write-a-spec SKILL.md skillA

write-a-spec from different-ai/openwork is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add different-ai/openwork/write-a-spec@git:20261115.d7237d2

Pins git:20261115.d7237d2 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
different-ai/openwork
Path
.opencode/skills/write-a-spec/SKILL.md
Versions recorded
13
Latest version
git:20261115.d7237d2, committed Nov 15, 2026
First version recorded
Sep 4, 2026
Size
14,186 bytes
Repository stars
24,563
License
a license file GitHub does not identify

Extend a core journey in evals/core or write a one-off proof in evals/proofs 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.

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

# Skill: Write a Spec

Every `evals/core/*.e2e.test.ts` or `evals/proofs/*.proof.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.

## Map: from change to reviewed proof

| Moment | Skill | Output |
| --- | --- | --- |
| Decide whether a journey is needed and design it | `write-a-spec` (this) | a spec whose titles, steps, and evidence read as the report |
| Run it and read your own record | `run-tests` | `evals/results/test-runs/<latest>/` with the captions in order |
| Let a reviewer click through the change | `pnpm world help` (preview worlds) | a sandbox link in the report's **Show sandbox** panel |
| Describe it on the PR | `open-a-pr` | an `## Evidence` line naming the spec and its before → after |

### Which lane runs your spec (and when to tag)

CI picks the lane from the file name and tags alone. Pick the lane first:
it decides the world you can build.

| If the spec… | Name / tag | CI lane |
| --- | --- | --- |
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_ym7chbqpj54tpb4y/7355644075d7328da2085025004a1636789097e7ae62f57840ca41873d5fc4a6.json

Then /plugin install write-a-spec@markdownregistry-ym7chbqpj54tpb4y in Claude Code. It installs git:20261115.d7237d2, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add different-ai/openwork/write-a-spec@sha256:7355644075d7328d

The line at the top of this page pins the label git:20261115.d7237d2, 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_ym7chbqpj54tpb4y.svg)](https://markdownregistry.com/a/art_ym7chbqpj54tpb4y)

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

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in different-ai/openwork/write-a-spec since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of write-a-spec from somewhere else? Ask it: where did my write-a-spec come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 13 versions of this file, between Sep 4, 2026 and Nov 15, 2026, about one every 6 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261115.d7237d2 latest2026-11-15 d7237d2 14,186 BA view · diff
git:20261113.22ca4802026-11-13 22ca480 14,416 BA view · diff
git:20261031.ae4e3b82026-10-31 ae4e3b8 14,474 BA view · diff
git:20261015.ef455ca2026-10-15 ef455ca 14,291 BA view · diff
git:20261014.ae5014f2026-10-14 ae5014f 14,008 BA view · diff
git:20261008.f4e974b2026-10-08 f4e974b 13,343 BA view · diff
git:20261007.6d48ffa2026-10-07 6d48ffa 13,284 BA view · diff
git:20260925.963ee332026-09-25 963ee33 12,921 BA view · diff
git:20260921.bbe08f82026-09-21 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
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

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 (14186 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 · 24,563 stars · license a license file GitHub does not identify · pushed 2026-11-19 · 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/7355644075d7328da2085025004a1636789097e7ae62f57840ca41873d5fc4a6

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 different-ai/openwork

AGENTS.md@.github AGENTS.md file
different-ai/openwork · .github/AGENTS.md
git:20261028.06f44d2 · audit A · 24,563 stars
add-a-feature SKILL.md skill
different-ai/openwork · .opencode/skills/add-a-feature/SKILL.md · Decide whether work needs a feature flag (any change to product behavior users can see does), then declare it, roll it…
git:20261113.d897285 · audit A · 24,563 stars
drive-desktop-cdp SKILL.md skill
different-ai/openwork · .opencode/skills/drive-desktop-cdp/SKILL.md · Drive the running OpenWork app over CDP from the shell, headless by default (nothing opens on screen). Evaluate JS…
git:20261015.ef455ca · audit B · 24,563 stars
dry-run-a-risky-change SKILL.md skill
different-ai/openwork · .opencode/skills/dry-run-a-risky-change/SKILL.md · Billing, plans, seats, permissions, access rules, auth, flag removals or data migrations that could lock real…
git:20261115.d7237d2 · audit A · 24,563 stars
fake-model-faults SKILL.md skill
different-ai/openwork · .opencode/skills/fake-model-faults/SKILL.md · Make the desktop's model provider fail on demand (connection refused, DNS not found, socket reset, 429, 5xx, 401, 402…
git:20261002.739dae1 · audit B · 24,563 stars
open-a-pr SKILL.md 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:20261118.ab88b17 · audit A · 24,563 stars
run-tests SKILL.md skill
different-ai/openwork · .opencode/skills/run-tests/SKILL.md · Run the tests, run one spec, run e2e locally or on Daytona, investigate a skipped spec. Use for executing…
git:20261015.ef455ca · audit B · 24,563 stars
verify-openwork SKILL.md skill
different-ai/openwork · .opencode/skills/verify-openwork/SKILL.md · Prove an OpenWork change works on the real product before calling it done. Start the product, drive the change the way…
git:20261031.ae4e3b8 · audit A · 24,563 stars
AGENTS.md AGENTS.md file
different-ai/openwork · AGENTS.md
git:20261117.6afc794 · audit A · 24,563 stars
DESIGN.md DESIGN.md file
different-ai/openwork · DESIGN.md
git:20261117.c8595b2 · audit A · 24,563 stars
AGENTS.md@ee/apps/den-web AGENTS.md file
different-ai/openwork · ee/apps/den-web/AGENTS.md
git:20261111.3f0df82 · audit A · 24,563 stars
CLAUDE.md@ee/apps/den-web CLAUDE.md file
different-ai/openwork · ee/apps/den-web/CLAUDE.md
git:20260923.d1a801d · audit B · 24,563 stars

Every file in different-ai/openwork

Other files named write-a-spec

write-a-spec SKILL.md 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:20261014.adeb8b5 · audit A · 4,855 stars
write-a-spec SKILL.md 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:20261014.2bb8524 · audit A · 17 stars

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

Kept in .opencode/skills, the folder OpenCode reads. More agent skills for OpenCode.