Research & Data

Shepherd is a Rust-native development platform that supervises AI coding agents (Claude Code, Codex) and verifies requirement completeness—》HumanInTheLoop

Universal data-source assistant. Use this skill when the user wants external structured data such as stocks, financial reports, technical indicators, A-share/HK/US markets, global macroeconomics, Chinese enterprise registry information, arXiv papers, Google Scholar results, or Chinese laws/regulations and judicial cases. This plugin exposes tools via MCP server `plugin-kimi-datasource_data`; call them in the flow `mcp__plugin-kimi-datasource_data__get_data_source_desc` → `mcp__plugin-kimi-datasource_data__call_data_source_tool`.

Apply a senior-analyst reasoning discipline: reconstruct the real request, find the load-bearing assumption, verify against the actual artifact instead of pattern-matching, keep uncertainty visible, lead with the conclusion, and try to break the answer before delivering it. Use for ANY non-trivial task — analysis, debugging, planning, decisions, code, math, research, review, or writing that must be right — and especially when the user says "think carefully," "double-check," "be rigorous," or "are you sure," or when they will act on the answer without verifying it themselves. If being wrong would cost the user real time, money, or credibility, apply this skill even if they didn't ask.

Use when implementing, integrating, upgrading, debugging, or answering anything involving third-party APIs, libraries, frameworks, CLIs, cloud services, model/provider SDKs, fast-moving product behavior, user requests for latest/current/official behavior, unfamiliar repo docs/specs, errors that may indicate API drift, or high-stakes auth, security, billing, data, migration, deployment, compliance, or privacy behavior. Forces Codex to web-search for current official docs and read primary docs before assuming from memory.

Debug like Fable 5 — systematic root cause analysis with natural reasoning flow. Use this skill when you encounter an error, unexpected behavior, failing tests, or anything that does not work as intended.

Apply the same orchestration as `/efficient-fable` to any high-cost frontier model: delegate research, coding, and testing to cheaper subagents while keeping planning, synthesis, and final review with the expensive model.

Use when running Claude Fable on codebase-heavy or token-heavy work and the user wants Fable to orchestrate research, coding, and testing while cheaper subagents do bounded heavy lifting.

Codex Skill for scope-controlled security penetration testing, vulnerability scanning, evidence capture, reporting, and retesting.

AI agent skill for Solace PubSub+ estate management — inventory, topology, health monitoring, consumption chargeback, and security posture analysis via SEMP v2. Read-only, safe for production.

城市更新案例研究与小红书内容生产 Skill | A Codex skill for urban-renewal research and Xiaohongshu publishing.

Reusable Codex skills for empirical economics and management research workflows

Evidence-aware literature research workflow and reusable Codex skills for economics, finance, and management research

A Codex skill for QA-first research coding, goal-oriented loops, and anti-drift handoff.

Codex skill: prevent garbled characters in Chinese PDF generation with ReportLab

A security scanner for Agent Skill packages. Skill Sentinel uses multi-agent AI analysis to detect prompt injection, data exfiltration, command injection, malware, and other threats hiding in skill packages for Cursor, Claude Code, Codex, and OpenClaw.

Citation-first Codex Skill for official sources, public X conversations, and current social research.

Codex skill that analyzes frontend and backend Git changes and generates prioritized test scope

A collection of AI agent skills relevant to analysis and development of R/Bioconductor packages + statistical and bioinformatic analysis

六爻占卜 AI Agent 技能 + Python 排盘引擎｜纳甲·六亲·暗动·墓库·三合·应期，含完整断卦方法论与验证卦例

Experimental library for discovering, validating, and sharing reusable Agent Skills / 用于发现、验证和共享可复用 Agent Skills 的实验仓库

Reproducible, auditable R pipeline for cleaning sleep-diary (EMA) data — configurable corrections, sleep metrics (TST/SOL/WASO/SE), and 27 QC figures, with a schema-validated config and a human-in-the-loop review trail.

Autonomous multi-batch development skill for Claude Code and Codex. They work while you sleep.

Search WeChat public account articles by keyword via Sogou WeChat Search. Returns structured JSON — no API key required.

Setup and use Bedrock AgentCore Web Search on your local AI IDE with skills