MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
The theory of LLM wikis, running as one. A framework for agent-operated knowledge: typed, linked, review-gated markdown your agents execute.
SkillCC-BY-4.0★ 91No key
Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron `embed`/`rerank` retrieval recipes.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Use this skill when the user is doing hands-on DOCA RDMA programming on a BlueField DPU, ConnectX NIC, or DOCA host — bringing up an RDMA context on a doca_dev, picking a connection method (RDMA CM, b
OfficialSkillApache-2.0★ 3.6k in collectionNo key
A recipe for any AI agent to build a self-improving theory-of-mind model of its user from interaction logs (feedback precognition). What you mind is what you get.
SkillMIT★ 3Few starsNo key
knowledge base tools for humans & ai (bleeding edge)
SkillGPL-3.0Few starsNo key
The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai
SkillGPL-3.0★ 8.7kNo key
This repository is a set of *companion* skills for Qualitative Comparative Analysis (QCA: csQCA / mvQCA / fsQCA / tQCA), positioned as a **methodological knowledge and writing-navigation layer**.
SkillMIT★ 3Few starsNo key
Concept–Knowledge design sessions in Claude Code. Every concept must be undecidable against knowledge, and every expansive partition must name what it breaks — enforced by the tool, not by good intent
SkillMITFew starsNo key
Portable open-source Second Brain framework & agent skill: cross-session memory, honesty/coordinate discipline, governance schemas (GIR/CRL), local-first, MIT. Works with DeepSeek / WorkBuddy and othe
SkillMIT★ 1Few starsNo key
🎯 Production-grade multi-agent Claude Skill for live-ops game retention & daily quest design. Uses Self-Determination Theory (SDT) & D1/D7/D30 telemetry metrics to maximize long-term engagement while
SkillMIT★ 5No key
A knowledge base for builders. Session-over-session context that compounds. Everything resolves to markdown.
SkillMIT★ 4Few starsNo key
Bilingual academic skills and knowledge packs for Claude Code and Codex.
SkillMIT★ 3Few starsNo key
🎲 Research-backed Vietlott statistics advisor grounded in 30 academic sources. Combines combinatorial probability with behavioral economics (gambler's fallacy, near-miss effect), real draw independen
SkillMIT★ 4Few starsNo key
A reusable agent skill for deep PDF literature review, Excel knowledge-base organization, and relevance-based reading prioritization.
SkillMIT★ 8No key
Design guardrails, not templates. A library of UI design direction files that give LLMs (and humans) the context to build tasteful, consistent interfaces in any style.
SkillMIT★ 10No key
DSH skill + gate kit: inject Lua/Luau into Unity+XLua games and read runtime state without memory scanning
SkillMIT★ 1Few starsNo key
A standardized method to give AI agents a persistent philosophical and ethical operating context.
SkillApache-2.0★ 4Few starsNo key
ADAM — self-improvement layer for Claude Code. Observes session friction (corrections, retry loops, dead-ends, error loops, edit churn) via lightweight hooks and proposes targeted skills, memory entri
SkillMIT★ 3Few starsNo key
A domain-agnostic methodology for building, extending, reviewing, and refactoring ontologies, domain models, taxonomies, and knowledge-graph schemas — packaged as a Claude Code / Claude Skills plugin.
SkillCC-BY-4.0★ 4Few starsNo key
OpenClaw-inspired memory + bootstrap layer for Claude Code (hooks, templates, skills, subagent)
SkillMIT★ 1Few starsNo key
150 lines that make Codex a senior refactoring engineer. Process + guardrails, not knowledge — because LLMs already know how to refactor.
SkillMIT★ 3Few starsNo key
Agent Teacher: an evidence-graded pedagogy knowledge library, a local teacher rehearsal on authored fraction cases, and a draft publication pipeline. Python, no model calls.
SkillLink only★ 4Few stars
AI 会编数据、假报完成、换人就失忆？7 个实战方法论技能，让 AI 干活可验证、可追溯。Practical skills that make AI honest - no fabrication, no fake completions, no lost context.
SkillMIT★ 1Few starsNo key
Skills, hooks, and memory patterns for Claude Code. Built from daily use, not theory.
SkillMITFew starsNo key
Who stands behind it
