agentleFS
Sign inStart free
paultyngpaultyng/skill-issue/skills/verify-when-complete/SKILL.md

verify-when-complete

Skill8 starsChanged 3 months agoMITView on GitHub

Run format, lint, build, and test verification before claiming work is complete. Detects the project toolchain (Taskfile, Makefile, or raw Go) and runs the appropriate commands. Use before committing, pushing, creating PRs, claiming a fix works, or any completion assertion.

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 12 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈12

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No completion claims without fresh verification evidence.

    line 8
  2. Distinctive:

    Before claiming any status or expressing satisfaction:

    line 18
  3. Distinctive:

    If NO: state actual status with evidence

    line 24
  4. Distinctive:

    If YES: state claim with evidence

    line 25
  5. Distinctive:

    Use the detected toolchain above to select commands from the tables below.

    line 40
  6. Distinctive:

    Run each step in order. If any step fails, stop and report the error.

    line 44
  7. Very specific:

    If a specific task/target doesn't exist, fall back to the raw Go equivalent.

    line 78
  8. Distinctive:

    Before committing or pushing

    line 82
  9. Distinctive:

    Before creating or updating a pull request

    line 83
  10. Distinctive:

    Before claiming a bug is fixed

    line 84
  11. Distinctive:

    Before claiming a rebase or conflict resolution succeeded

    line 85
  12. Distinctive:

    Before moving to the next task after making changes

    line 86
  13. Distinctive:

    Before any statement asserting correctness or completion

    line 87

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “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 When Complete

No completion claims without fresh verification evidence.

This skill is the operational arm of ~/.claude/rules/probe-not-assume.md: claims of completion require fresh, probed evidence, not implementer self-report.

Core Principle

Evidence before claims, always. If you haven't run the verification command in this message, you cannot claim it passes.

Gate Rule

Before claiming any status or expressing satisfaction:

  1. Identify: What command proves this claim?
  2. Run: Execute the full command (fresh, complete)
  3. Read: Full output, check exit code, count failures
  4. Verify: Does output confirm the claim?
    • If NO: state actual status with evidence
    • If YES: state claim with evidence
  5. Only then: make the claim

Red Flags: Stop and Verify

  • Using "should", "probably", "seems to"
  • Expressing satisfaction before verification ("Great!", "Done!")
  • About to commit/push/PR without verification
  • Relying on a previous run, not a fresh one
  • Trusting subagent success reports without independent verification

Detected Toolchain

!if [ -f Taskfile.yaml ]; then echo "taskfile"; elif [ -f Makefile ]; then echo "makefile"; else echo "raw"; fi

Use the detected toolchain above to select commands from the tables below.

Verification Steps

Run each step in order. If any step fails, stop and report the error.

Format

ToolchainCommand
Taskfiletask fmt (if exists)
Makefilemake fmt (if exists)
Raw Gogo fmt ./...

Lint

ToolchainCommand
Taskfiletask lint (if exists)
Makefilemake lint (if exists)
Raw Gogo vet ./...

Build

ToolchainCommand
Taskfiletask build (if exists)
Makefilemake build (if exists)
Raw Gogo build ./...

Test

ToolchainCommand
Taskfiletask test (if exists)
Makefilemake test (if exists)
Raw Gogo test -race -count 1 -v ./...

If a specific task/target doesn't exist, fall back to the raw Go equivalent. Run tests uncached (-count 1), with race detection, no -short flag.

When to Apply

  • Before committing or pushing
  • Before creating or updating a pull request
  • Before claiming a bug is fixed
  • Before claiming a rebase or conflict resolution succeeded
  • Before moving to the next task after making changes
  • Before any statement asserting correctness or completion

Cross-references

  • The narrowest verification command this skill produces (e.g. task test -- -run '^TestX$' -count=1) is the natural reproducer for the bisect skill. When a test that this skill once green-lit is now red, bisect with that exact command.

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.

Check your setup, free