Agent Skills
Method-driven agent skills for knowledge work: strategy, research, critical thinking, data analysis, docs, slides. Works with Claude Code, Codex, Cursor and any…
Install: /plugin marketplace add tronghieu/agent-skills
Works with Claude Code, Codex, Cursor · 78 GitHub stars
Install
/plugin marketplace add tronghieu/agent-skillsInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →Agent Skills
Language: English | Tiếng Việt | 中文
A collection of method-driven skills for people who use AI to make decisions, run projects, analyze evidence, create documents, and produce finished work. These skills are designed for active collaborators: you provide the real context and remain responsible for the decision; the agent supplies structure, analysis, and quality checks.
Quick start
Install the full collection:
npx skills add tronghieu/agent-skills
Or install as a Claude Code plugin:
/plugin marketplace add tronghieu/agent-skills
/plugin install agent-skills@tronghieu-skills
Then invoke a skill in your agent:
/market-researcher Assess the market for this product idea in Vietnam.
Most agent tools use slash commands. Codex and ChatGPT use $; in those tools, replace the leading / with $.
Choose a skill
| Your job | Start with |
|---|---|
| Generate or challenge ideas | brainstorm-coach, critical-thinking |
| Diagnose a recurring problem | problem-solver |
| Understand customers or markets | design-thinking, market-researcher |
| Decide what to build and deliver it | product-manager, project-manager |
| Run software sprints and improve team process | scrum-master |
| Analyze data or long documents | data-scientist, deep-reader |
| Make a high-stakes business decision | strategy-board |
| Create documentation, prompts, slides, or fiction | diataxis-writer, system-prompt-creator, slidewright, fiction-studio |
| Learn through guided questions | socratic-questor |
| Compare CVs with a job description | cv-scorer |
| Understand what an autonomous coding run did, or why it stalled | bmad-run-inspector |
| Test a running app by hand and prove what you saw | manual-tester |
Skills
bmad-run-inspector
For anyone running bmad-loop, an autonomous coding orchestrator, who needs an honest read on a run — watching one in progress or investigating one that finished, failed, or paused overnight. Only useful inside a project that already runs bmad-loop.
npx skills add tronghieu/agent-skills --skill bmad-run-inspector
Read the bmad-run-inspector guide
brainstorm-coach
For founders, product teams, marketers, creators, and anyone who needs to generate options before evaluating them.
npx skills add tronghieu/agent-skills --skill brainstorm-coach
Read the brainstorm-coach guide
critical-thinking
For decision-makers, analysts, and writers who need to inspect the claims, evidence, assumptions, and logical gaps in a document.
npx skills add tronghieu/agent-skills --skill critical-thinking
Similar plugs
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local…
Why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
Production-grade engineering skills for AI coding agents.
The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create prototypes, websites, apps, dashboards, presentations, images, and videos with your team…