debt-audit
Run all five debt dimensions (code, doc, test, dep, design) and synthesize a cross-cutting report. Surfaces systemic hotspots — modules with debt in multiple dimensions. Use when planning a tech-health effort or preparing for a major release.
What this skill does
# Debt Audit
Run every debt dimension and find the places where debt compounds.
## Philosophy
> "Where does our debt concentrate, and what's the single highest-leverage place to repay?"
Running each dimension separately is fine, but patterns emerge only when you look across them. A module flagged by code-debt, test-debt, AND design-debt isn't three separate problems — it's one neglected area. The umbrella's job is surfacing that.
## Scope
User may specify a path, glob, or directory. Whole-project scans are valid but can be long. If not specified, ask: *"Which directory should the audit cover? (Project root is fine for small codebases; a subsystem for larger ones.)"*
## Config Integration
Follow `references/config-migration.md` for preflight.
Read `.assistant-config.md` for:
- **Debt Scope** — any dimensions permanently out of scope
- **Acknowledged Debt**
## Dimension Selection
Before running, show the user the five dimensions and allow per-run exclusion via `AskUserQuestion`:
> Will check: code, doc, test, dep, design. Exclude any for this run? (none / list)
Respect `.assistant-config.md` **Debt Scope** exclusions as defaults.
## Process
### 1. Run each dimension
For each selected dimension, invoke the dimension skill via the `Skill` tool, passing the same scope:
- `code-debt <scope>`
- `doc-debt <scope>`
- `test-debt <scope>`
- `dep-debt <scope>`
- `design-debt <scope>`
Capture each sub-report as text.
### 2. Parse sub-reports
For each report, extract (per the parsing contract in `references/debt-output-format.md`):
- Dimension name
- Every `file:line` entry under `### Findings`
- The single Impact/Effort/Priority triple per location group
- Each Ready-to-file item as a complete block
Build a **location map:**
```
{
"src/auth/handlers.ts": {
"code": [...findings],
"test": [...findings],
"design": [...findings]
},
"src/orders/": {
"dep": [...findings]
}
}
```
### 3. Score hotspots
- **Systemic hotspot:** any location appearing in three or more dimensions.
- **Deep debt zone:** any location with five or more findings in one dimension.
### 4. Surface themes
Prose summary of cross-cutting patterns. Examples:
- "The `auth/` module has unresolved TODOs from 2024, two skipped tests, and inconsistent error handling — this is your highest-debt area."
- "Dep debt concentrates in legacy packages (`request`, `moment`); addressing those would cover most of this dimension."
- "Design drift shows up mostly in handlers; the services layer is consistent."
### 5. Prioritize
Top ten items across all dimensions, ranked by a combined score:
- Impact (H=3, M=2, L=1)
- Priority (P2=3, P3=2, P4=1)
- Hotspot bonus: +2 if the location is a systemic hotspot
Break ties by lower Effort first (S before M before L).
## Output format
```markdown
## Debt Audit: <path>
**Config loaded:** .assistant-config.md
**Dimensions run:** code, doc, test, dep, design
**Dimensions skipped:** <none or list>
### TL;DR
<Two or three sentences: total count, top hotspot, recommended first move.>
### Systemic hotspots
<Locations with debt in three or more dimensions. For each, name the dimensions and the top finding. If none, state that.>
**<location>** — flagged by <dimensions>
- <top finding per dimension>
### Top 10 items (across all dimensions)
1. **[<dimension>] <Title>** — Impact <H/M/L> · Effort <S/M/L> · Priority <P>
- Location: `<file:line>`
- Why: <one-line rationale>
- Ready-to-file: <see sub-report or include inline>
(Items 2-10)
### Per-dimension summary
| Dimension | Findings | Top item |
|---|---|---|
| Code | <n> | <one-line> |
| Doc | <n> | <one-line> |
| Test | <n> | <one-line> |
| Dep | <n> | <one-line> |
| Design | <n> | <one-line> |
### Full per-dimension reports
For full findings, re-run the individual skill:
- `/code-debt <scope>`
- `/doc-debt <scope>`
- `/test-debt <scope>`
- `/dep-debt <scope>`
- `/design-debt <scope>`
Sub-reports are NOT duplicated here. The cross-cutting view above is the umbrella's value.
```
## What Makes This Different From Running Each Skill Separately
Running each skill gives you five lists. The umbrella gives you:
1. The **same finding seen from multiple angles** (a hotspot)
2. The **shortest path to impact** (top ten, ranked across dimensions)
3. A **story about the codebase**, not just a catalog
If a user wants the raw catalog, they can run each skill directly. The umbrella is for *deciding where to start*.
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.