Agent Skills (tronghieu) plugin
A collection of skills for decisions and projects: strategy, market research, thinking, data analysis, docs and slides.
- 107 ★ on the repository
- Last commit
Minimal access
Why this level
- The skills contain instructions and run nothing by themselves.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add plugins/agent-skills-tronghieuDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skills contain instructions and run nothing by themselves.
This is third-party code. Review the repository files before installing.
What it does
A set of method-driven skills for people who decide with AI, run projects, analyze evidence and produce finished materials. The person brings real context and owns the decision, while the agent supplies structure, analysis and quality checks. Skills are invoked with a slash command, such as `/market-researcher Assess the market for this idea in Vietnam`, and in Codex and ChatGPT the slash becomes `$`. Skills include `brainstorm-coach` and `critical-thinking` for ideas, `problem-solver` for recurring problems, `design-thinking` and `market-researcher` for customers and markets, `product-manager`, `project-manager` and `scrum-master` for delivery, `data-scientist` and `deep-reader` for data and long documents and `strategy-board` for high-stakes decisions. There are skills for Diataxis documentation, system prompts, slides, fiction, comparing CVs with a job description and `bmad-run-inspector` for analyzing autonomous runs.
Who it is for. Product and project managers, founders and analysts who want structured methods instead of the agent's generic advice.
Good fit when
- You need to assess the market for a product idea in a specific country.
- A decision is expensive and should be examined in the `strategy-board` skill's strategy session.
- A team runs sprints and wants to improve its process through `scrum-master`.
- A long document has to be read deeply and its arguments extracted.
Not a fit when
- The task is one narrow operation and a general skill would only complicate it.
- You want a decision made for you; the skills leave responsibility with you.
- Texts and analysis would run without your real context.
Example request
/market-researcher Assess the market for an expense-tracking app in Vietnam and name three sources to verify.Limitations
Skills work with the context you provide, so conclusions about markets, strategy and data need checking against real sources. Part of the README also exists in Vietnamese and Chinese. Installing the whole collection with `npx skills add` puts many skills into the project at once, while in the Claude Code plugin they are available under one name. The `cv-scorer` skill compares a CV with a job description: a human must check candidate scores, and decisions should not rely on them without your review. The `bmad-run-inspector` skill analyzes traces of autonomous runs and matters only if you use the corresponding method.
How to disable. Remove the plugin through `/plugin` or delete the skill folders from the agent's skills directory.
FAQ
How do I install the whole collection?
Run `npx skills add tronghieu/agent-skills`. For Claude Code there is a plugin: `/plugin marketplace add tronghieu/agent-skills` and `/plugin install agent-skills@tronghieu-skills`.
How do I invoke a skill?
With a slash command naming the skill and the task, such as `/market-researcher ...`. In Codex and ChatGPT the `/` becomes `$`.
Where do I start if I need an idea?
With `brainstorm-coach` to generate and `critical-thinking` to challenge ideas. For a recurring problem `problem-solver` fits better.
What is bmad-run-inspector?
A skill for analyzing an autonomous coding run: what it did and why it stalled. It also ships as a separate ZIP in the `skills/` folder.
Does a skill make decisions for me?
No. By the set's description you provide real context and own the decision, while the agent adds structure, analysis and quality checks.
Discussion
No questions or reviews yet.
Related
Pluginscafe3310's personal skill collection: spec-driven project work, reviews, reports, browser, 3D and video in one repository
18 portable skills for work where AI is weakest: messy voice input, message tone, small trend tests and safe shipping.
A set of 13 SKILL.md skills: research, a product doc, decks, articles and audits for any compatible agent
ProductMind Skills gives an agent 17 skills where the product decision comes before code: feature vetting, MVP or SLC, pricing.
A set of skills that turn an AI agent into a tutor built on cognitive science, from school to career and social skills
A set of business, marketing, UX and code skills based on well-known books, plus step-by-step metaskill journeys
README in short
A collection of method-driven skills with a Claude Code plugin and a one-command install for other agents.