Matlab Review Fi Code

Reviews MATLAB fixed-point (fi) code for perf, codegen efficiency, and correctness

Tested · Works

Test report

Verdict
Tested · Works
Score
9.2/10
Tested
Jul 21, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Aug 10, 2026 · c460dde

Fetched SKILL.md and manifest.yaml (both HTTP 200) from skills-catalog/code-generation/matlab-review-fi-code/; body is self-contained with inline MATLAB examples, no external scripts, no security smells. Wrote a planted MATLAB FIR snippet with 8 antipatterns, then produced a baseline review (no skill) and a skill-following review. Baseline caught generic issues (preallocation, vectorization, dead acc, division); the skill review additionally flagged fixed-point-specific defects the baseline missed entirely — accumulator bit-growth needing acc(:) assignment (Check 3), name-value vs positional constructor cost (Check 8), default-fimath bloated-C / KeepLSB (Check 4), bitsra for power-of-2 divide (Check 6), sin(fi) to FunctionApproximation/CORDIC (Check 7), and the types-table pattern (Check 2) — emitted in the required [CATEGORY] Line N (Check N) format. Technical claims spot-checked as accurate (bitsra, hdlfimath, FunctionApproximation.Problem, cordicsin, quantizenumeric).

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 5/5
  • Output vs. baseline 8/10
  • Docs & honesty 5/5

What Matlab Review Fi Code does

A code-review checklist that inspects MATLAB fixed-point code and flags antipatterns across 11 checks: scalar fi() in loops, name-value constructors, accumulator bit-growth, default fimath, fixed-point division, transcendental functions on fi inputs, and more. Triggers when reviewing MATLAB code that uses fi, fimath, numerictype, or quantizenumeric, or when preparing fixed-point code for C or hardware code generation. Emits findings in a structured [PERF]/[CODEGEN]/[CORRECTNESS]/[PATTERN]/[DEBUG] format keyed to each check.

How to install Matlab Review Fi Code

git clone --depth 1 https://github.com/matlab/matlab-agentic-toolkit.git /tmp/matlab-review-fi-code-src
mkdir -p ~/.claude/skills
cp -R /tmp/matlab-review-fi-code-src/skills-catalog/code-generation/matlab-review-fi-code ~/.claude/skills/matlab-review-fi-code
# Self-contained: SKILL.md + manifest.yaml only, no external scripts to fetch.
# The review itself (reading fi code, emitting categorized findings) runs with no MATLAB install.
# manifest.yaml lists required-products "Fixed-Point Designer" and required-tools
#   evaluate_matlab_code / check_matlab_code — only needed if you want the agent to
#   actually RUN/verify the suggested MATLAB, not to perform the static review.
# Official install path is the MATLAB Agentic Toolkit installer: in MATLAB run
#   setupAgenticToolkit("install")  (see repo README).

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Matlab Review Fi Code

  • /matlab-review-fi-code Reviews MATLAB fixed-point (fi) code for perf, codegen efficiency, and correctness

It also activates on plain-language prompts like these:

  • Review this fimath code for performance issues
  • Check this numerictype usage for antipatterns
  • Suggest idiomatic fixes for this quantizenumeric code

Frequently asked questions

Is the Matlab Review Fi Code skill free?
Yes. The skill itself is free from matlab/matlab-agentic-toolkit. SkillProof publishes the install command and an independent test verdict at no cost.
Does Matlab Review Fi Code work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Fetched SKILL.md and manifest.yaml (both HTTP 200) from skills-catalog/code-generation/matlab-review-fi-code/; body is self-contained with inline MATLAB examples, no external scripts, no security smells. Wrote a planted MATLAB FIR snippet with 8 antipatterns, then produced a baseline review (no skill) and a skill-following review. Baseline caught generic issues (preallocation, vectorization, dead acc, division); the skill review additionally flagged fixed-point-specific defects the baseline missed entirely — accumulator bit-growth needing acc(:) assignment (Check 3), name-value vs positional constructor cost (Check 8), default-fimath bloated-C / KeepLSB (Check 4), bitsra for power-of-2 divide (Check 6), sin(fi) to FunctionApproximation/CORDIC (Check 7), and the types-table pattern (Check 2) — emitted in the required [CATEGORY] Line N (Check N) format. Technical claims spot-checked as accurate (bitsra, hdlfimath, FunctionApproximation.Problem, cordicsin, quantizenumeric).
What is the Matlab Review Fi Code SkillProof Score?
9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Matlab Review Fi Code?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Matlab Review Fi Code with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.