agentsclimarketplace

Fresh eyes review

Skill michellepellon/superpowers/skills/fresh-eyes-review

A curated set of agent skills to support my daily workflows.

Install
npx -y skills add michellepellon/superpowers --skill fresh-eyes-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when about to commit, create a PR, or declare work complete — after verification-before-completion confirms tests pass but before code ships. Catches security vulnerabilities, logic errors, and business rule bugs that slip through despite passing tests.

SKILL.md

3.1 KB, as published. Nobody here has run it

Fresh-Eyes Review

Overview

Deliberate re-reading of changed code with psychological distance. Catches what you assumed was correct.

Core principle: 100% test coverage can coexist with critical bugs.

Prerequisite: verification-before-completion must pass first.

Process

  1. Announce: "Starting fresh-eyes review of [N] files."
  2. Walk each changed file through the five checklists below.
  3. Fix immediately. Re-run tests after each fix.
  4. Declare: "Fresh-eyes complete. [N] issues found and fixed: [brief description of each]." Include this even for zero findings.

Checklists

Security

CheckLook For
InjectionUnsanitized input in queries, commands, or templates
Path traversalUnvalidated file paths, ../ sequences
Auth gapsUnprotected endpoints, missing authorization checks
SecretsHardcoded credentials, tokens, or keys

Logic

CheckLook For
BoundariesOff-by-one in indices, loops, pagination
Race conditionsConcurrent access to shared state
Null handlingUnguarded access chains that could throw
Error swallowingEmpty catch blocks, ignored rejections

Business Rules

CheckLook For
CalculationsFormulas matching requirements, correct rounding
ConditionsAND/OR logic correct, negations applied properly
Edge casesEmpty input, single item, zero, maximum values
DefaultsSensible values when optional fields omitted

Input Validation

CheckLook For
Type checksExpected types enforced at boundaries
Range checksNumeric bounds, string lengths, array sizes
Format checksEmail, URL, date formats validated

Performance

CheckLook For
N+1 queriesLoops making individual database/API calls
Unbounded workMissing limits on iterations, result sets, payloads
Resource leaksUnclosed connections, streams, event listeners

Resistance Patterns

RationalizationReality
"Tests are comprehensive"Tests validate design, not correctness
"I'm confident it's correct"Confidence is inversely correlated with bugs
"It's just a small change"Small changes cause large outages
"Partner is waiting"3 minutes now saves 3 hours debugging later
"Senior dev already approved"They reviewed intent, not implementation details
"Production is blocked"Rushing causes the outages being rushed to fix

Red Flags — STOP

  • "I already looked at this code while writing it"
  • "The tests cover everything"
  • "This is too trivial to review"
  • "I just need to commit this quickly"

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.