Research & Data

AI Agent Skill (SKILL.md) security audit engine — static rules + AST dataflow + LLM semantic review. Catches ClawHavoc-style malicious skills. Open core: engine + 30 baseline rules open, 7 ClawHavoc-specific rules commercial.

Three-phase lint runner for Claude Code: pre-commit replay, parallel read-only analysis, approval-gated fixes.

Literature Review Paper Screener - local agent skill (search, evidence packaging, validation, Excel rendering). Cloud template is proprietary.

Public Claude skills from Bossa

證據優先的 Codex Skill，用於研究 Revit MCP 與 BIM 既有工作流程，將外掛、SOP、Issue/PR、模型證據與失敗紀錄整理成可審查、可驗證、可分流的下一步。

口径先行的数据建模流：先锁口径再清洗，双交付高清 matplotlib 图与交互 HTML。

agentic assisted automatic git commit, sign, tag, push with dedicated roles for agent/human, generate with one command a detaild commit message analysis, commits, signs, tags automaticly, leaves the review & git push to human only

This is a similar usage behavioral data analysis agent skills for Antigravity users like `/insights` in Claude Code.

读取钉钉周报并生成、校验和发送客户满意度回访互动卡片的 Agent Skill

Claude Skill: find the people who publicly asked for what you sell this week, qualify each ask, check the competition, and draft the reply. Runs on Bright Data MCP.

SYMBaiEX: public software, AI systems, source-grounded research, an agent-ready forum, and documented REST, MCP, OpenAPI, and Agent Skills surfaces.

Codex Skill for guarded Rhino to MoI to Cinema 4D geometry handoff and metadata-driven hierarchy reconstruction

AI Agent Skill for systematic bug analysis and reduction, with a daily loop, evidence gate and self-growing lesson library

TQX agent tooling: skills, CLI, and SDK

if it can be clicked twice, it will be. An agent skill that tests your code the way real users eventually will.

Claude Code skill: release workflow for DOI-registered research repositories following the authorship-strategy identifier-federation triplet (ADRs 0001-0003). Five-phase verify-and-deposit runbook.

Agent Skill: audit and sync the four citation layers of a research repo — in-text docs, .zenodo.json, graph.jsonld, Wikidata P2860 — bottom-up.

name: infinity-ads-compliance-audit

Engineering-first OpenAI Codex guide: 14 modules, 9 installable skills, reproducible benchmarks, testing, review, orchestration, and a Living Wiki.

The discovery layer for the agentic web: connecting developers and AI agents to build together

Agent skill to audit and clean a self-hosted Plex library. HTML report, duplicates vs soft copies, action stacks for Cursor/Claude.

A Codex skill for auditing creator contracts, routing metadata, source boundaries, and declared validation evidence.

Codex skill for guided DFRobot WIAnode configuration, validation, and SKU reporting

Save anything. Find the right thing when work starts. AI agent skills that turn saved material into a searchable working library.