把模糊想法推进到 PRD 或想清楚的「不做」/ An adversarial, evidence-first product-requirements discussion skill for SKILL.md-compatible agents
SkillMIT★ 4Few starsNo key
Evidence-first SEO, AEO, GEO and AI-search workflows for Codex and Claude Code — one router, 27 focused skills.
SkillApache-2.0★ 4Few starsNo key
Evidence-first Codex skills for auditing, shrinking, and optimizing Z80 and ZX Spectrum projects.
SkillMIT★ 5No key
Guarded MCP tools for AI-assisted mobile build, Appium testing, security scanning, verification, and fix-retest loops.
DockerMIT★ 11No key
OpenAI Codex plugin for evidence-first code review, audits, fact checks, run contracts, and bounded subagent workflows.
SkillMIT★ 4Few starsNo key
Evidence-first product quality checks for web apps
SkillApache-2.0★ 1Few starsNo key
The local intern for Claude Code — 44 job-shaped tools, evidence-first briefs, durable artifacts. Local-first MCP server over Ollama with zero egress by default; no GPU big enough? Ollama Cloud runs t
Node.jsMIT★ 1Few starsNo key
Research-grounded, harness-agnostic skills for AI coding agents
SkillMIT★ 15No key
Evidence-first workflow skills for Codex CLI: right-sized planning, Two-Strike re-plan, and completion claims backed by checks that ran.
SkillMIT★ 11No key
CCHIA Security Compiler and read-only security checks for AI, cloud, IAM, Kubernetes and agents
SkillApache-2.0★ 3Few starsNo key
Evidence-first embedded debug workbench for real firmware projects: project adapters, debug packets, deterministic analyzers, and regression-ready reports.
SkillMIT★ 4Few starsNo key
Evidence-first Android and iOS security audits with CLI, TUI, MCP, public vulnerability intelligence, and OWASP-aligned evidence.
PythonMITFew starsNo key
Who stands behind it
