write-eval SKILL.md skillA

write-eval from dzhng/duet-agent is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add dzhng/duet-agent/write-eval@git:20261002.2075ed7

Pins git:20261002.2075ed7 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
dzhng/duet-agent
Path
.agents/skills/write-eval/SKILL.md
Versions recorded
6
Latest version
git:20261002.2075ed7, committed Oct 2, 2026
First version recorded
Jun 5, 2026
Size
17,426 bytes
Repository stars
50
License
Apache-2.0

Write a live eval for new or changed runner/agent behavior using red/green TDD plus a falsification check that proves the eval fails when the behavior is broken. Use whenever you add or modify behavior that should be covered by an eval, when asked to "write an eval", "add an eval", "cover this with an eval", or after landing a feature that needs end-to-end proof it works.

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 an Eval

An eval is only trustworthy if you have seen it both **fail for the right reason** and **pass for the right reason**. Writing the assertions, watching them go green once, and moving on is how you ship an eval that passes whether or not the feature works. The standard operating procedure is: pick the outermost entry point, design the assertion so it can only hold when the behavior is present, watch it go green, then **falsify** — break the production code, confirm the eval goes red with a diagnostic that points at the real path, and restore.

This is the flow used to land `evals/state-machine-slash-skill-expansion.eval.ts`; read it as the reference implementation for a **deterministic wiring** eval (the feature either injects the right context or it doesn't).
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add dzhng/duet-agent/write-eval@sha256:1f0fd512633a77bb

The line at the top of this page pins the label git:20261002.2075ed7, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_soyafclgjb5k5ypw.svg)](https://markdownregistry.com/a/art_soyafclgjb5k5ypw)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 6 versions of this file, between Jun 5, 2026 and Oct 2, 2026, about one every 24 days.

versioncommittedcommitsizeaudit
git:20261002.2075ed7 latest2026-10-02 2075ed7 17,426 BA view · diff
git:20260928.3181c052026-09-28 3181c05 15,664 BA view · diff
git:20260708.65758052026-07-08 6575805 15,668 BA view · diff
git:20260605.7f516fc2026-06-05 7f516fc 15,595 BA view · diff
git:20260605.94635622026-06-05 9463562 12,868 BA view · diff
git:20260605.6e90e7a2026-06-05 6e90e7a 12,867 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (17426 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

GitHub

dzhng/duet-agent · 50 stars · license Apache-2.0 · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_soyafclgjb5k5ypw
GET https://markdownregistry.com/api/v1/resolve?ref=dzhng/duet-agent/write-eval
GET https://markdownregistry.com/api/v1/blob/1f0fd512633a77bbbfce1d57a95d7bff132517c09aecafd6566425d4022e1333

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 dzhng/duet-agent

audit-agents SKILL.md skill
dzhng/duet-agent · .agents/skills/audit-agents/SKILL.md · Audit or rewrite AGENTS.md so it holds only lasting principles. Run it only when the user asks for it by name; never…
git:20261002.bbef714 · audit A · 50 stars
audit-choices SKILL.md skill
dzhng/duet-agent · .agents/skills/audit-choices/SKILL.md · Audit the choices an implementing agent made, not its diff — a pure decision audit that traces the session's history…
git:20260813.f2a4f7b · audit A · 50 stars
audit-tests SKILL.md skill
dzhng/duet-agent · .agents/skills/audit-tests/SKILL.md · Audit whether tests earn their maintenance cost and which suite owns each contract. Use when pruning redundant tests…
git:20261002.7680dea · audit A · 50 stars
claude SKILL.md skill
dzhng/duet-agent · .agents/skills/claude/SKILL.md · Use Claude Code as an independent `claude -p` subagent when the user explicitly asks for Claude, wants a second-agent…
git:20261015.0e6cd08 · audit A · 50 stars
close-spec SKILL.md skill
dzhng/duet-agent · .agents/skills/close-spec/SKILL.md · When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec)…
git:20260721.6692189 · audit A · 50 stars
code-review SKILL.md skill
dzhng/duet-agent · .agents/skills/code-review/SKILL.md · Review changed code for naming, stale references, unnecessary complexity, and comment quality. Use after completing…
git:20261021.e955131 · audit A · 50 stars
codex SKILL.md skill
dzhng/duet-agent · .agents/skills/codex/SKILL.md · Use the local Codex CLI as an independent second agent. Two branches — (1) proactively run `codex review` for a second…
git:20261020.37d28d9 · audit A · 50 stars
compare-screenshots SKILL.md skill
dzhng/duet-agent · .agents/skills/compare-screenshots/SKILL.md · Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for…
git:20261014.dcaa49d · audit A · 50 stars
debug-memory SKILL.md skill
dzhng/duet-agent · .agents/skills/debug-memory/SKILL.md · Reproduce observational-memory bugs (reflection, recall, observer, freshness, eviction) by dumping the live…
git:20260525.773900d · audit A · 50 stars
design-with-images SKILL.md skill
dzhng/duet-agent · .agents/skills/design-with-images/SKILL.md · Explore UI and visual design with image generation, then iterate the real implementation against the user-selected…
git:20261002.7680dea · audit A · 50 stars
eli5 SKILL.md skill
dzhng/duet-agent · .agents/skills/eli5/SKILL.md · Explain a technical spec or proposed change in plain language: what problem it solves, how the solution works, and…
git:20260813.f2a4f7b · audit A · 50 stars
eval-skills SKILL.md skill
dzhng/duet-agent · .agents/skills/eval-skills/SKILL.md · Eval and improve a skill against golden cases — run the target skill blind in a fresh, context-free subagent on each…
git:20260717.934babf · audit A · 50 stars

Every file in dzhng/duet-agent

Browse by kind, by grade A, or by owner.