spec-evaluator SKILL.md skillA
spec-evaluator from nguyenvanphituoc/shapeup-sdlc-plugin is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add nguyenvanphituoc/shapeup-sdlc-plugin/spec-evaluator@git:20261108.7150974Pins git:20261108.7150974 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- nguyenvanphituoc/shapeup-sdlc-plugin
- Path
skills/spec-evaluator/SKILL.md- Versions recorded
- 19
- Latest version
- git:20261108.7150974, committed Nov 8, 2026
- First version recorded
- Aug 13, 2026
- Size
- 19,251 bytes
- Repository stars
- 3
- License
- MIT
Use this skill whenever the user wants to evaluate, QA, or verify that an implemented task actually matches its spec and acceptance criteria — the judge in a planner→generator→evaluator harness. Trigger on: "evaluate task TASK-NNN", "QA TASK-NNN", "verify against spec", "check acceptance criteria", "does this match the spec", "grade this build", "run evaluator", or a loop --order dispatch. Skeptical by default — absence of evidence is a FAIL; probes the running app and files file:line bugs.
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
# Spec Evaluator (the single judge, pure worker v1.0) **Assume broken until proven working. Grade evidence, not claims. Return data, not writes.** The **judge** in a planner → generator → evaluator loop. It reads the committed spec, exercises the **running** app, and returns a hard-threshold verdict plus a file:line bug list — as a WorkResult envelope the orchestrator applies. The generator fixes; the evaluator re-runs. **Core guarantee — skeptical by default.** Out-of-the-box an LLM is a lenient QA: it finds a real defect, then talks itself into approving anyway. This skill inverts that posture. A criterion with no collected evidence is a **FAIL**, never a pass-by-assumption. > **Anti-leniency protocol** → `references/anti-leniency.md` — read before printing any verdict. > **Verdict ledger (re-probe + confidence + flip detection)** → `references/verdict-ledger.md`. > **Dimension contract (injection interface)** → `references/dimension-contract.md`. > Where any reference file describes *writing* shared state (task files, `.verdicts` ledger, > run-state), the pure-worker contract overrides it: that data returns in the WorkResult and …
Read the whole file at its exact version.
How to install
mdr add nguyenvanphituoc/shapeup-sdlc-plugin/spec-evaluator@sha256:d60a80009eadb825The line at the top of this page pins the label git:20261108.7150974, 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_3hy5l7p6ihhn5hwr)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 19 versions of this file, between Aug 13, 2026 and Nov 8, 2026, about one every 5 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261108.7150974 latest | 2026-11-08 | 7150974 | 19,251 B | A | view · diff |
| git:20261108.d2c957e | 2026-11-08 | d2c957e | 19,259 B | A | view · diff |
| git:20261108.7da9840 | 2026-11-08 | 7da9840 | 19,379 B | A | view · diff |
| git:20261107.d77501f | 2026-11-07 | d77501f | 19,542 B | A | view · diff |
| git:20260929.09b5ec8 | 2026-09-29 | 09b5ec8 | 19,547 B | A | view · diff |
| git:20260929.f6f6bda | 2026-09-29 | f6f6bda | 19,434 B | A | view · diff |
| git:20260928.dcf3619 | 2026-09-28 | dcf3619 | 19,275 B | A | view · diff |
| git:20260928.61f7c4a | 2026-09-28 | 61f7c4a | 19,142 B | A | view · diff |
| git:20260927.f34b229 | 2026-09-27 | f34b229 | 18,746 B | A | view · diff |
| git:20260926.fd76c9b | 2026-09-26 | fd76c9b | 18,309 B | A | view · diff |
| git:20260926.33b048f | 2026-09-26 | 33b048f | 17,913 B | A | view · diff |
| git:20260926.eb56d6a | 2026-09-26 | eb56d6a | 17,524 B | A | view · diff |
| git:20260926.9d0a757 | 2026-09-26 | 9d0a757 | 17,303 B | A | view · diff |
| git:20260925.665a891 | 2026-09-25 | 665a891 | 16,857 B | A | view · diff |
| git:20260919.9106bc8 | 2026-09-19 | 9106bc8 | 15,609 B | A | view · diff |
| git:20260910.a95e85f | 2026-09-10 | a95e85f | 14,696 B | A | view · diff |
| git:20260817.86d4174 | 2026-08-17 | 86d4174 | 14,612 B | A | view · diff |
| git:20260814.4b8b353 | 2026-08-14 | 4b8b353 | 13,652 B | A | view · diff |
| git:20260813.0e41b77 | 2026-08-13 | 0e41b77 | 13,678 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 (19251 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
nguyenvanphituoc/shapeup-sdlc-plugin · 3 stars · license MIT · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_3hy5l7p6ihhn5hwr GET https://markdownregistry.com/api/v1/resolve?ref=nguyenvanphituoc/shapeup-sdlc-plugin/spec-evaluator GET https://markdownregistry.com/api/v1/blob/d60a80009eadb825e0219d2788486ed006efa603792e7b216a0b3ee989a2e521
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.