Research & Data

GitHub quota/cache hygiene: gh, ghx, xcache, gitcrawl, mirrors, limits.

ClawSweeper status: URLs, workflow health, active workers, ops snapshot.

GitHub deep review: bugs, PRs, best fix, stale-or-real, read code first.

ClickClack ops: chat app, Hetzner deploy, DNS/docs/app, Docker rollout.

Instruments/xctrace profiling: macOS/iOS traces, binaries, args, exports.

GitHub issue/PR triage: queues, CI, blockers, risk, proof, next actions.

A Codex skill for Sunzi-style strategic analysis.

A Codex skill for source-backed research dossiers and research report drafts

Personal Claude skills for epidemiology, statistics,and public health research

MCP connector that recommends and installs Claude skills from a scraped skill database

Gaia is a living, open registry of every AI agent skill in existence — structured as a leveling skill graph. Basic skills combine into Extras, Extra Skills evolve into Ultimates. Fork it, extend it, PR a fusion. The complete skill frontier of AI agents, mapped and growing.

A growing collection of Agent Skills for Claude Code — first up: postmortem-analyst, agentic incident analysis over 243 real-world postmortems

A Codex skill for Git-first research project setup, remote sbatch workflows, literature grounding, and result retrieval.

Agent Skill for Claude Code: incident precedent & failure-pattern analysis over 243 real-world postmortems (danluu/post-mortems), with nested agent fan-out workflows

Recently updated agent-skill-related GitHub repository: GRIND-Lab-Core/night_owl_research_agent.

A Codex skill for rational consumer product evaluation, source-aware research, market-regime analysis, and purchase timing decisions.

Production-ready enterprise document knowledge base (DOCX/PDF/PPTX) with structure-preserving Docling parsing, metadata-complete semantic chunking, and hybrid Dense+BM25/RRF retrieval, exposed as a Remote MCP Server (FastMCP). Includes a reusable document-preprocessing Claude Skill. Deployed on Zeabur (ARM64, CPU-only).

Multi-agent skill for extracting X/Twitter KOL outreach data at scale. Supports Codex, OpenClaw, Hermes and other agents. Deep-scrolls profiles, samples recent original/quote posts, calculates average impressions, and exports Excel plus Feishu/Lark-ready TSV tables.

Codex skill for Polymarket sports betting analysis, whale flow, EV/CLV strategy, and confirmed order workflow

Codex skill for generating self-contained interactive HTML study cards from notes, formulas, code, and learning materials.

Collection of Claude Agent Skills for IT students and professionals: document formatting, analysis, automation, and workflow optimization tools built with custom prompting patterns

A curated bundle of 18 Claude Skills for quantitative research in business, finance & social science (bilingual 中/EN)

YLF agent skills for disciplined coding tasks and persistent project instructions

Detect, analyze, and eliminate flaky tests across any test runner. An AI agent skill that identifies non-deterministic test failures, categorizes root causes, and applies targeted fixes.