AI Code Review Skill: Every Bug Gets a Failing Test
by César Pereiro
Code review for Claude Code, Cursor and Codex that proves each serious bug with a test it ran. Fewer nitpicks, no guessing.
I build and maintain core modules for large-scale hospital information systems (HIS/EHR), where reliability and strict data handling are essential. My work focuses on enterprise Java and Spring architecture, handling complex clinical workflows and legacy codebases where stability is everything. Every solution is built for heavy-duty healthcare environments, ensuring seamless integration and robust performance. Start free with AI Code Review, save with the bundles.
by César Pereiro
Code review for Claude Code, Cursor and Codex that proves each serious bug with a test it ran. Fewer nitpicks, no guessing.
by César Pereiro
Turn any third-party skill or plugin into a SAFE / REVIEW / DANGEROUS verdict with file:line evidence, before it runs on your machine.
by César Pereiro
Free review pass that attacks the change like a hostile tester and only reports what it can prove.
by César Pereiro
Free gate that fails the build when a requirement has no real test behind it. Works with any language.
by César Pereiro
Turn your app's URL into a one-page launch report card: leaked keys, open Supabase tables, phone layout, Google and AI search, speed. Plain English, with a fix list to paste to your AI.
by César Pereiro
Free Claude Code hook: your agent can't end its turn on "done" until the tests really ran green after its last edit. Checks the commands that ran, not its words.
by César Pereiro
Free final check that decides done or not-done from command exit codes, not from what the agent says.
by César Pereiro
Turn a risky Postgres or MySQL migration into a safe one: flags table locks and rewrites before they hit production and suggests the zero-downtime version.
by César Pereiro
Turn a one-line brief into a responsive landing page with a real design system, then check it in light and dark mode at three widths until nothing is broken.
by César Pereiro
Turn a SQL log into a ranked list of N+1 and duplicate queries with the ORM fix (select_related, includes, JOIN FETCH, selectinload).
by César Pereiro
Turn 'feels slower' into a verdict: runs old and new code alternately, then reports the slowdown with a confidence interval, or says the noise is too high.
by César Pereiro
Turn rm -rf, git reset --hard and force pushes into a checked step: blocks destructive shell commands only when they would really lose work.
by César Pereiro
Turn AI-written Python into code that calls real functions: checks every import, attribute and keyword argument against the library you actually installed.
by César Pereiro
Turn a flaky test into a named culprit: measures its failure rate and bisects test order to find the polluting test in a handful of runs.
by César Pereiro
Turn a slow test suite into just the tests your change can break: maps your git diff to the affected tests and prints the exact command to run.
by César Pereiro
Turn any coverage report into the only number that matters for a PR: which changed lines no test runs, grouped by file, with a CI gate.
by César Pereiro
Turn /compact from a reset into a checkpoint: your rules, goal, edited files and last test result are saved before compaction and put back after it.
by César Pereiro
Turn every pip/npm/cargo install your agent runs into a checked one: blocks typosquats and hallucinated package names before they reach your machine.
by César Pereiro
Turn a rough AI-built page into a polished one: renders it at phone, tablet and desktop, scores the design 0-100 and hands your agent a ranked fix list with annotated screenshots.
by César Pereiro
Turn any website into a scored GEO + SEO fix list: a real crawler checks 69 rules for Google and AI search (ChatGPT, Perplexity, Claude) and writes the fix files.
by César Pereiro
Turn a huge log file into a 2 KB summary with the real error on top: templates, counts, folded stack traces and what is new since the last good run.
by César Pereiro
Five role-restricted sub-agents, from planner to verifier. Hand-offs pass only when a command's exit code says so, never an agent's word.