agentleFS
26zl26zl/universal-agent-skills/skills/verify-changes/SKILL.md

verify-changes

Skill2 starsChanged 37 days agoMITView on GitHub

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.

12 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use intelligent-routing, design-spec and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • SKB3002Skill

    intelligent-routing

    Automatic agent selection and intelligent task routing. Analyzes user requests and automatically selects the best specialist agent(s) without requiring explicit user mentions.

    Also in 3 projects that use this

  • jornalistainclusivoSkill

    design-spec

    How to author a DESIGN.md file — the machine-readable design-token + human-rationale format that must exist before any UI is built. YAML front-matter token schema (colors, typography, spacing, rounded, components), type system, token references, and canonical section order.

    Also in 3 projects that use this

  • xenitV1Skill

    bash-linux

    Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.

    Also in 3 projects that use this

  • xenitV1Skill

    red-team-tactics

    Red team tactics principles based on MITRE ATT&CK. Attack phases, detection evasion, reporting.

    Also in 3 projects that use this

  • xfstudioSkill

    rust-pro

    Master Rust 1.75+ with modern async patterns, advanced type system

    Also in 3 projects that use this

  • +7 more from xenitV1

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 8

    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:

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

    line 9
  2. Distinctive:

    Run the smallest focused test that exercises each changed behavior.

    line 15
  3. Distinctive:

    Run the relevant formatter, linter, type checker, build, or broader test suite when the change can affect adjacent code.

    line 16
  4. Distinctive:

    Do not claim success without fresh evidence from the current working tree.

    line 23
  5. Distinctive:

    Do not hide failing checks because they appear unrelated.

    line 24
  6. Distinctive:

    Do not broaden the change merely to make unrelated checks pass.

    line 25
  7. Distinctive:

    Never expose credentials or sensitive output in logs or the final report.

    line 26
  8. Distinctive:

    Treat skipped checks as residual risk, not as passing checks.

    line 27

“Common” is measured: kept by at least 6 in 10 of the 10 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

Verify Changes

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

Workflow

  1. Inspect the final diff and list the behaviors that changed.
  2. Identify the repository's documented validation commands before inventing new ones.
  3. Run the smallest focused test that exercises each changed behavior.
  4. Run the relevant formatter, linter, type checker, build, or broader test suite when the change can affect adjacent code.
  5. Inspect generated files and user-visible output when automated assertions cannot cover layout or behavior.
  6. Re-read the diff for accidental edits, debug output, secrets, stale comments, and missing tests.
  7. 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.

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.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.