What it does
This repo is a collection of 37 skills
- Connects Instruction files the AI reads, with steps that call an outside service
- Account or key Some steps need a key for DEEPSEEK_API_KEY, OpenAI, QWEN_API_KEY, Anthropic, Google Gemini, MOONSHOT_API_KEY (per the README)
- Category Coding
Maker’s original description
Poirot is a deep research agent kernel built for those who care about how agents are architected.For makers: add a badge to your README
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/hezaohezao-poirot)Use together with
MCP servers that connect the AI to services for the same work
Fallow
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
Desktop Commander
MCP server for terminal commands, file operations, and process management
Similar Skills
Same kind of work, ordered like the Skills list
| This one poirot | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| Maker | HezaoHezao | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skills | 37 | 1 | 1 | 1 | 1 |
| GitHub stars | 261 | 468,733 | 234,332 | 150,287 | 144,566 |
| Last code change | Jul 29, 2026 | Nov 19, 2026 | Apr 20, 2026 | Nov 18, 2026 | Nov 18, 2026 |
| License | MIT | MIT | – | Apache-2.0 | MIT |
37 skills (instruction sets) by HezaoHezao that an AI reads and follows · not an MCP server
Pick the skill to install
Install only the ones you use. Open a skill to see how to install it
This set has 37 skills, too many to install at once: every installed skill’s description loads into every chat, so the AI picks the wrong one more easily. Pick only the ones you use from the list below
- academic-paper-review
Structured peer-review of academic papers.
- architecture-diagram
Dark-themed SVG architecture/cloud/infra diagrams as HTML.
- arxiv
Search arXiv papers by keyword, author, category, or ID.
- blogwatcher
Monitor blogs and RSS/Atom feeds via blogwatcher-cli.
- bootstrap
Onboarding conversation to generate a user profile.
- chart-visualization
Generate charts: select type, extract data, render image.
- code-documentation
Generate docs: README, API reference, architecture, guides.
- codebase-inspection
Inspect codebases: LOC, languages, ratios via pygount.
- concept-diagrams
Minimal SVG diagrams as standalone HTML files.
- consulting-analysis
Consulting-grade research reports: framework + final report.
- data-analysis
Analyze Excel/CSV files with DuckDB SQL via bash.
- deep-research
Systematic multi-angle web research methodology.
- find-skills
Discover available skills in the builtin library by keyword.
- frontend-design
Create distinctive, production-grade frontend interfaces.
- github-auth
GitHub auth setup: HTTPS tokens, SSH keys, gh CLI.
- github-code-review
Review PRs: diffs, inline comments via gh or REST.
- github-deep-research
Multi-round deep research on any GitHub repo via API.
- github-issues
Create, triage, label, assign GitHub issues via gh or REST.
- github-pr-workflow
GitHub PR lifecycle: branch, commit, open, CI, merge.
- github-repo-management
Clone, create, fork repos; manage remotes, releases.
- newsletter-generation
Research and write professional newsletters.
- node-inspect-debugger
Debug Node.js via --inspect + Chrome DevTools Protocol.
- osint-investigation
Public-records OSINT: SEC, sanctions, courts, property.
- plan
Plan mode: write markdown plan, no execution.
- ppt-generation
Generate PPTX presentations from slide plan + content.
- python-debugpy
Debug Python: pdb REPL + debugpy remote (DAP).
- requesting-code-review
Pre-commit review: security scan, quality gates, auto-fix.
- research-paper-writing
ML paper pipeline: experiment design to submission.
- simplify-code
Sequential 3-lens cleanup of recent code changes.
- skill-authoring
Author SKILL.md: frontmatter, structure, writing principles.
- skill-creator
Create, edit, and evaluate agent skills iteratively.
- source-verification
验证信源可信度的研究过程知识,指导 agent 在涉及事实声明时交叉核验信源
- spike
Throwaway experiments to validate an idea before build.
- subagent-driven-development
Execute plans task-by-task with two-stage review.
- systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
- systematic-literature-review
Systematic literature review across multiple arXiv papers.
- test-driven-development
TDD: enforce RED-GREEN-REFACTOR, tests before code.
How a Skill differs from MCP
MCP = the hands
Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.
Skill = the manual
A text file that teaches the AI how to do a task. It connects to nothing.
Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.
Works with
Codex
From the maker’s README and the folders in the repo
Install
Pick a skill first
This repo has 37 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP
Discussion
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
From GitHub
- GitHub stars
- 261
Stars are for the whole repo, not each skill - Maker
- HezaoHezao
- License
- MIT
- Last code change
- Jul 29, 2026
- SKILL.md files in the repo (including translated copies and templates)
- 37
- Topics
- agent, agent-memory, agent-skill, agent-skills, agentic-ai, agents, ai-agent, ai-agents, ai-coding, memory, memory-system, multi-agent