Skills
The seven skills I run every day as an AI product lead: sharpen the idea, gate it before code, then audit the module, the screen and the bundle. Built on measurement rather than guesswork.
Install
Claude Code, as a plugin (updates arrive automatically):
/plugin marketplace add giraybatiturk/skills
/plugin install giraybatiturk-skills@giraybatiturk
Codex and other agents, or an editable copy:
npx skills@latest add giraybatiturk/skills
Plugin skills are namespaced by Claude Code (/giraybatiturk-skills:real-grill). For the short /real-grill form, link the skill folders into ~/.claude/skills; the README shows the one-liner.
Get oriented
Three stages. Between gate and audit you build with your own flow; Claude Code's code review, TDD and debugging skills already cover it.
- idea
/real-grillinterview until nothing is silently assumed; --docs leaves ADRs and a glossary - gate
/real-feature-gatefive headings, eight scenario classes, approval; no code yet - audit
/real-module-audit → /real-design-audit → /real-perf-auditmodule, screen, bundle; in that order
Idea and gate stay in one context window. A fact you need on the way: /real-research. Any UI work picks up real-design-rules on its own.
Featured
/real-feature-gate opens in a new tabRuns BEFORE any code for a new feature. Discovers intent, measures what exists today, and puts scenarios plus five scope headings up for approval. No file is opened until the user approves.
/real-module-audit opens in a new tabAudits a built feature or module against user scenarios. Finds the missing cases by MEASURING the code and the backend contract; produces scenarios in eight classes, a permission matrix, and a priority order.
/real-design-audit opens in a new tabAudits one screen against the project's DESIGN.md from a screenshot plus the code, scores it across 9 dimensions, and fixes on approval. Runs when a screen is done.
real-grill opens in a new tabGrill the user relentlessly about a plan, decision, or idea until nothing is silently assumed. Use when the user wants to stress-test their thinking or says 'grill'. With `--docs`, also writes ADRs and a glossary as decisions settle.
The skill set
Product gate and audits
Runs BEFORE any code for a new feature. Discovers intent, measures what exists today, and puts scenarios plus five scope headings up for approval. No file is opened until the user approves.
Audits a built feature or module against user scenarios. Finds the missing cases by MEASURING the code and the backend contract; produces scenarios in eight classes, a permission matrix, and a priority order.
Measures bundle and load performance against a budget, finds where an overrun comes from, and applies the fix recipes. Runs when a dependency is added and before release.
Design
Audits one screen against the project's DESIGN.md from a screenshot plus the code, scores it across 9 dimensions, and fixes on approval. Runs when a screen is done.
Binding baseline rules for any UI work (token discipline, forms, states, accessibility, UX writing). Load for any screen, component, form or visual task. The project's own DESIGN.md takes precedence.
Engineering
Grill the user relentlessly about a plan, decision, or idea until nothing is silently assumed. Use when the user wants to stress-test their thinking or says 'grill'. With `--docs`, also writes ADRs and a glossary as decisions settle.
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
A leading slash means you type it; no slash means the model picks it up when the topic matches.
Source: github.com/giraybatiturk/skills opens in a new tab · v0.5.0 · 2026-09-09 · /real-grill and /real-research adapted from mattpocock/skills (MIT) opens in a new tab