write-skill-eval SKILL.md skillA
write-skill-eval from mattbrailsford/umbraco-devkit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add mattbrailsford/umbraco-devkit/write-skill-eval@git:20261018.616fa5ePins git:20261018.616fa5e in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- mattbrailsford/umbraco-devkit
- Path
.claude/skills/write-skill-eval/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261018.616fa5e, committed Oct 18, 2026
- First version recorded
- Oct 17, 2026
- Size
- 11,083 bytes
- Repository stars
- 3
- License
- MIT
Repo-only guide to writing an eval case for one of this devkit's skills, running it with and without the plugin, and proving each grader can fail before trusting its score. Use when the user asks to add, write, or fix an eval, test whether a skill earns its place, or close a gap that `scripts/check-evals.sh` reports. Not shipped with the plugin.
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
# Write a skill eval
An eval case earns its place when plain Claude fails it and the skill fixes that. The
process: start from a real failure, set up the scenario, prove plain Claude fails, write the
smallest rule that fills the gap, prove the skill fixes it and actually loaded, then keep the
case as a guard. Follow the eval rules in `CLAUDE.md` ("No build, lint, or test step")
throughout; this skill is the order to apply them in.
## 1. Start from a real failure
Begin with something Claude got wrong, not with the skill's text:
- **Knowledge skill:** a bug that shipped in a package, or a mistake Claude was seen making.
Tag a shipped bug's case `real-bug`. Writing a case from a rule you already have only
shows the rule gets loaded, not that it's needed.
- **Workflow skill** (`feature-*`, `quick-fix`, `issue-*`, ...): a rule the skill must keep,
such as stopping when its input is missing or never touching git.
One case tests one behavior. If you find two, write two cases.
## 2. Write the prompt
Create `plugins/umbraco-devkit/evals/<case-name>/prompt.md`. Name the case like its
neighbors: the skill's short name, then what it tests (`env-sync-access-rules`).
```markdown
…Read the whole file at its exact version.
How to install
mdr add mattbrailsford/umbraco-devkit/write-skill-eval@sha256:9bc06ac4a54d4569The line at the top of this page pins the label git:20261018.616fa5e, 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_2uenkjpjzi5viamz)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Oct 17, 2026 and Oct 18, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261018.616fa5e latest | 2026-10-18 | 616fa5e | 11,083 B | A | view · diff |
| git:20261017.10def4c | 2026-10-17 | 10def4c | 10,678 B | A | view · diff |
| git:20261017.8be9de3 | 2026-10-17 | 8be9de3 | 8,999 B | A | view · diff |
| git:20261017.315ef95 | 2026-10-17 | 315ef95 | 8,931 B | A | view · diff |
| git:20261017.dff582d | 2026-10-17 | dff582d | 8,283 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 (11083 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
mattbrailsford/umbraco-devkit · 3 stars · license MIT · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_2uenkjpjzi5viamz GET https://markdownregistry.com/api/v1/resolve?ref=mattbrailsford/umbraco-devkit/write-skill-eval GET https://markdownregistry.com/api/v1/blob/9bc06ac4a54d456961a05ad9713f114fcb1368f1666f9e002d8e909bd21b7f55
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.