Skill Claude CodeCodex
Generate a new dragoon skill scaffold (SKILL.md, scripts/ .js, test/ .test.js, README.md) into .dragoon/forge/ / for review. dragoon does NOT auto-install forged skills. After review, copy into /.dragoon/skills/ and add an entry to bin/dragoon's COMMANDS map. Use to extend the pack with custom skills. Run as node…
Skill Claude CodeCodex
Declare directories that are off-limits to edits. Stores the list in .dragoon/freeze.json. Optionally installs a git pre-commit hook that fails the commit if any frozen path is touched. Subcommands list/add/remove/hook/check. Use when isolating a refactor, locking legacy directories, or onboarding a contributor with…
Skill Claude CodeCodex
Generate a markdown dev handoff doc with everything the next engineer needs - stack, design tokens, palette, type scale, spacing grid, motion, existing components, and conventions - all pulled from dragoon.json. Use when handing off work to another engineer or documenting the codebase for new contributors. Output goes…
Skill Claude CodeCodex
One-line install for dragoon. Detects supported coding agents (claude-code, codex, cursor, opencode, factory, kiro) and installs the skill pack into each. Multi-host on day one. Use when the user wants to install dragoon, mentions setup, or asks how to add dragoon to their environment. The install script is ./setup at…
Skill Claude CodeCodex
Catalog of components (PascalCase files), hooks (useFoo), pages/routes, story files, and token files in the codebase. Use to understand what already exists before adding more, or to audit a design system. Heuristic-based, no AST. Run as node /.claude/skills/dragoon/skills/inventory/scripts/inventory.js [root].
Skill Claude CodeCodex
Structured root-cause investigation template. Encodes the rule "no patches until you can reproduce, predict, and explain the bug." Forces hypothesis-test pairs, evidence collection, and a prevention plan. Use when the user reports a bug or asks to fix something they don't fully understand yet. Run as node…
Skill Claude CodeCodex
Post-merge sanity check. Verifies branch, HEAD sha, that local matches remote, and that the working tree is clean. dragoon does NOT trigger deploys (platform-specific creds out of scope). Use right before a deploy step in CI or before manual prod pushes. Exits non-zero if any check fails. Run as node…
Skill Claude CodeCodex
Architecture overview of the codebase. Reports total file/line/byte counts, top hot files (most imported), largest files by line count, orphan files (imported by nobody), and most-used external dependencies. Pure regex on import statements, no AST. Use to understand a new codebase, find dead code, or audit dependency…
Skill Claude CodeCodex
Small persistent key-value store at .dragoon/memory.json for project-specific facts dragoon (and the user) want to remember across sessions. Subcommands list/get/set/remove/clear. Keys are lowercase ascii (.//-, max 64). Values are plain text (max 8KB, max 256 keys). Use to remember conventions, decisions, gotchas.…
Skill Claude CodeCodex
Generate motion tokens (durations + easings) using values detected by /scan, falling back to material-quality defaults when nothing was detected. Produces fast/normal/slow durations and standard/enter/exit easings. Use when the user wants to formalize motion tokens or scaffold a motion system. Defaults to dry-run…
Skill Claude CodeCodex
Static performance hints (large images, missing img dimensions, no loading=lazy, sync script tags) plus optional Lighthouse JSON report ingestion that surfaces failing audits ranked by potential ms savings. Use when the user wants to audit web performance or process a Lighthouse report. Dragoon does NOT run Lighthouse…
Skill Claude CodeCodex
Generate a structured design plan markdown that respects the constraints in dragoon.json (spacing grid, type ratio, palette, font families). Forces a screens-and-flows breakdown, accessibility plan, responsive plan, and design review checklist gated on /critique and /slop. Use after /brief or before any UI work.…
Skill Claude CodeCodex
Generate a structured engineering plan markdown for an idea, pre-filled with codebase facts (stack, dependencies, current critique score) from dragoon.json. Forces a test matrix, edge cases, migration plan, and review checklist. Use after /brief or before any non-trivial feature implementation. Output goes to…
Skill Claude CodeCodex
Scaffold a playwright e2e test suite with 4 smoke tests (page loads, h1 visible, no console errors, no broken images). Detects the project's stack to set the right baseURL. Writes a runner script that installs browsers on first run. Dragoon does NOT install browsers itself - the runner script does. Defaults to…
Skill Claude CodeCodex
Generate a structured research template for a topic. Use before deciding to build something - forces specific decision-driven research with sources, expert disagreement, and a steelman. dragoon does NOT fetch the web. Output goes to .dragoon/research/research-{slug}-{date}.md. Run as node…
Skill Claude CodeCodex
Weekly retro markdown template with git stats pre-loaded (commit count, files changed, +/- lines, contributors). Forces a what-shipped, what-slipped, what-we-learned, what-to-do-less-of, what-to-do-more-of, and quality-trends section. Use end-of-week or end-of-sprint. Output goes to .dragoon/retros/retro-{date}.md.…
Skill Claude CodeCodex
Unified code + design review in a single pass. Runs slop detection, design critique, and engineering signals (TODO/FIXME, any types, large files) at once. On any UI files in scope (jsx/tsx/vue/svelte/css/scss/html), /critique and /slop run automatically - engineering review and design review in one read. Use when the…
Skill Claude CodeCodex
Fingerprint a codebase's design DNA and write dragoon.json. Use when the user wants to set up dragoon in a project, or asks to "scan", "fingerprint", or "analyze" the design system. Always run this first before /critique, /slop, or /review on a project that hasn't been scanned yet. Outputs detected stack, palette…
Skill Claude CodeCodex
Build a structured packet to paste into another model or share with a colleague. Includes branch, head, recent commits, and optional file contents (max 5 files, 200 lines each). dragoon does NOT call other models for you - this is the prompt you copy. Use when stuck on an approach, considering tradeoffs, or wanting…
Skill Claude CodeCodex
Pre-PR check orchestrator. Runs /critique with a threshold (default 80), /slop --severity high, gathers git context (branch, changed files), and optionally opens a PR via the gh CLI. Use before opening any PR. Exits non-zero if any check fails. Run as node /.claude/skills/dragoon/skills/ship/scripts/ship.js.
Skill Claude CodeCodex
Detect AI-generated design slop with concrete, locatable findings. Use when the user wants to check code for AI authorship tells, design inconsistency, or generic UI patterns. Each finding includes file, line, column, the offending snippet, why it's a problem, and a concrete fix. 12 rules covering shadow/radius…
Skill Claude CodeCodex
Generate a spacing scale token file based on the spacing grid detected by /scan (4px, 8px, etc). Produces an 8-step t-shirt scale (xs/sm/md/lg/xl/2xl/3xl/4xl) anchored on the grid. Use when the user wants to formalize spacing tokens or scaffold a layout system. Defaults to dry-run; pass --apply to write. Run as node…
Skill Claude CodeCodex
Scaffold storybook config (.storybook/main.ts, preview.ts) plus auto-generated .stories.tsx files for every PascalCase component in the codebase that has a matching named export. Caps at 50 components per run. dragoon does NOT install storybook - run npx storybook init after. Use to bootstrap stories quickly across an…
Skill Claude CodeCodex
Export design tokens to figma.tokens.json (tokens-studio-compatible format) so they can be imported into the Figma "tokens studio" plugin. dragoon does NOT live-sync with Figma - that requires OAuth and the Figma REST API. Use for one-way export from code to Figma, manually re-run after major token changes. Run as…