MCP servers and skills: search, filter by where they run, and compare.
Skill for end-to-end predictive maintenance: explores raw IoT telemetry in S3, engineers features, trains AutoML models (RUL regression, failure classification, multi-label classification, or survival
OfficialSkillMIT-0★ 8No key
Agentic test automation skills for test case authoring, context, intent, self healing, failure classification, guardrails and progressive context disclosure
SkillApache-2.0★ 1Few starsNo key
Offline-first diagnostic and Root Cause Analysis tool that turns CI, build, test, deployment, and container failures into evidence-backed reports and actionable ticket drafts.
SkillMIT★ 5No key
Agent skill for production resilience: proportional defensive engineering, failure classification, idempotency, backpressure, and evidence-backed verification.
SkillMIT★ 1Few starsNo key
PowerShell skills and guardrails for reliable Windows command execution by AI agents, with Codex and Claude Code adapters.
SkillMIT★ 2Few starsNo key
CLI installer for AI agent skills (SKILL.md) targeting RHEL DevOps tooling — supports Claude Code, Cursor, and 40+ Agent Skills standard compatible tools
SkillApache-2.0Few starsNo key
Govern Power Automate flows and Power Apps at scale using the FlowStudio MCP cached store. Classify flows by business impact, detect orphaned resources, audit connector usage, enforce compliance stand
OfficialSkillMIT★ 40k in collectionNo key
Extract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes/no) predictions. Use when the user asks to "analyze VLM BCQ gaps", "extract VLM false positives and fal
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Use when a concrete ./holohub command fails, hangs, regresses, or returns wrong output and needs reproducible diagnosis and verification.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Stop your coding agent from stalling real work on self-invented bookkeeping - receipts, hashes, locks, certification rituals. Ship first, then verify. Skill for Claude Code, Codex, and other agents.
SkillMIT★ 179No key
Claude Code and Codex skills for empirical applied-micro research: reproducibility auditing, LLM-pipeline methods, event studies, WRDS, Stata, publication-grade tables
SkillMIT★ 22No key
洁癖.skill：让 AI Agent 少留痕，留下的都有用。 Tidy Skill: make AI agent artifacts intentional, scoped, and disposable when needed.
SkillMIT★ 18No key
A guided Cloudflare skill for durable, receive-first AI agent email inboxes.
SkillMIT★ 7No key
Classify a raw app idea into CS terms and emit a frozen, machine-parseable architecture contract — before any technology is named.
SkillMIT★ 3Few starsNo key
jq-like stream processor for semantic matching and extraction
SkillMIT★ 2Few starsNo key
Improve existing agent skills, prompts, articles and workflows through bounded, reversible experiments. Compatible with Codex, Claude Code, Hermes and OpenClaw.
SkillMIT★ 2Few starsNo key
Turn agent development into deterministic state, evidence, and gate-controlled delivery for humans and AI.
SkillApache-2.0★ 3Few starsNo key
Diagnosis-first, reversible Skill for Codex Reconnecting 1/5 through 5/5 loops
SkillMIT★ 6No key
Agent skill for typed decisions via any Laya-compatible API — routing, triage, guardrails, moderation, tool pre-screening. Provider-agnostic.
SkillApache-2.0★ 2Few starsNo key
Neuro-Symbolic memory for LLM agents: LEGACY repo - new work at prethinker
SkillMIT★ 5No key
Essential workflow skill for AI coding agents. Structured dev cycle: understand, plan, implement, verify, commit, review.
SkillMIT★ 2Few starsNo key
Agent skill for systematically improving other skills with held-out validation gates
SkillMIT★ 4Few starsNo key
Who stands behind it
