evaluator SKILL.md skillA
evaluator from dayvisonassis/sdd-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add dayvisonassis/sdd-skills/evaluator@git:20261013.fceb1bfPins git:20261013.fceb1bf in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- dayvisonassis/sdd-skills
- Path
skills/evaluator/SKILL.md- Versions recorded
- 10
- Latest version
- git:20261013.fceb1bf, committed Oct 13, 2026
- First version recorded
- Sep 30, 2026
- Size
- 40,538 bytes
- Repository stars
- 3
- License
- MIT
Externally evaluates an already-implemented feature against its contract.md (environment, quality gates, coverage manifest, observable criteria), producing screenshots, a report, and chat findings. Owns the evaluation loop — keeps the attempt counter in progress.json, decides the state (CLEAN/FAIL/PENDING/ABORTED), and routes each failure: code failures (gate/observable) to fix-runner, test failures to the matching test-writer (then confirmed by the matching test-validator) before resuming.…
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
# Evaluator A second, independent layer of validation. After `implement-feature` finishes a feature, the `evaluator` looks at it **from the outside** and confirms — against `contract.md` — whether the delivery conforms. It finds deviations the implementer's self-check missed. It **does not fix code**; it evaluates and **orchestrates the correction loop**, dispatching `fix-runner` on failure. > Base docs: `https://github.com/dayvisonassis/sdd-skills/blob/main/docs/Skill_Evaluator.md` (full rationale), > `https://github.com/dayvisonassis/sdd-skills/blob/main/docs/Contrato_de_Feature.md` (contract structure), > `https://github.com/dayvisonassis/sdd-skills/blob/main/docs/Como_criar_gates.md` (gates), > `https://github.com/dayvisonassis/sdd-skills/blob/main/docs/ARQUITETURA_DAS_SKILLS.md` (flow, states, progress.json schema). > Report schema: `references/evaluation-report-schema.md`. The evaluator complements automated tests — it does not replace them. ## INPUT Free-form. The skill needs: - **The target feature** (ID/name) — explicit and required. Abort if absent or ambiguous (list candidates). …
Read the whole file at its exact version.
How to install
mdr add dayvisonassis/sdd-skills/evaluator@sha256:c8f956b2d0696b09The line at the top of this page pins the label git:20261013.fceb1bf, 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_qp2kevtfj7djafof)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 10 versions of this file, between Sep 30, 2026 and Oct 13, 2026, about one every day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261013.fceb1bf latest | 2026-10-13 | fceb1bf | 40,538 B | A | view · diff |
| git:20261013.ace2f8a | 2026-10-13 | ace2f8a | 36,893 B | A | view · diff |
| git:20261013.7e0f408 | 2026-10-13 | 7e0f408 | 34,953 B | A | view · diff |
| git:20261012.d370df0 | 2026-10-12 | d370df0 | 32,655 B | A | view · diff |
| git:20261012.e7232f7 | 2026-10-12 | e7232f7 | 32,101 B | A | view · diff |
| git:20261004.5bbf263 | 2026-10-04 | 5bbf263 | 27,487 B | A | view · diff |
| git:20260930.17fecc4 | 2026-09-30 | 17fecc4 | 27,418 B | A | view · diff |
| git:20260930.6c16e8c | 2026-09-30 | 6c16e8c | 22,747 B | A | view · diff |
| git:20260930.d5a6f72 | 2026-09-30 | d5a6f72 | 22,745 B | A | view · diff |
| git:20260930.42fb58d | 2026-09-30 | 42fb58d | 22,607 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 (40538 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
dayvisonassis/sdd-skills · 3 stars · license MIT · pushed 2026-10-13 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_qp2kevtfj7djafof GET https://markdownregistry.com/api/v1/resolve?ref=dayvisonassis/sdd-skills/evaluator GET https://markdownregistry.com/api/v1/blob/c8f956b2d0696b0977070aeeb1fa17ac1be7e1f3dd998a861c26bf136135911f
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 dayvisonassis/sdd-skills
Every file in dayvisonassis/sdd-skills