Home / different-ai / openwork · .opencode/skills/write-a-spec/SKILL.md · GitHub

write-a-spec skillA

write-a-spec is agent-read markdown (skill) from different-ai/openwork: Write or extend an E2E journey spec in evals/specs that proves a PR's change to a human reviewer. Use when a PR changes user-visible behaviour, when a reviewer asks "show me", or when the coverage decision says a journey is missing..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Skill: Write a Spec

Every `evals/specs/**/*.e2e.test.ts` a PR adds or changes runs in CI on the PR
head and is published as that PR's proof (private report + one PR comment).
Write the spec for the person who will read that report in thirty seconds,
not for the machine that runs it.

## Do not write one when…

- An existing journey covers the behaviour: extend it. One spec per user
  journey, not per PR; bug fixes add a step to the journey they escaped from.
- The change is a pure function: write a colocated unit test, not evidence.
- You would import `../../apps|packages|ee`, read source files, or spawn another
  runner. That is a unit test in disguise; the boundary ratchet rejects it.

No UI does not mean no spec. A server, proxy, or protocol bug gets a
browser-less world (see `evals/specs/session-title-recovery.test.ts`); the
steps still read as one person's before → after.

## The proof shape

A proof answers: **who** can now do **what** they could not before, and who
still cannot. Structure every spec as that story. Each beat is one `step()`
with a claim-sized name; each visual beat ends in `user.screenshot()`.

```
…

Read the whole file at its exact version.

How to install

Latest version
mdr add different-ai/openwork/write-a-spec@git:20260921.bbe08f8
Exact content
mdr add different-ai/openwork/write-a-spec@sha256:c046ec19fbe53950

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ym7chbqpj54tpb4y.svg)](https://markdownregistry.com/a/art_ym7chbqpj54tpb4y)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260921.bbe08f8 latest2026-09-21 bbe08f8 10,397 BA view · diff
git:20260921.8da7a962026-09-21 8da7a96 6,832 BA view · diff
git:20260920.e7594622026-09-20 e759462 5,761 BA view · diff
git:20260904.13c282d2026-09-04 13c282d 3,028 BA view · diff
git:20260904.25c10142026-09-04 25c1014 2,560 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, 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 (10397 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

different-ai/openwork · 23,724 stars · license NOASSERTION · pushed 2026-09-25 · branch dev

API

GET https://markdownregistry.com/api/v1/artifacts/art_ym7chbqpj54tpb4y
GET https://markdownregistry.com/api/v1/resolve?ref=different-ai/openwork/write-a-spec
GET https://markdownregistry.com/api/v1/blob/c046ec19fbe53950e30a9e1ba4eb917f182b10d98a81923cdb0475ccaeab9465

Your agent 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.

More from different-ai/openwork

browser-automation skill
different-ai/openwork · .opencode/skills/browser-automation/SKILL.md · Local OpenWork Electron browser automation with CDP. Use when driving a local Electron dev app, browser_list…
git:20260904.25c1014 · audit B · 23,724 stars
create-plugin skill
different-ai/openwork · .opencode/skills/create-plugin/SKILL.md · Create an OpenCode plugin for OpenWork. Scaffolds the plugin file with the correct API shape, tool definitions, and…
git:20260602.20013d2 · audit A · 23,724 stars
daytona-seeded-cloud-demo skill
different-ai/openwork · .opencode/skills/daytona-seeded-cloud-demo/SKILL.md · Daytona seeded cloud demo, demo credentials, Acme Robotics seed. Use when the user asks to spin up, keep running, seed…
git:20260827.92f4f3f · audit B · 23,724 stars
daytona-windows-cert skill
different-ai/openwork · .opencode/skills/daytona-windows-cert/SKILL.md · test on Windows, enterprise CA, corporate certificate, GPO cert, TLS fetch failed, Windows sandbox, daytona windows…
git:20260904.25c1014 · audit A · 23,724 stars
daytona skill
different-ai/openwork · .opencode/skills/daytona/SKILL.md · Daytona CLI setup, sandbox debugging, keep a sandbox alive, secrets volume, snapshot refresh. Use when Daytona itself…
git:20260905.46ba486 · audit A · 23,724 stars
diagnose-a-red-run skill
different-ai/openwork · .opencode/skills/diagnose-a-red-run/SKILL.md · Test is red, typecheck failed, CI job failed, flaky, timed out, was this already broken. Use to classify any failing…
git:20260921.bbe08f8 · audit A · 23,724 stars
get-env-var skill
different-ai/openwork · .opencode/skills/get-env-var/SKILL.md · get an env var, fetch a secret, missing env var, missing token/API key, load secrets from Infisical, infisical. Fetch…
git:20260902.114ecbd · audit A · 23,724 stars
hunt-a-prod-error skill
different-ai/openwork · .opencode/skills/hunt-a-prod-error/SKILL.md · A user saw internal_error, "Unexpected server error", a 500, or an opaque failure in a shipped OpenWork build. Find the…
git:20260921.bbe08f8 · audit A · 23,724 stars
open-a-pr skill
different-ai/openwork · .opencode/skills/open-a-pr/SKILL.md · Open a PR, write or rewrite a PR description, "the PR body is too long", or check whether a PR description is readable…
git:20260923.b2fdf64 · audit A · 23,724 stars
openwork-models skill
different-ai/openwork · .opencode/skills/openwork-models/SKILL.md · Manage OpenWork inference model aliases, openwork model overlays, discounts, validation, and automated base model…
git:20260911.4fa0232 · audit B · 23,724 stars
preview-my-work skill
different-ai/openwork · .opencode/skills/preview-my-work/SKILL.md · Boot, reopen, update, or reset OpenWork PR previews. Discover script worlds, use configurable app-web locally or…
git:20260924.c340d9e · audit A · 23,724 stars
record-a-demo skill
different-ai/openwork · .opencode/skills/record-a-demo/SKILL.md · Screenshots, recording, and presentation artifacts.
git:20260921.bbe08f8 · audit B · 23,724 stars

Every file in different-ai/openwork

Other files named write-a-spec

write-a-spec skill
inkeep/open-knowledge · packages/server/assets/skills/packs/software-lifecycle/write-a-spec/SKILL.md · Scope a feature end to end and write an implementation spec under specs/ from an accepted proposal — current-system…
git:20260825.3ab979a · audit A · 4,311 stars
write-a-spec skill
inkeep/open-knowledge-skills · skills/starter-packs/software-lifecycle/write-a-spec/SKILL.md · Scope a feature end to end and write an implementation spec under specs/ from an accepted proposal — current-system…
git:20260825.dda5ab1 · audit A · 8 stars

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