MCP servers and skills: search, filter by where they run, and compare.
The marketplace for verifiable AI outcomes: state a task, get a fixed price upfront, and Primitive Bench routes across tools to complete it, refunded if the outcome isn't delivered. This repo is the o
SkillApache-2.0★ 122No key
Concurrent-agent benchmark suite packaged as a Hermes skill. Markdown REPORT.md output
SkillMITFew starsNo key
Free browser tools for developers, SEO and files, each also callable by AI agents through an MCP server.
Hosted by authorMITFew starsNo key
📦 CloudArc bounded-memory benchmark: streaming pack/unpack SLOs, multi-file .vibo dedup, remote-search telemetry, CI gates #agentskills #benchmark #memory #vibo
SkillLink onlyFew stars
拆抖音对标 · 输入一个抖音账号，全量采集公开作品数据并产出对标调研报告（原始数据 + Markdown + 浅色杂志风 HTML）。Agent-friendly skill.
SkillMIT★ 5No key
Local-first benchmark comparing four Skill packaging patterns — doc-only, inline-code, Python script, and Go binary — to find which is most reliable when an LLM coding agent executes a Skill.
SkillLink onlyFew stars
ERPNext management, file operations, read-only database access, and ERPNext API integration
PythonMIT★ 4Few starsNo key
Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this repo layout.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Use this skill to bring a supported object-detection vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors export, TRT e
OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key
Local-first MCP server that tells coding agents which files to read, and how sure it is. 97% Hit@10 on Java (SWE-bench Multilingual), 89% on Python (SWE-bench Lite), zero LLM cost. mcp-brain calibrate
PythonMIT★ 5No key
中文 AI 幻灯片 Skill 实测选型指南：同一份 BP 对比 SeaSlides、PPTX 与 HTML/PDF 工作流
SkillMITFew starsNo key
MCP-native second brain with an automatic entity graph over your markdown notes. Honest benchmark vs vanilla RAG and nano-graphrag included.
PythonApache-2.0Few starsNo key
Linter for AI-writing tells in commit messages, PR descriptions and docs. It does not guess who wrote it. It shows the tells.
SkillMIT★ 13No key
Any file → clean Markdown for AI agents: PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images (OCR), audio and video (metadata, subtitles, transcripts). A fast Rust MCP server and CLI that r
SkillMIT★ 1.1kNo key
Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.
SkillApache-2.0★ 694No key
Research Knowledge Acquisition Engine — 5 autonomous campaigns (literature-survey, patent-mining, benchmark-archaeology, meta-analysis, baseline-establishment) with quantitative budget enforcement
SkillApache-2.0★ 1Few starsNo key
Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal Nemotron-3-Content-Safety. Produces a Markdown policy, J
OfficialSkillApache-2.0 AND CC-BY-4.0★ 3.6k in collectionNo key
Fully local MCP retrieval tool for coding agents. 161M encoder, ~1s per tool call, no API, no LLM in the query path. No file reads: line numbers, callers, callees and exact call sites, packed to a tok
GoMIT★ 5No key
모두 파싱해버리겠다 — HWP·HWPX·PDF·Office 문서를 Markdown으로. 양식 자동 채우기와 신구대조를 갖춘 CLI·MCP 서버 | Convert Korean documents (HWP, HWPX, PDF, Office) to Markdown — CLI and MCP server with form filling and diff
Node.jsMIT★ 2.9kNo key
A Claude Code skill that tailors your resume to one job posting. Nothing invented: every claim comes from your own fact bench. Every bullet measured against your real document width.
SkillMIT★ 1Few starsNo key
The fast, precise document-intelligence engine for every language: text, tables and metadata from 100+ formats, with OCR, transcription and code intelligence.
SkillMIT★ 9.5kNo key
Analyze text content and produce statistics including word count, line count, character count, most frequent words, and readability metrics. Works on any plain text input provided inline or from a fil
OfficialSkillApache-2.0★ 564 in collectionNo key
Codex plugin MCP server (codex-plugin-mcp) for token efficiency, token reduction, context compression: exact-recoverable terminal, file, project, web, memory.
SkillMIT★ 4Few starsNo key
Give your coding agent the right code, not more code. Local context engine for Claude Code, Cursor & Codex: code graph + hybrid search + embeddings + git history, packed into a token budget. Held-out
PythonMITFew starsNo key
Who stands behind it
