Verify changes

Skill 26zl/universal-agent-skills/skills/verify-changes

Verify code or configuration changes with focused tests, static checks, and diff inspection before reporting completion. Use after implementing or modifying a repository; do not use for read-only explanations or when no files changed.From its SKILL.md

Install

npx -y skills add 26zl/universal-agent-skills --skill verify-changes

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 file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

1.7 KB, 278 tokens by cl100k_base, as published. Nobody here has run it

Verify Changes

Verify the actual change at the narrowest useful scope, then expand checks in proportion to risk.

Workflow

Inspect the final diff and list the behaviors that changed.
Identify the repository's documented validation commands before inventing new ones.
Run the smallest focused test that exercises each changed behavior.
Run the relevant formatter, linter, type checker, build, or broader test suite when the change can affect adjacent code.
Inspect generated files and user-visible output when automated assertions cannot cover layout or behavior.
Re-read the diff for accidental edits, debug output, secrets, stale comments, and missing tests.
Report which checks ran, their outcomes, and any check that could not run.

Rules

Do not claim success without fresh evidence from the current working tree.
Do not hide failing checks because they appear unrelated. Distinguish pre-existing failures only when evidence supports that conclusion.
Do not broaden the change merely to make unrelated checks pass.
Never expose credentials or sensitive output in logs or the final report.
Treat skipped checks as residual risk, not as passing checks.

Completion evidence

Provide a concise summary containing:

focused checks and their results;
broader checks and their results, when applicable;
manual inspection performed, when applicable;
remaining limitations or unverified behavior.

What ships with it: 1 file

191 B alongside SKILL.md

agents/

openai.yaml191 B

Gives 0 of the 12 instructions most quality gates skills give in 278 tokens

Counted across 1,524 of the 2,830 authors here whose files we hold, read 2026-09-06

Read full output and check exit codein 45 of 1524, across 40 files
Verify output confirms the claimin 44 of 1524, across 39 files
Identify the command that proves the claimin 43 of 1524, across 39 files
Execute the full verification commandin 36 of 1524, across 30 files
Produce a verification reportin 34 of 1524, across 18 files
Review git diff changesin 30 of 1524, across 16 files
Fix build failures immediatelyin 29 of 1524, across 9 files
Group findings by severityin 28 of 1524
State claim only with evidencein 27 of 1524, across 22 files
Verify regression tests with red-green cyclein 26 of 1524, across 22 files
Run the full test suitein 26 of 1524, across 25 files
Run test suite with coveragein 25 of 1524, across 10 files

Said here and by no other author read

Inspect the final diff
List the behaviors that changed
Identify documented validation commands
Inspect generated files and user-visible output
Re-read the diff for accidental edits
Report check outcomes and limitations

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.