prowl-workflow SKILL.md skillA
prowl-workflow from onevcat/prowl is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add onevcat/prowl/prowl-workflow@git:20261017.e04373ePins git:20261017.e04373e in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- onevcat/prowl
- Path
skills/prowl-workflow/SKILL.md- Versions recorded
- 7
- Latest version
- git:20261017.e04373e, committed Oct 17, 2026
- First version recorded
- Sep 8, 2026
- Size
- 12,026 bytes
- Repository stars
- 653
- License
- a license file GitHub does not identify
Author, validate, run, and participate in Prowl Agent Workflows — the `prowl.workflow/v1` bundles that orchestrate several live coding agents (launch, message, loop on verdicts, collect outputs, run built-in or local script actions) inside the running Prowl app. Use it to create, test, or debug a workflow action. Reach for this whenever the user wants a workflow created or edited ("write me a Prowl workflow that has two agents review each other", "add an input to the guessing-game workflow")…
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
# Prowl Agent Workflows A workflow is a `.pwlworkflow` directory with `workflow.yaml` (`schema: prowl.workflow/v1`) and optional local script actions, helpers, schemas, and assets. It declares roles and sequential steps, typed state, nested conditions and loops. Prowl executes it; agent roles use real terminal panes. Sources, later shadowing earlier by ID: app bundle (`prowl.*` reserved), user (`~/.prowl/workflows/*.pwlworkflow`), repo (`<repo root>/.prowl/workflows/*.pwlworkflow`). Pass bundle directories, not loose YAML files. Pick the section for the task; load a reference file only when that task is at hand: | Task | Where | | --- | --- | | Write or edit a workflow | read [references/authoring.md](references/authoring.md) first — full DSL, validator rules, patterns, worked example | | Create or test a script action | [references/actions.md](references/actions.md) — package layout, JSON protocol, approval, result records | | Start a workflow, inspect or debug a run, decode an error | [Running](#running-a-workflow) below; details in [references/runbook.md](references/runbook.md) | | A `[Prowl] …` line appeared in this pane | [Participating](#participating-in-a-run) below | …
Read the whole file at its exact version.
How to install
mdr add onevcat/prowl/prowl-workflow@sha256:a92aaebdf4c5961cThe line at the top of this page pins the label git:20261017.e04373e, 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.
[](https://markdownregistry.com/a/art_lg4e32pqkg5g2pwj)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Sep 8, 2026 and Oct 17, 2026, about one every 7 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261017.e04373e latest | 2026-10-17 | e04373e | 12,026 B | A | view · diff |
| git:20261014.bdcefe4 | 2026-10-14 | bdcefe4 | 10,914 B | A | view · diff |
| git:20260916.c8d92e0 | 2026-09-16 | c8d92e0 | 10,784 B | A | view · diff |
| git:20260910.05a0647 | 2026-09-10 | 05a0647 | 9,584 B | A | view · diff |
| git:20260909.fd5c7d7 | 2026-09-09 | fd5c7d7 | 9,643 B | A | view · diff |
| git:20260908.6f49e14 | 2026-09-08 | 6f49e14 | 9,637 B | A | view · diff |
| git:20260908.809eb97 | 2026-09-08 | 809eb97 | 9,558 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (12026 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
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_lg4e32pqkg5g2pwj GET https://markdownregistry.com/api/v1/resolve?ref=onevcat/prowl/prowl-workflow GET https://markdownregistry.com/api/v1/blob/a92aaebdf4c5961c4d4266fbfb90d04397a9d7a34a14cd93b250e8a4d825fa24
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.