Research & Data

An evidence-driven Codex skill for reviewing code, diffs, repositories, tests, dependencies, CI/CD, infrastructure configuration, and machine-generated analysis reports.

A Codex skill and project-local toolkit for installing AUTO-07p, running bifurcation analysis, and visualizing continuation results.

Codex Skill for research-gated, approval-bound, self-converging Skill changes with coupling and rollback checks.

A Codex skill for one-way GitHub mirrors: keep project context available for ChatGPT analysis and Codex execution.

A package manager for Agent Skills with search, install, versioning, and lockfiles.

Claude skill for OneLogin SSO/SCIM setup, benchmarked: 100% with-skill vs 50% without on the same rubric. Full eval harness and transcripts included.

Outcome-owned Codex Skill for multi-agent research, planning, execution, model routing, verification, cold review, and release-ready delivery.

linkedin-boost — Claude skill for every LinkedIn surface — feed, search, recruiter sourcing, applicant ranking — built from LinkedIn Engineering's published mechanism, and explicit about which popular rules are folklore.

name: radar-install

AI agent skill that turns any idea into a rigorous mathematical model: decomposition, parameter tables, multi-perspective modeling, validation code

Strict plan + independent auditor Agent Skill — verifies AI agent work with real command evidence, never trusts the agent's report

Manage your personal finances offline with Poka CE, a simple, open-source Flutter app that keeps your data yours.

每天自动送达的 AI 日报 Agent Skill：12 源采集 + LLM 筛选摘要，落地飞书表格/机器人推送/云文档归档

Turn any CV into a researched, bilingual Excel shortlist of top-fit companies with salaries, scores, and next steps.

Teach AI assistants eight reusable skills for studying, presentations, customer service, browser handoffs, and privacy.

A Claude Code plugin with two loops: a gate-verified pipeline that migrates legacy .NET applications with RoselineMCP, and a hands-off GitHub issue → PR lifecycle (create-issue, implement-issue, merge-pr, auto-dev) that runs on any repository through one committed profile.

📐 Python SDK for agent evals and skill routing — measure a skill's real lift before you trust it

Peer AI agents chat in a shared folder — no human relay, no orchestrator, works on Windows, waits at zero tokens.

Bulgarian payroll (ТРЗ) audit skill for Claude Code and GitHub Copilot — checks ведомости against КТ, КСО, ЗДДФЛ and НСОРЗ

Description Evidence-driven evaluation, benchmarking, and verified repair for Agent Skills across Codex, Claude Code, Gemini CLI, and Antigravity.

A reusable Codex skill for structured A-share industry analysis

Elenchus: a Korean Codex skill for deep interviews, optional research, and agreed execution plans.

Reusable Codex skill for organizing Canvas courses, assignments, required readings, and alerts in Notion

Codex skill for reviewing China A-share trades with public market data, Chan theory, and fee-aware journaling.