Skip to main content
NeVibeCode · repository · 18 items

agent-skills: a set by tronghieu

The tronghieu/agent-skills repository on GitHub: 18 cards with a description and an install command. They work in Claude Code, Codex, Cursor — 8 platforms in total.

About the repository

GitHub
tronghieu/agent-skills
Stars
★ 117
License
MIT
Source updated
2026-10-18
In the catalog since
2026-10-26
strategy-board skill strategy-board runs a virtual C-level advisory board of specialized AI personas to analyze business decisions, pressure-test assumptions, and build executive decks. CX Codex +1 ★ 117repo stars socratic-questor skill socratic-questor is a skill that guides learning through questions, helping explore concepts, test understanding, or discuss a document. CX Codex +1 ★ 117repo stars slidewright skill slidewright turns a talk into a website of slides meant for a projector, with one presenter driving. Pick a single HTML file or a Vite + React project. CX Codex +1 ★ 117repo stars scrum-master skill scrum-master runs sprint planning, monitors blockers, and tracks retrospective actions directly in project files. Keeps agile habits intact without faking velocity metrics. CX Codex +1 ★ 117repo stars project-manager skill project-manager is a Claude Code skill for managing projects from goals to results, with plans, date estimates, risk tracking, status reports, and change decisions. It keeps records in _project/ across sessions. CX Codex +1 ★ 117repo stars product-manager skill product-manager — a skill that turns data and assumptions into production artifacts: PRDs, backlogs, metrics, OKRs, and launch plans. Works as a persistent PM workspace that remembers every decision and rejects fabricated numbers. CX Codex +1 ★ 117repo stars problem-solver skill problem-solver structures root-cause analysis for unexplained failures, bugs, and metric drops. Separates verified facts from working assumptions before suggesting any fix. CX Codex +1 ★ 117repo stars market-researcher skill The market-researcher skill researches market size, competitors, and demand signals using cited sources. Use it to assess a launch decision or explore a market before committing to deeper research. CX Codex +1 ★ 117repo stars manual-tester skill manual-tester runs manual testing sessions against your running app: exploratory, verification, smoke, UX and localization review, AI answer probes. CX Codex +1 ★ 117repo stars fiction-studio skill fiction-studio runs a virtual writers' room with specialist agents for creative prose. It guides authors from an initial premise to a finished manuscript. CX Codex +1 ★ 117repo stars diataxis-writer skill diataxis-writer is a Claude Code skill that writes, restructures, and reviews documentation using Diataxis, separating learning, task steps, reference, and explanation. CX Codex +1 ★ 117repo stars design-thinking skill design-thinking walks a project through Empathize, Define, Ideate, Prototype and Test while keeping every claim about users tied to real evidence. Useful when churn or unmet needs have no clear cause. CX Codex +1 ★ 117repo stars deep-reader skill deep-reader reads books and papers over 50 pages using chapter notes without blowing the context window. Creates an anchored workspace with verified citations. CX Codex +1 ★ 117repo stars data-scientist skill data-scientist is a Claude Code skill that explores datasets, tests hypotheses, and builds predictive models. It activates for data analysis, experiments, and reviews of existing work. CX Codex +1 ★ 117repo stars cv-scorer skill cv-scorer scores candidate CVs against a job description and returns a number out of 100. Handy when a stack of applications needs sorting. CX Codex +1 ★ 117repo stars critical-thinking skill critical-thinking audits arguments in memos, proposals, and draft documents. It identifies logical leaps and asks for your own judgment before revealing findings to keep your thinking sharp. CX Codex +1 ★ 117repo stars brainstorm-coach skill brainstorm-coach guides a brainstorming session from open-ended idea generation to priorities and next steps. Use it to think through a topic with an AI agent. CX Codex +1 ★ 117repo stars bmad-run-inspector skill bmad-run-inspector reads bmad-loop run artifacts from .bmad-loop/runs/ — logs, journals, task state. Answers live questions about what the agent is doing and explains what went wrong in past runs. CX Codex +1 ★ 117repo stars

More in NeVibeCode

Project sponsors

Companies that keep this analytics open