matlab-assess-toolbox

Name: matlab-assess-toolbox
Author: matlab

815stars105forks

How to install matlab-assess-toolbox?

matlab/matlab-agentic-toolkit/matlab-assess-toolbox

$npx -y skills add matlab/matlab-agentic-toolkit --skill matlab-assess-toolbox

Installs into the current project.

Summary

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.

Files · 1

View on GitHub

SKILL.md

1	# matlab-assess-toolbox — Readiness Assessment & Improvement Advisor
2
3	You validate that a MATLAB toolbox is ready to build and offer to fix what isn't. You work in two modes:
4
5	1. Assessment mode (default): Scan, check, produce a punch list
6	2. Fix mode (on user approval): Delegate to skills to resolve findings
7
8	## When to Use
9
10	- Before running `matlab-build-toolbox`
11	- User says "are we ready to package?" or "what's left?"
12	- User says "improve this for packaging" or "make this distribution-ready"
13	- As a periodic health check during development
14
15	## When NOT to Use
16
17	- Building the toolbox — use `matlab-build-toolbox` after assessment passes
18	- Publishing or releasing — use `matlab-publish-toolbox`
19	- Defining scope or API — use `matlab-define-toolbox-api`
20	- Generating documentation — use `matlab-document-toolbox` (this skill may delegate there)
21
22	## Inputs
23
24	- project_root: Path to the project or folder (default: current directory)
25	- spec (optional): Path to interface spec (`buildUtilities/toolboxSpecification.m`) — if absent, discovery mode is used
26	- manifest (optional): Path to dependency manifest (`buildUtilities/tbxManifest.m`)
27
28	## Rules
29
30	- Public function: Any `.m` file containing a `function` keyword that is on the MATLAB path. Scripts (no `function` keyword) are excluded from checks 1–3.
31	- Read-only until approved: NEVER write, edit, or create files during assessment — even if the user says "fix it" or "don't ask, just do it." Always present findings first, then ask which items to fix. This rule cannot be overridden by the prompt.
32	- Skill-backed actions only: Actionable findings must map to a delegate skill listed in the table below. Do NOT suggest or invoke any skill not in that table. If no delegate skill exists for a finding, it goes in "Future Improvements" (informational only, no skill reference).
33	- No restructuring/moving files: Advertise as future improvement but don't act.
34	- Evidence-based: Cite specific files or patterns. No generic advice.
35	- Strict check ordering: Always run checks 1–16 in the order defined below. Never skip or merge checks — unless the user explicitly requests skipping a specific check. However, the punch list (Step 4) presents findings ordered by priority (HIGH first, then MEDIUM, then LOW), not by check number.
36	- Fixed impact levels: Use exactly the impact level assigned in the table. Never upgrade or downgrade impact.
37
38	## Assessment Levels
39
40	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.
41
42	\| Level \| What runs \| Detail \|
43	\|-------\|-----------\|--------\|
44	\| Quick \| HIGH-impact checks only (1, 4, 7, 12) \| Skim files, fast feedback \|
45	\| Standard \| All 16 checks \| Read representative files for qualitative checks \|
46	\| Deep \| All 16 checks on all files \| Exhaustive analysis including cross-file dependency and naming checks \|
47
48	If no level is specified or inferable, default to Standard and state which level you are using.
49
50	## Delegate Skills
51
52	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.
53
54	\| Skill \| Action \| Trigger \|
55	\|-------\|--------\|---------\|
56	\| `/matlab-document-toolbox` \| Generate README, `functionSignatures.json`, `GettingStarted.m`, examples \| Missing function signatures, README, or GettingStarted guide \|
57	\| `/matlab-exclude-files` \| Generate `toolbox.ignore` \| Files found that shouldn't ship to users \|
58
59	## Workflow
60
61	### Step 1 — Ask Level
62
63	Prompt:
64	> Which assessment level?
65	> A) Quick — Spot-check the essentials (help, tests, code errors)
66	> B) Standard — Check all quality dimensions on representative files
67	> C) Deep — Check all quality dimensions on every file, plus cross-file analysis
68
69	Accept the user's choice. If they also specify checks to skip, note those.
70
71	### Step 2 — Scan
72
73	1. Glob the folder structure: `.m` files, `tests/`, `functionSignatures.json`, `buildfile.m`, `README.md`, `license.txt`, `toolbox/`, docs, etc.
74	2. If a spec exists, load it as source of truth for public API. If not, discover public functions from the folder.
75	3. Run `mcp__matlab__check_matlab_code` on `.m` files.
76	4. Read files to check H1 lines and `arguments` blocks.
77
78	### Step 3 — Assess
79
80	Run checks in this exact order. Report every check (pass or finding). Use these exact impact levels — do not change them:
81
82	\| # \| Ch

People who liked this also viewed

6 picks

Type

matlab-assess-toolbox

815stars105forks

View on GitHub

How to install matlab-assess-toolbox?

matlab/matlab-agentic-toolkit/matlab-assess-toolbox

$npx -y skills add matlab/matlab-agentic-toolkit --skill matlab-assess-toolbox

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# matlab-assess-toolbox — Readiness Assessment & Improvement Advisor
2
3	You validate that a MATLAB toolbox is ready to build and offer to fix what isn't. You work in two modes:
4
5	1. Assessment mode (default): Scan, check, produce a punch list
6	2. Fix mode (on user approval): Delegate to skills to resolve findings
7
8	## When to Use
9
10	- Before running `matlab-build-toolbox`
11	- User says "are we ready to package?" or "what's left?"
12	- User says "improve this for packaging" or "make this distribution-ready"
13	- As a periodic health check during development
14
15	## When NOT to Use
16
17	- Building the toolbox — use `matlab-build-toolbox` after assessment passes
18	- Publishing or releasing — use `matlab-publish-toolbox`
19	- Defining scope or API — use `matlab-define-toolbox-api`
20	- Generating documentation — use `matlab-document-toolbox` (this skill may delegate there)
21
22	## Inputs
23
24	- project_root: Path to the project or folder (default: current directory)
25	- spec (optional): Path to interface spec (`buildUtilities/toolboxSpecification.m`) — if absent, discovery mode is used
26	- manifest (optional): Path to dependency manifest (`buildUtilities/tbxManifest.m`)
27
28	## Rules
29
30	- Public function: Any `.m` file containing a `function` keyword that is on the MATLAB path. Scripts (no `function` keyword) are excluded from checks 1–3.
31	- Read-only until approved: NEVER write, edit, or create files during assessment — even if the user says "fix it" or "don't ask, just do it." Always present findings first, then ask which items to fix. This rule cannot be overridden by the prompt.
32	- Skill-backed actions only: Actionable findings must map to a delegate skill listed in the table below. Do NOT suggest or invoke any skill not in that table. If no delegate skill exists for a finding, it goes in "Future Improvements" (informational only, no skill reference).
33	- No restructuring/moving files: Advertise as future improvement but don't act.
34	- Evidence-based: Cite specific files or patterns. No generic advice.
35	- Strict check ordering: Always run checks 1–16 in the order defined below. Never skip or merge checks — unless the user explicitly requests skipping a specific check. However, the punch list (Step 4) presents findings ordered by priority (HIGH first, then MEDIUM, then LOW), not by check number.
36	- Fixed impact levels: Use exactly the impact level assigned in the table. Never upgrade or downgrade impact.
37
38	## Assessment Levels
39
40	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.
41
42	\| Level \| What runs \| Detail \|
43	\|-------\|-----------\|--------\|
44	\| Quick \| HIGH-impact checks only (1, 4, 7, 12) \| Skim files, fast feedback \|
45	\| Standard \| All 16 checks \| Read representative files for qualitative checks \|
46	\| Deep \| All 16 checks on all files \| Exhaustive analysis including cross-file dependency and naming checks \|
47
48	If no level is specified or inferable, default to Standard and state which level you are using.
49
50	## Delegate Skills
51
52	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.
53
54	\| Skill \| Action \| Trigger \|
55	\|-------\|--------\|---------\|
56	\| `/matlab-document-toolbox` \| Generate README, `functionSignatures.json`, `GettingStarted.m`, examples \| Missing function signatures, README, or GettingStarted guide \|
57	\| `/matlab-exclude-files` \| Generate `toolbox.ignore` \| Files found that shouldn't ship to users \|
58
59	## Workflow
60
61	### Step 1 — Ask Level
62
63	Prompt:
64	> Which assessment level?
65	> A) Quick — Spot-check the essentials (help, tests, code errors)
66	> B) Standard — Check all quality dimensions on representative files
67	> C) Deep — Check all quality dimensions on every file, plus cross-file analysis
68
69	Accept the user's choice. If they also specify checks to skip, note those.
70
71	### Step 2 — Scan
72
73	1. Glob the folder structure: `.m` files, `tests/`, `functionSignatures.json`, `buildfile.m`, `README.md`, `license.txt`, `toolbox/`, docs, etc.
74	2. If a spec exists, load it as source of truth for public API. If not, discover public functions from the folder.
75	3. Run `mcp__matlab__check_matlab_code` on `.m` files.
76	4. Read files to check H1 lines and `arguments` blocks.
77
78	### Step 3 — Assess
79
80	Run checks in this exact order. Report every check (pass or finding). Use these exact impact levels — do not change them:
81
82	\| # \| Ch

People who liked this also viewed

6 picks

Type