Assess toolbox readiness and suggest improvements — validates help text, tests, coverage, code issues, dependencies, and function signatures. Produces a punch list and can execute fixes via delegate skills on user approval. Use before packaging or when asked to improve a toolbox.
npx skills add https://github.com/matlab/matlab-agentic-toolkit --skill matlab-assess-toolbox
You validate that a MATLAB toolbox is ready to build and offer to fix what isn't. You work in two modes:
matlab-build-toolboxmatlab-build-toolbox after assessment passesmatlab-publish-toolboxmatlab-define-toolbox-apimatlab-document-toolbox (this skill may delegate there)buildUtilities/toolboxSpecification.m) — if absent, discovery mode is usedbuildUtilities/tbxManifest.m).m file containing a function keyword that is on the MATLAB path. Scripts (no function keyword) are excluded from checks 1–3.Before starting the assessment, ask the user which level they want (or accept if they specify upfront). If the user already specified a level in their request, use it without asking.
| Level | What runs | Detail |
|-------|-----------|--------|
| Quick | HIGH-impact checks only (1, 4, 7, 12) | Skim files, fast feedback |
| Standard | All 16 checks | Read representative files for qualitative checks |
| Deep | All 16 checks on all files | Exhaustive analysis including cross-file dependency and naming checks |
If no level is specified or inferable, default to Standard and state which level you are using.
The following skills from this pipeline can automate fixes for findings. Only reference a delegate skill if it is currently loaded and available. If unavailable, use the generic fix suggestion from the checks table instead.
| Skill | Action | Trigger |
|-------|--------|---------|
| /matlab-document-toolbox | Generate README, functionSignatures.json, GettingStarted.m, examples | Missing function signatures, README, or GettingStarted guide |
| /matlab-exclude-files | Generate toolbox.ignore | Files found that shouldn't ship to users |
Prompt:
> Which assessment level?
> A) Quick — Spot-check the essentials (help, tests, code errors)
> B) Standard — Check all quality dimensions on representative files
> C) Deep — Check all quality dimensions on every file, plus cross-file analysis
Accept the user's choice. If they also specify checks to skip, note those.
.m files, tests/, functionSignatures.json, buildfile.m, README.md, license.txt, toolbox/, docs, etc.mcp__matlab__check_matlab_code on .m files.arguments blocks.Run checks in this exact order. Report every check (pass or finding). Use these exact impact levels — do not change them:
| # | Check | What it validates | Impact | Delegate (if available) | Generic fix |
|---|-------|-------------------|--------|-------------------------|-------------|
| 1 | H1 help | Public functions have H1 line | HIGH | — | Add a %FUNCNAME One-line description as the first comment after the function signature |
| 2 | Help text | Full help (H1 + description + syntax) | LOW | — | Expand help block with description, syntax examples, and See Also |
| 3 | Arguments blocks | Input validation via arguments | LOW | — | Add arguments block with type and size validation |
| 4 | Tests exist | Public functions have tests | HIGH | — | Create test files in tests/ using matlab.unittest framework |
| 5 | Tests pass | Tests succeed when run (skip if no tests exist) | HIGH | — | Fix failing tests |
| 6 | Coverage | Line coverage meets threshold | MEDIUM | — | Add tests covering untested code paths |
| 7 | Code issues | No error-severity Code Analyzer findings | HIGH | — | Resolve Code Analyzer errors shown by checkcode |
| 8 | Spec drift | Files in spec (buildUtilities/toolboxSpecification.m) match disk (skip if no spec) | MEDIUM | — | Update spec to match current file set |
| 9 | Dependencies | No shadows, all deps declared | MEDIUM | — | Rename shadowing files; declare toolbox dependencies |
| 10 | Function signatures | functionSignatures.json exists | LOW | /matlab-document-toolbox | Create functionSignatures.json for tab-completion support |
| 11 | Version set | Not "0.0.0" or empty | LOW | — | Set version in Contents.m or ToolboxOptions |
| 12 | README | README.md exists at root (recommended for discoverability and onboarding) | HIGH | /matlab-document-toolbox | Create a README.md with toolbox name, purpose, installation, and quick-start |
| 13 | License file | license.txt or LICENSE exists at root (required for File Exchange submission) | MEDIUM | — | Add a license file |
| 14 | Toolbox folder separation | Distributable content is in a toolbox/ folder OR a package.ignore/toolbox.ignore excludes non-distributable files — either approach is valid | MEDIUM | — | Separate distributable content or add an ignore file |
| 15 | GettingStarted guide | GettingStarted.m or GettingStarted.mlx exists in toolbox/doc/ or toolbox/ (MATLAB auto-presents this on toolbox install) | MEDIUM | /matlab-document-toolbox | Create a GettingStarted.m with examples |
| 16 | Ignore file | toolbox.ignore or package.ignore exists with appropriate exclusions for files that shouldn't ship | MEDIUM | /matlab-exclude-files | Create ignore file excluding build artifacts, tests, and dev-only files |
Impact key: HIGH = high benefit to end-user experience if addressed. MEDIUM = recommended best practice. LOW = nice-to-have, improves polish.
Quick level: Only run checks 1, 4, 7, 12. Report the rest as "skipped (Quick level)".
## Readiness Report — [Toolbox Name]
### Level: Standard
### Status: IMPROVEMENTS RECOMMENDED (3 high-impact, 1 medium-impact, 1 low-impact)
### Improvements
| # | Check | Impact | Finding | Fix |
|---|-------|--------|---------|-----|
| 1 | 7 | HIGH | 3 Code Analyzer errors | Resolve Code Analyzer errors shown by `checkcode` |
| 2 | 4 | HIGH | 5 functions have no test coverage | Create test files in `tests/` using `matlab.unittest` framework |
| 3 | 1 | HIGH | 8 functions missing H1 help | Add H1 help lines to these functions |
| 4 | 9 | MEDIUM | `Disp.m` may shadow built-in | Rename shadowing files; declare toolbox dependencies |
| 5 | 10 | LOW | No `functionSignatures.json` in 4 subfolders | `/matlab-document-toolbox` |
(Ordered by priority, not check number.)
### Passing
- [x] Check 8: Spec drift — spec matches disk
- [x] Check 11: Version set — 2.8.0
### Skipped (user request)
- Check 6: Coverage — skipped by user
### Future Improvements (no delegate skill for these)
1. Namespace reorganization (+package/) would prevent name collisions
2. GettingStarted.m would improve onboarding
3. buildfile.m would enable automated CI
Status rules:
Prompt user: which findings to fix? Options:
> A) All — fix everything with available delegate skills
> B) Select — pick specific finding numbers (e.g., "1, 3, 5")
> C) Skip — proceed without fixing
For findings with an available delegate skill: invoke the skill with relevant context.
For findings with only a generic fix: perform the fix directly (e.g., add H1 lines, create files).
Report results before moving to next finding.
Yes — the punch list is the gate. User reviews and decides whether to fix or proceed.
This skill uses the following MCP tools during assessment:
| Tool | Purpose |
|------|---------|
| mcp__matlab__check_matlab_code | Static analysis (Code Analyzer) on .m files |
| mcp__matlab__run_matlab_test_file | Run test files to verify they pass |
| mcp__matlab__evaluate_matlab_code | Execute MATLAB commands for coverage or dependency checks |
/matlab-build-toolbox — if all checks pass, execute the build plan and produce the .mltbx artifact/matlab-document-toolbox for missing docs, /matlab-exclude-files for ignore file) and re-run this skill----
Copyright 2026 The MathWorks, Inc.
----
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
Take matlab/matlab-assess-toolbox from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.