principle-prove-it-works SKILL.md skillA

This file is byte-identical to the first copy the registry indexed, one of 5 indexed copies. Same content hash, so the same checks give both the same grade.

principle-prove-it-works from barbieri/local-openfinance is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add barbieri/local-openfinance/principle-prove-it-works@git:20261005.32edae5

Pins git:20261005.32edae5 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
barbieri/local-openfinance
Path
.agents/skills/principle-prove-it-works/SKILL.md
Versions recorded
2
Latest version
git:20261005.32edae5, committed Oct 5, 2026
First version recorded
Sep 9, 2026
Size
1,371 bytes
Repository stars
24
License
GPL-3.0

Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 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

## 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).

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add barbieri/local-openfinance/principle-prove-it-works@sha256:ec79a15025bac8d3

The line at the top of this page pins the label git:20261005.32edae5, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_rpp7dwrjxaap3tdy.svg)](https://markdownregistry.com/a/art_rpp7dwrjxaap3tdy)

0 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Sep 9, 2026 and Oct 5, 2026, about one every 26 days.

versioncommittedcommitsizeaudit
git:20261005.32edae5 latest2026-10-05 32edae5 1,371 BA view · diff
git:20260909.1e5ab422026-09-09 1e5ab42 2,068 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (1371 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

barbieri/local-openfinance · 24 stars · license GPL-3.0 · pushed 2026-10-28 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_rpp7dwrjxaap3tdy
GET https://markdownregistry.com/api/v1/resolve?ref=barbieri/local-openfinance/principle-prove-it-works
GET https://markdownregistry.com/api/v1/blob/ec79a15025bac8d33d62011c54f3b612733fd2a024e623b531b3637aa75070e2

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from barbieri/local-openfinance

agent-browser SKILL.md skill
barbieri/local-openfinance · .agents/skills/agent-browser/SKILL.md · Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages…
git:20261005.32edae5 · audit A · 24 stars
ai-sdk SKILL.md skill
barbieri/local-openfinance · .agents/skills/ai-sdk/SKILL.md · Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK…
git:20261005.32edae5 · audit A · 24 stars
architect SKILL.md skill
barbieri/local-openfinance · .agents/skills/architect/SKILL.md · Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use…
git:20261005.32edae5 · audit A · 24 stars
arena SKILL.md skill
barbieri/local-openfinance · .agents/skills/arena/SKILL.md · Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for…
git:20261005.32edae5 · audit A · 24 stars
automate-me SKILL.md skill
barbieri/local-openfinance · .agents/skills/automate-me/SKILL.md · Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a…
git:20261005.32edae5 · audit A · 24 stars
banco-mcp SKILL.md skill
barbieri/local-openfinance · .agents/skills/banco-mcp/SKILL.md · access to Banco MCP REST API to fetch OpenFinance bank data
git:20260909.1e5ab42 · audit A · 24 stars
blast-radius SKILL.md skill
barbieri/local-openfinance · .agents/skills/blast-radius/SKILL.md · Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe…
git:20261005.32edae5 · audit A · 24 stars
bro SKILL.md skill
barbieri/local-openfinance · .agents/skills/bro/SKILL.md · Restate the last message in plain human language, with no jargon.
git:20260909.1e5ab42 · audit A · 24 stars
cancel-ralph SKILL.md skill
barbieri/local-openfinance · .agents/skills/cancel-ralph/SKILL.md · Cancel an active Ralph Loop. Use when the user wants to stop, cancel, or abort a running ralph loop.
git:20260909.1e5ab42 · audit A · 24 stars
check-compiler-errors SKILL.md skill
barbieri/local-openfinance · .agents/skills/check-compiler-errors/SKILL.md · Run compile and type-check commands and report failures
git:20260909.1e5ab42 · audit A · 24 stars
cli-for-agents SKILL.md skill
barbieri/local-openfinance · .agents/skills/cli-for-agents/SKILL.md · Designs or reviews CLIs so coding agents can run them reliably: non-interactive flags, layered --help with examples…
git:20260909.1e5ab42 · audit A · 24 stars
code-review SKILL.md skill
barbieri/local-openfinance · .agents/skills/code-review/SKILL.md · Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code…
git:20261005.32edae5 · audit A · 24 stars

Every file in barbieri/local-openfinance

Other files named principle-prove-it-works

principle-prove-it-works SKILL.md skill
cursor/plugins · harness/pstack/claude-code/skills/principle-prove-it-works/SKILL.md · Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the…
git:20261016.182f2ce · audit A · 15,125 stars
principle-prove-it-works SKILL.md skill
cursor/plugins · pstack/skills/principle-prove-it-works/SKILL.md · Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the…
git:20260923.b0b9c7a · audit A · 15,125 stars
principle-prove-it-works SKILL.md skill
nightly-labs/openbot · marketplace/production-catalog/bundles/pstack/skills/principle-prove-it-works/SKILL.md · Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the…
git:20261013.9e6954c · audit A · 5,267 stars
principle-prove-it-works SKILL.md skill
michael-denyer/pstack-claude · plugins/pstack/skills/principle-prove-it-works/SKILL.md · Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the…
git:20261016.963781d · audit A · 3,776 stars
principle-prove-it-works SKILL.md skill
backnotprop/pstack · skills/principle-prove-it-works/SKILL.md · Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the…
git:20261004.c0c3f13 · audit A · 3,337 stars
principle-prove-it-works SKILL.md skill
iap/pstack-hermes · skills/principle-prove-it-works/SKILL.md · Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the…
git:20261031.336cc57 · audit A · 32 stars
principle-prove-it-works SKILL.md skill
j-star-films-studios/vibecode-protocol-suite · assets/.agent/skills/engineering-principles/prove-it-works/SKILL.md · Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the…
git:20260821.1b830a3 · audit A · 26 stars
principle-prove-it-works SKILL.md skill
theonlyfusioncube/potetos-for-everyone · skills/principle-prove-it-works/SKILL.md · Verify the requested behavior against the real artifact or surface whenever possible; a proxy check only proves the…
git:20260908.f096f61 · audit A · 20 stars

Browse by kind, by grade A, or by owner.