dough-slice-plan-refinement SKILL.md skillA
dough-slice-plan-refinement from nerds-odd-e/doughnut is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add nerds-odd-e/doughnut/dough-slice-plan-refinement@git:20261020.55007daPins git:20261020.55007da in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- nerds-odd-e/doughnut
- Path
.agents/skills/dough-slice-plan-refinement/SKILL.md- Versions recorded
- 14
- Latest version
- git:20261020.55007da, committed Oct 20, 2026
- First version recorded
- Sep 8, 2026
- Size
- 7,820 bytes
- Repository stars
- 50
- License
- MIT
Refines an executable plan in place into proportionate, proof-owned Behavior/Structure slices. Use during or after dough-slice-planning when boundaries fragment cohesive work, combine independent concerns, accumulate special cases, or overrun. Creates no new plan and preserves the selected story or bounded correction outcome. After rewriting the plan, reassess readiness through the shared preparation procedure without granting Take or execution.
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
# Slice-plan refinement Refine an existing executable plan in place. Do not create another plan, implement product code, or change its selected story or bounded correction outcome. ## Require a refinable plan Require an existing executable plan and this project's context required by [dough-slice-planning](../dough-slice-planning/SKILL.md), especially any supplied target, hard limit, exceptions, overrun policy, and the plan lifecycle. Identify whether the plan's source is a selected feature story or a bounded retrospective correction under [planning scope and lifecycle](../dough-story-refinement/references/planning.md#choose-the-planning-level). For a complete correction, use its correction input directly from its story and plan, or from a plan-homed correction's plan alone; create no seed. Name whichever required correction field is missing and stop. A complete plan permits refinement, not execution; preserve the invoking instruction's authorization boundary. Before revising boundaries, apply the shared [reassessment decision](../dough-execute-plan/references/execution-decisions.md#reassess-before-extending-work). - If no plan exists, use `dough-slice-planning`. …
Read the whole file at its exact version.
How to install
mdr add nerds-odd-e/doughnut/dough-slice-plan-refinement@sha256:94519a7400b1ce7bThe line at the top of this page pins the label git:20261020.55007da, 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_ktn5cn54xgren6no)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 14 versions of this file, between Sep 8, 2026 and Oct 20, 2026, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261020.55007da latest | 2026-10-20 | 55007da | 7,820 B | A | view · diff |
| git:20261011.8ac439b | 2026-10-11 | 8ac439b | 7,345 B | A | view · diff |
| git:20260928.f0a795c | 2026-09-28 | f0a795c | 6,959 B | A | view · diff |
| git:20260926.916e56c | 2026-09-26 | 916e56c | 6,949 B | A | view · diff |
| git:20260926.d290a66 | 2026-09-26 | d290a66 | 6,946 B | A | view · diff |
| git:20260922.7e7bbcc | 2026-09-22 | 7e7bbcc | 6,786 B | A | view · diff |
| git:20260921.783382a | 2026-09-21 | 783382a | 5,990 B | A | view · diff |
| git:20260913.4b89109 | 2026-09-13 | 4b89109 | 5,617 B | A | view · diff |
| git:20260911.c7f6165 | 2026-09-11 | c7f6165 | 5,450 B | A | view · diff |
| git:20260910.0e59fc4 | 2026-09-10 | 0e59fc4 | 5,071 B | A | view · diff |
| git:20260910.e09bb13 | 2026-09-10 | e09bb13 | 4,111 B | A | view · diff |
| git:20260910.592db5c | 2026-09-10 | 592db5c | 3,496 B | A | view · diff |
| git:20260909.3784459 | 2026-09-09 | 3784459 | 3,429 B | A | view · diff |
| git:20260908.f2be7c0 | 2026-09-08 | f2be7c0 | 3,325 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 (7820 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
nerds-odd-e/doughnut · 50 stars · license MIT · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ktn5cn54xgren6no GET https://markdownregistry.com/api/v1/resolve?ref=nerds-odd-e/doughnut/dough-slice-plan-refinement GET https://markdownregistry.com/api/v1/blob/94519a7400b1ce7b211c4b96dd78648901400465b45d8696103bdd88f96c856f
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.