agentleFS
Sign inStart free
hamzafarooqhamzafarooq/claude-code-starter/.claude/skills/verify-work/SKILL.md

verify-work

Skill145 starsChanged 6 months agoMITView on GitHub

End-of-session code review — checks for unused imports, console.logs, missing error handling, hardcoded values, and edge cases before committing. Use when the user is done coding and wants a final pass before committing or shipping.

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If nothing is found: "All clear — no issues found in the reviewed files."

    line 41

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Review all recently modified files in the current session. Check for:

Verify Work — Pre-Commit Review

Cleanliness

  • No console.log, print, or debug statements left in
  • No commented-out code blocks
  • No TODO comments that belong in the backlog, not the file
  • No unused imports or variables

Correctness

  • Every function that can fail has error handling
  • No hardcoded API keys, URLs, or credentials
  • Environment variables are used for config values
  • No hardcoded user IDs, test emails, or magic numbers without a constant name

Edge cases

For each modified function, check:

  • What happens if the input is null, empty, or the wrong type?
  • What happens if an API call fails or times out?
  • What happens on first run with no existing data?

Security

  • No user input is passed directly to a shell command, SQL query, or file path
  • No sensitive data logged to console or written to files

Report format:

For each issue found:

File: path/to/file.ts line [N] Issue: [what's wrong] Fix: [specific change to make]

If nothing is found: "All clear — no issues found in the reviewed files."

Fix issues directly if asked. Otherwise report only, don't change files.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free