self-verify-prowl SKILL.md skillA

self-verify-prowl from onevcat/prowl is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add onevcat/prowl/self-verify-prowl@git:20261002.cc9cd4a

Pins git:20261002.cc9cd4a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
onevcat/prowl
Path
.claude/skills/self-verify-prowl/SKILL.md
Versions recorded
5
Latest version
git:20261002.cc9cd4a, committed Oct 2, 2026
First version recorded
Jun 14, 2026
Size
9,914 bytes
Repository stars
653
License
a license file GitHub does not identify

Explicitly verify Prowl changes end to end in a separate Prowl Debug instance with a dedicated PROWL_CLI_SOCKET. Use only when the user explicitly requests self-verify-prowl or asks to run end-to-end verification against Prowl Debug. Do not invoke automatically after ordinary implementation work, and do not use it as a replacement for tests, make check, or make build-app.

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

# Self Verify Prowl

## Invocation Contract

Run this skill only after an explicit user request. A request to implement, fix, test, or build Prowl does not by itself
authorize this workflow.

This skill is an opt-in end-to-end layer on top of focused tests, `make check`, and `make build-app`. It launches a real
GUI app, reads shared user data, and is slower and less deterministic than those checks.

Use one of these final outcomes for every scenario:

- `PASS` — every stated assertion has direct evidence.
- `FAIL` — the observed result contradicts an assertion.
- `SKIPPED` — a declared capability or permission is unavailable, so no action was attempted.
- `INCONCLUSIVE` — the action ran, but the available evidence cannot prove or disprove the assertion.

Never turn missing evidence into `PASS`.

## Define the Scenario First

Before building or launching, write a small verification contract:

1. Setup — the worktree, initial tab or window, and required state.
2. Action — the exact CLI command or UI interaction.
3. Assertions — observable terminal text, JSON fields, accessibility state, or pixel-level result.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add onevcat/prowl/self-verify-prowl@sha256:4d4ffec99faf99fd

The line at the top of this page pins the label git:20261002.cc9cd4a, 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_3wgwdodlaaq22ks3.svg)](https://markdownregistry.com/a/art_3wgwdodlaaq22ks3)

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

Versions

The registry has recorded 5 versions of this file, between Jun 14, 2026 and Oct 2, 2026, about one every 28 days.

versioncommittedcommitsizeaudit
git:20261002.cc9cd4a latest2026-10-02 cc9cd4a 9,914 BA view · diff
git:20260801.ca5151e2026-08-01 ca5151e 9,905 BA view · diff
git:20260801.fb346c62026-08-01 fb346c6 9,429 BA view · diff
git:20260626.eefe59f2026-06-26 eefe59f 12,903 BA view · diff
git:20260614.b520c1b2026-06-14 b520c1b 12,749 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 (9914 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

onevcat/prowl · 653 stars · license a license file GitHub does not identify · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_3wgwdodlaaq22ks3
GET https://markdownregistry.com/api/v1/resolve?ref=onevcat/prowl/self-verify-prowl
GET https://markdownregistry.com/api/v1/blob/4d4ffec99faf99fdadb521b686effe1c341f2b37edf27226c8d598c48c2d9bc4

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 onevcat/prowl

prowl-ui SKILL.md skill
onevcat/prowl · .claude/skills/prowl-ui/SKILL.md · Explicitly inspect, operate, and iteratively improve the native Prowl Debug UI verification surface with agent-ctrl on…
git:20260802.b6da364 · audit A · 653 stars
release SKILL.md skill
onevcat/prowl · .claude/skills/release/SKILL.md · Build, sign, notarize, and publish a Prowl release.
git:20260917.72cdb96 · audit A · 653 stars
run-benchmark SKILL.md skill
onevcat/prowl · .claude/skills/run-benchmark/SKILL.md · Run Prowl's performance benchmark layers for the current branch or a release, compare against recorded baselines, and…
git:20261002.cc9cd4a · audit A · 653 stars
sync-docs SKILL.md skill
onevcat/prowl · .claude/skills/sync-docs/SKILL.md · Keep the agent-facing manual under docs/ in sync with the implementation. Diff-driven from a committed commit baseline…
git:20261002.cc9cd4a · audit A · 653 stars
sync-l10n SKILL.md skill
onevcat/prowl · .claude/skills/sync-l10n/SKILL.md · Bring the app string catalog in step with the code at release time - translate new UI copy with the project glossary…
git:20261002.cc9cd4a · audit A · 653 stars
write-ai-doc SKILL.md skill
onevcat/prowl · .claude/skills/write-ai-doc/SKILL.md · Create and maintain curated docs-ai/ records for substantial features and non-trivial, decision-shaping fixes (numbered…
git:20261018.8a15bff · audit A · 653 stars
AGENTS.md AGENTS.md file
onevcat/prowl · AGENTS.md
git:20261018.8a15bff · audit A · 653 stars
CLAUDE.md CLAUDE.md file
onevcat/prowl · CLAUDE.md
git:20260120.00eddd5 · audit B · 653 stars
prowl-cli SKILL.md skill
onevcat/prowl · skills/prowl-cli/SKILL.md · Use the Prowl CLI (`prowl`) to inspect or control a running Prowl GUI app and the agent sessions it hosts. Prowl runs…
git:20261019.8fbbd70 · audit A · 653 stars
prowl-workflow SKILL.md skill
onevcat/prowl · skills/prowl-workflow/SKILL.md · Author, validate, run, and participate in Prowl Agent Workflows — the `prowl.workflow/v1` bundles that orchestrate…
git:20261017.e04373e · audit A · 653 stars

Every file in onevcat/prowl

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