decision/q-problem-runner SKILL.md skillA
decision/q-problem-runner from lulufoo/lulu-workflow is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add lulufoo/lulu-workflow/decision/q-problem-runner@git:20260930.a7c6e38Pins git:20260930.a7c6e38 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- lulufoo/lulu-workflow
- Path
decision/runners/q-problem-runner/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260930.a7c6e38, committed Sep 30, 2026
- First version recorded
- Sep 26, 2026
- Size
- 1,712 bytes
- Repository stars
- 3
- License
- MIT
Internal runner for the Decision Q gate.
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
# q-problem-runner Produce a clear problem definition. Complete when the user confirms the problem statement. ## Prerequisites - Run `$GATE_CONTROL resolve-context`; pin `$CTX` (`active_gate` is `Q`). - Apply `$CTX.domain_constraints` (`objective`, `role.instruction`, `domain.instruction`) to the dialogue. - Before the first probe, read `$SKILL_ROOT/shared/references/ask-protocol.md`; apply it to every probe. ## Must hold | ID | Must hold | |----|-----------| | `G-problem` | A clear problem definition: what triggered this decision, and what problem we are solving. | A merely stated problem claim is not a pass. Evaluate from the conversation so far. ## Modes | Mode | When | Behavior | |------|------|----------| | `probe` | `G-problem` not yet clear | Apply ask-protocol. | | `summarize` | `G-problem` clear | Restate the problem once; ask if correct. | | `close` | User confirms summarize | `$GATE_CONTROL gate-close --gate Q --payload '<json>'` | If the user rejects the summary: treat the denied point as a gap → `probe`. ## Signals Apply Decision [Signals](../../SKILL.md#signals) throughout Q. ## Act …
Read the whole file at its exact version.
How to install
mdr add lulufoo/lulu-workflow/decision/q-problem-runner@sha256:729d33915e4a1d12The line at the top of this page pins the label git:20260930.a7c6e38, 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_j3abhg5hbwgloulb)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Sep 26, 2026 and Sep 30, 2026, about one every 2 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260930.a7c6e38 latest | 2026-09-30 | a7c6e38 | 1,712 B | A | view · diff |
| git:20260927.0e88d70 | 2026-09-27 | 0e88d70 | 1,703 B | A | view · diff |
| git:20260926.09b7c01 | 2026-09-26 | 09b7c01 | 1,608 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 (1712 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
lulufoo/lulu-workflow · 3 stars · license MIT · pushed 2026-10-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_j3abhg5hbwgloulb GET https://markdownregistry.com/api/v1/resolve?ref=lulufoo/lulu-workflow/decision/q-problem-runner GET https://markdownregistry.com/api/v1/blob/729d33915e4a1d1299aadee570962c1fa74b649d39ef5c8e733fc347f99de237
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.