workshop-grill SKILL.md skillA

workshop-grill from frolad/tars is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add frolad/tars/workshop-grill@git:20261104.96c9a51

Pins git:20261104.96c9a51 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
frolad/tars
Path
skills/workshop-grill/SKILL.md
Versions recorded
1
Latest version
git:20261104.96c9a51, committed Nov 4, 2026
Size
7,769 bytes
Repository stars
3
License
MIT

TARS interview procedure. Maps a plan as a design tree and puts its open decisions to the user in numbered rounds, each question with a recommended answer, until nothing is silently assumed; the agent finds the facts itself. workshop-craft loads it to grill a task's scope and split, and workshop-forge loads its light mode for the mini grill before each iteration. Use it when workshop-craft or workshop-forge calls for it, or when the user mentions "workshop grill" or "grill workshop" or types…

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

sttp applies. A grill reaches a shared understanding of a plan before anything is built. The facts are yours to find; the decisions are the user's. The grill itself edits nothing: what gets written, and when, is decided by the skill that loaded it.

## Before the first round

- Read the sources in full: the plan, the documents it names, the code it touches. A question asked from half a source is often answered in the other half.
- The first round confirms the intent. State your reading of the goal, and of what the thing is for, as recommended answers the user can correct. No detail question (names, file formats, layouts) comes before the intent is shared: details decided against a misread goal get decided twice.

## Rounds

Map the subject as a design tree: every decision branches into the decisions that hang off it. The frontier is every decision whose prerequisites are settled, the questions that can be asked now without guessing at answers not heard yet.

- Ask the whole frontier in one round. Number each question and give a recommended answer. Then stop and wait for the answers.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add frolad/tars/workshop-grill@sha256:9c184fdfeba3656f

The line at the top of this page pins the label git:20261104.96c9a51, 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_vrmbryr7wb5qr3ru.svg)](https://markdownregistry.com/a/art_vrmbryr7wb5qr3ru)

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

Versions

The registry has recorded 1 version of this file, committed on Nov 4, 2026.

versioncommittedcommitsizeaudit
git:20261104.96c9a51 latest2026-11-04 96c9a51 7,769 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 (7769 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

frolad/tars · 3 stars · license MIT · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_vrmbryr7wb5qr3ru
GET https://markdownregistry.com/api/v1/resolve?ref=frolad/tars/workshop-grill
GET https://markdownregistry.com/api/v1/blob/9c184fdfeba3656f6fb32cc536c1db98692854fb0964e585315d1f07e159f492

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 frolad/tars

sttp-enforce SKILL.md skill
frolad/tars · skills/sttp-enforce/SKILL.md · Bring the files under a path to sttp's rules. The first turn analyses the files and lists what sttp would change, by…
git:20261104.96c9a51 · audit A · 3 stars
sttp-guards SKILL.md skill
frolad/tars · skills/sttp-guards/SKILL.md · Show or switch the TARS git guard. "off" stops it from checking git steps in this session; "on" turns it back on…
git:20261104.96c9a51 · audit A · 3 stars
sttp-mode SKILL.md skill
frolad/tars · skills/sttp-mode/SKILL.md · Show or set the STTP mode. "primary" applies STTP to the main thread only (default), "full" also to subagents. No…
git:20261104.96c9a51 · audit A · 3 stars
sttp-software-coding SKILL.md skill
frolad/tars · skills/sttp-software-coding/SKILL.md · Straight To The Point coding. Applies when writing or editing code, in chat or in files. The smallest change that does…
git:20261106.8fbeeda · audit A · 3 stars
sttp-software-engineering SKILL.md skill
frolad/tars · skills/sttp-software-engineering/SKILL.md · Straight To The Point engineering conduct. Applies to any engineering work - debugging, investigating, reviewing…
git:20261104.96c9a51 · audit A · 3 stars
sttp-software-testing SKILL.md skill
frolad/tars · skills/sttp-software-testing/SKILL.md · Straight To The Point testing, built on test-driven development. Applies whenever tests are written, changed or judged…
git:20261104.96c9a51 · audit A · 3 stars
sttp SKILL.md skill
frolad/tars · skills/sttp/SKILL.md · Answer first, only the subject, normal grammar. No preamble, flattery, hedging filler, self-narration, recap, or…
git:20261104.96c9a51 · audit A · 3 stars
tars-doctor SKILL.md skill
frolad/tars · skills/tars-doctor/SKILL.md · Checks that STTP works in this session and is back on course. Reloads the STTP rules and the running TARS skills that…
git:20261104.96c9a51 · audit A · 3 stars
workshop-craft SKILL.md skill
frolad/tars · skills/workshop-craft/SKILL.md · Define a complex task with the user and write its blueprint, the split into pipelines and iterations, for…
git:20261104.96c9a51 · audit A · 3 stars
workshop-forge SKILL.md skill
frolad/tars · skills/workshop-forge/SKILL.md · Build one pipeline of a task with the user, one reviewed iteration per turn, from an workshop-craft blueprint or from…
git:20261104.96c9a51 · audit A · 3 stars
workshop-glossary-bootstrap SKILL.md skill
frolad/tars · skills/workshop-glossary-bootstrap/SKILL.md · Build the glossary of an existing project with the user, area by area, and ADRs for the surprising decisions the user…
git:20261104.96c9a51 · audit A · 3 stars
workshop-glossary SKILL.md skill
frolad/tars · skills/workshop-glossary/SKILL.md · TARS project glossary and ADRs. Keeps the project's terms in docs/GLOSSARY.md and the decisions that outlive a task as…
git:20261104.96c9a51 · audit A · 3 stars

Every file in frolad/tars

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