mcpField
P
principle-prove-it-works

principle-prove-it-works

github.com/michael-denyerTesting & quality3.6k892 installsUpdated today
Repository

About principle-prove-it-works

A verification-principle skill that calls for checking actual outputs and process state rather than relying on proxies or self-reports. It applies to development and agent workflows where task results need direct confirmation.

Key features

  1. 01Inspect actual results directly
  2. 02Check process state and exit codes
  3. 03Confirm the source record for facts
  4. 04Verify with reproducible scripts

Use cases

  1. 01Confirming a service actually started
  2. 02Checking output against expectations
  3. 03Verifying a state change took effect

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/michael-denyer/pstack-claude --skill principle-prove-it-works

After installing, type/principle-prove-it-worksin Claude Code to confirm it loaded.

Details

From the project README

Prove It Works

Verify every task output by checking the real thing directly. Do not infer from proxies, self-reports, or "it compiles."

Why: Unverified work has unknown correctness. Indirect verification (file mtimes, output freshness, agent self-reports, cached screenshots) feels cheaper than direct observation. Acting on a wrong inference costs far more than checking the source.

Check the real thing, not a proxy:

  • Check process liveness directly, not indirectly through derived state
  • Read the actual value, not a cached or derived representation
  • When verification fails, suspect the observation method before suspecting the system
  • Before you report success (merged, sent, started), read the real state and the exit code. Truncated output (| tail -1) and your own echo prove nothing

Verify the process as well as the outcome. A correct result can rest on a broken process, and a review that checks results passes it: a clause reconstructed from the user's paste instead of the durable record, a constraint honored by chance from a file never read. For each fact you relied on, name the record it came from and confirm that record is the one the project's rules point at.

Red is a colour, not a measurement. A failing check proves the instrument only when the failure content is the disagreement you predicted. An exception, an empty collection against a non-empty literal, and a real mismatch all print red, so quote the assertion's diff (Extra items in the right set), never the assertion (assert {...} == {...}). A convergence probe keys on behavior only the new artifact can produce, never an identity field the old one also emits. A same-SHA restart lets old code report the new commit SHA.

Script the check when you can

The strongest proof is a deterministic script that re-runs the same comparison, not a one-time eyeball. Write the script, run it, and keep its output as an artifact a reviewer can re-run instead of trusting your word.

Keep the artifact visible for the human. Commit it only for large or complex work where the trail has to be auditable later, like a big port or migration (the show-me-your-work skill).

Comments

Markdown supported