verification-before-done SKILL.md skillA

verification-before-done from baphuongna/pi-crew is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add baphuongna/pi-crew/verification-before-done@git:20260911.3de89a2

Pins git:20260911.3de89a2 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
baphuongna/pi-crew
Path
skills/verification-before-done/SKILL.md
Versions recorded
5
Latest version
git:20260911.3de89a2, committed Sep 11, 2026
First version recorded
May 28, 2026
Size
3,646 bytes
Repository stars
57
License
MIT

Evidence before claims. When NOT to use: mid-task self-correction (use scrutinize); pure execution tasks where output IS evidence.

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

# verification-before-done

Core principle: evidence before claims. A worker report, green-looking log, or previous run is not fresh verification.

Distilled from detailed reads of agent-skill patterns for verification-before-completion, TDD, review reception, and QA workflows.

## Gate Function

Before any completion claim:

1. Identify the command or inspection that proves the claim.
2. Run the full command fresh, or explicitly state why a command cannot be run.
3. Read the output, including exit code and failure counts.
4. Compare the output to the claim.
5. Report the claim only with the evidence.

## Claim-to-Evidence Table

| Claim | Requires | Not sufficient |
|---|---|---|
| Tests pass | Fresh test output with zero failures | Prior run, "should pass" |
| Typecheck passes | Typecheck command exit 0 | Lint or targeted tests only |
| Bug fixed | Original symptom/regression test passes | Code changed |
| Requirements met | Checklist against request/plan | Generic test success |
| Agent completed | Worker output plus artifact/diff/state inspection | Worker says DONE |
| Safe to commit | Relevant checks pass and status reviewed | Partial local confidence |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add baphuongna/pi-crew/verification-before-done@sha256:4956e8abe92480df

The line at the top of this page pins the label git:20260911.3de89a2, 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_mjmrjw2vtg34zxl3.svg)](https://markdownregistry.com/a/art_mjmrjw2vtg34zxl3)

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

Versions

The registry has recorded 5 versions of this file, between May 28, 2026 and Sep 11, 2026, about one every 27 days.

versioncommittedcommitsizeaudit
git:20260911.3de89a2 latest2026-09-11 3de89a2 3,646 BA view · diff
git:20260911.c97bc572026-09-11 c97bc57 3,045 BA view · diff
git:20260603.fa30bc02026-06-03 fa30bc0 2,933 BA view · diff
git:20260529.53de3c22026-05-29 53de3c2 2,917 BA view · diff
git:20260528.67ddbec2026-05-28 67ddbec 3,054 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 (3646 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

baphuongna/pi-crew · 57 stars · license MIT · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_mjmrjw2vtg34zxl3
GET https://markdownregistry.com/api/v1/resolve?ref=baphuongna/pi-crew/verification-before-done
GET https://markdownregistry.com/api/v1/blob/4956e8abe92480dfba853df808487fddc026a2c794e1922102372bc2d6f6ad22

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 baphuongna/pi-crew

AGENTS.md AGENTS.md file
baphuongna/pi-crew · AGENTS.md
git:20260910.8ce36f3 · audit A · 57 stars
CLAUDE.md CLAUDE.md file
baphuongna/pi-crew · CLAUDE.md
git:20261019.8ce1fa4 · audit A · 57 stars
async-worker-recovery SKILL.md skill
baphuongna/pi-crew · skills/async-worker-recovery/SKILL.md · Background worker, heartbeat, stale-run, crash-recovery, and deadletter workflow. Use when debugging stuck/dead workers…
git:20260911.c97bc57 · audit A · 57 stars
child-pi-spawning SKILL.md skill
baphuongna/pi-crew · skills/child-pi-spawning/SKILL.md · Child Pi worker spawning, lifecycle callbacks, and failure modes. When NOT to use: non-Pi subprocess execution (use…
git:20260911.c97bc57 · audit A · 57 stars
context-artifact-hygiene SKILL.md skill
baphuongna/pi-crew · skills/context-artifact-hygiene/SKILL.md · Use when constructing worker prompts, reading artifacts/logs, summarizing runs, compacting context, or handing work…
git:20260911.c97bc57 · audit A · 57 stars
council SKILL.md skill
baphuongna/pi-crew · skills/council/SKILL.md · Spawn 3 adversarial subagents (Skeptic, Pragmatist, Critic) to evaluate a decision, architecture choice, or plan…
git:20260911.60e2cb9 · audit A · 57 stars
delegation-patterns SKILL.md skill
baphuongna/pi-crew · skills/delegation-patterns/SKILL.md · Subagent/team delegation workflow. When NOT to use: pure read-only investigation (use read-only-explorer); pre-planning…
git:20261022.2697a16 · audit A · 57 stars
distill-persona SKILL.md skill
baphuongna/pi-crew · skills/distill-persona/SKILL.md · Distill a person's (or field's) thinking into a runnable pi skill — research, extract, validate, generate. REQUIRED —…
git:20260911.c97bc57 · audit A · 57 stars
distill-software SKILL.md skill
baphuongna/pi-crew · skills/distill-software/SKILL.md · Distill software engineering expertise — an engineer's judgment, a codebase's conventions, or a domain's practice — and…
git:20260911.c97bc57 · audit A · 57 stars
event-log-tracing SKILL.md skill
baphuongna/pi-crew · skills/event-log-tracing/SKILL.md · Structured event logging for worker lifecycle, live agents, crash recovery. When NOT to use: high-level metrics…
git:20260911.c97bc57 · audit A · 57 stars
git-master SKILL.md skill
baphuongna/pi-crew · skills/git-master/SKILL.md · Commit and release hygiene for safe version-control work. When NOT to use: experimental branches (use…
git:20260911.c97bc57 · audit A · 57 stars
iterative-audit SKILL.md skill
baphuongna/pi-crew · skills/iterative-audit/SKILL.md · Iterative multi-round codebase audit with diminishing-returns detection. Run 5-20+ rounds, each focusing on one…
git:20260911.c97bc57 · audit A · 57 stars

Every file in baphuongna/pi-crew

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