ar-board SKILL.md skillB
ar-board from dvwinck/capybara-toolbox is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add dvwinck/capybara-toolbox/ar-board@git:20261103.fd1d0dePins git:20261103.fd1d0de in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- dvwinck/capybara-toolbox
- Path
plugins/ar-board/skills/ar-board/SKILL.md- Versions recorded
- 6
- Latest version
- git:20261103.fd1d0de, committed Nov 3, 2026
- First version recorded
- Oct 12, 2026
- Size
- 13,730 bytes
- Repository stars
- 33
- License
- MIT
Starts a local approve/reject web panel (AR board) where the user judges many agent proposals one by one, then reads the decisions from disk. Use when the user wants to judge several options one at a time (ideas, templates, features, agent-architecture improvements, video themes, visual variations) with A/R keys and a comment per item, or wants to train an agent on their preferences. Triggers - /ar-board, /ar-board:ar-board, "ar board", "AR board", "approve/reject board…
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
# AR board (approval/rejection board) You propose N things. This skill turns that into one fast, informed decision. You write the items as JSON and start a local web panel. The user approves (A), rejects (R) or marks "maybe" (M) item by item, and comments why. When the user says "done" (the panel's banner asks for "done"; the pt-BR panel asks for "terminei"), you read the decisions straight from disk. The user never repeats anything. The comments are the most valuable output: they become reusable preferences. Reply to the user in the user's language. Write card content (titles, fields, risks, concepts) in that language too. The panel's own buttons and labels exist in English (the default) and in pt-BR: set `"lang": "pt-BR"` in the batch when the user writes in Portuguese, and `"lang": "en"` (or omit it) otherwise. The user can also switch the panel with the EN/PT toggle in its header; that never changes the cards. The command line (`check`, `summary`, `wait`) speaks the batch's `lang` too (`--lang` overrides it on every command). The panel and command-line literals below are written in English first, with the pt-BR wording next to them. ## When to use (and when not to) …
Read the whole file at its exact version.
How to install
mdr add dvwinck/capybara-toolbox/ar-board@sha256:a9b6c165fa1644dfThe line at the top of this page pins the label git:20261103.fd1d0de, 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_verjyjfjyccytetk)
9 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Oct 12, 2026 and Nov 3, 2026, about one every 4 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261103.fd1d0de latest | 2026-11-03 | fd1d0de | 13,730 B | B | view · diff |
| git:20261023.95dc2aa | 2026-10-23 | 95dc2aa | 11,936 B | B | view · diff |
| git:20261015.3abc430 | 2026-10-15 | 3abc430 | 11,062 B | B | view · diff |
| git:20261015.8b64526 | 2026-10-15 | 8b64526 | 10,606 B | B | view · diff |
| git:20261012.339af31 | 2026-10-12 | 339af31 | 9,391 B | B | view · diff |
| git:20261012.0f2971d | 2026-10-12 | 0f2971d | 8,935 B | B | view |
Audit of the latest version
- fail: No link to a raw IP address (matched: http://127.0.0.1)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (13730 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 script tag
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
dvwinck/capybara-toolbox · 33 stars · license MIT · pushed 2026-11-03 · branch base
API
GET https://markdownregistry.com/api/v1/artifacts/art_verjyjfjyccytetk GET https://markdownregistry.com/api/v1/resolve?ref=dvwinck/capybara-toolbox/ar-board GET https://markdownregistry.com/api/v1/blob/a9b6c165fa1644df9b4b39f1d7bb3c63a304c459159c0be52669cb4c0ddeb768
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.