Research & Data

Private repository for work4all Claude skills, references and reporting knowledge

Claude skill для ежедневного анализа лидов с отчетом в чат б24

Codex skill for auditing official ML benchmark protocol fidelity and result claims.

An Agent Skill for version-accurate Wwise SDK research from your locally installed headers, samples, CHM Help, and source code.

opencode/Claude skill for analyzing WeChat chat records via CipherTalk + ChatLab MCP

Skills for Claude Code. Includes dslrig-analysis: end-to-end MOSIP DSL run analysis into a Word + Markdown failure report.

Evidence-led Codex skill that turns scientific project materials into directly openable offline reports.

Review product decisions through behavioral psychology, economics, growth, pricing, platform, strategy, and welfare lenses.

Agent Skill that teaches an AI agent to benchmark commands correctly with hyperfine, instead of guessing from a single `time` call.

产业大会研究规划与证据工程：以可证伪假设、反证、边界条件和职责校验构建演讲级研究证据库。

Agent skill that interrogates a product's definition with five questions — asking past behavior, never future opinion — and returns a verdict with its validation debt.

A curated catalog of self-improved agent skills for Hermes and compatible agents

name: code-review

Skills for AI coding agents: code review, debugging, security audits, refactoring, cleaning up AI-written code and text, and more.

全球酒店预订&低价监控提醒Skill，200万+精选酒店，独家优惠价格，让你的Agent轻松预订品质酒店，支持支付宝下单+查询历史订单，24 小时客服支持，全天候响应。

A curated list of awesome Hermes (Nous Research) resources, models, agents, skills & tools

Codex Skills and plugins by Tengo, starting with Change Title for short, searchable task names.

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.

AI 产品架构逆向分析 Codex Skill

Canonical agent skills for Weft — search the agent web and pay any x402 endpoint

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

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.