write-spec SKILL.md skillA

write-spec from me2resh/apexyard is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add me2resh/apexyard/write-spec@git:20261015.37f5689

Pins git:20261015.37f5689 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
me2resh/apexyard
Path
.claude/skills/write-spec/SKILL.md
Versions recorded
5
Latest version
git:20261015.37f5689, committed Oct 15, 2026
First version recorded
Apr 9, 2026
Size
4,222 bytes
Repository stars
551
License
MIT

Write a feature spec or PRD from a problem statement or feature idea. Use when creating product requirements documents.

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-spec — Feature Specification

Writing: read docs/skills/shared/writing-rule.md before you write a durable artifact.

Write a feature specification or product requirements document (PRD).

## Activated role

When `/write-spec` runs, activate the **[Product Manager](../../../roles/product/product-manager.md)** role — they own PRD creation, user stories, and acceptance criteria. For roadmap-level prioritisation calls, escalate to the **[Head of Product](../../../roles/product/head-of-product.md)**.

Design-heavy features should also involve the **[UX Designer](../../../roles/design/ux-designer.md)** (for user flows) and the **[UI Designer](../../../roles/design/ui-designer.md)** (for component specs) once the PRD has a problem statement. Technical feasibility review happens at the Tech Design phase, not here — the `/write-spec` output hands off to the [Tech Lead](../../../roles/engineering/tech-lead.md) who activates for Phase 2.

See [`.claude/rules/role-triggers.md`](../../rules/role-triggers.md) for the full activation protocol.

## Usage

```
/write-spec SSO support for enterprise
/write-spec Users want to export data as CSV
/write-spec We need better onboarding
```
…

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_4is3je7ukek7hudn/c79b74df842bb41e9761141c7591e06483b6acba2a4a5b38a79053678f7330cb.json

Then /plugin install write-spec@markdownregistry-4is3je7ukek7hudn in Claude Code. It installs git:20261015.37f5689, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add me2resh/apexyard/write-spec@sha256:c79b74df842bb41e

The line at the top of this page pins the label git:20261015.37f5689, 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_4is3je7ukek7hudn.svg)](https://markdownregistry.com/a/art_4is3je7ukek7hudn)

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 me2resh/apexyard/write-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-spec from somewhere else? Ask it: where did my write-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 5 versions of this file, between Apr 9, 2026 and Oct 15, 2026, about one every 47 days.

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

versioncommittedcommitsizeaudit
git:20261015.37f5689 latest2026-10-15 37f5689 4,222 BA view · diff
git:20260910.aac255e2026-09-10 aac255e 4,343 BA view · diff
git:20260524.44f7e7a2026-05-24 44f7e7a 3,697 BA view · diff
git:20260518.4743f322026-05-18 4743f32 3,576 BA view · diff
git:20260409.59aaf482026-04-09 59aaf48 2,955 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 (4222 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

me2resh/apexyard · 551 stars · license MIT · pushed 2026-11-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_4is3je7ukek7hudn
GET https://markdownregistry.com/api/v1/resolve?ref=me2resh/apexyard/write-spec
GET https://markdownregistry.com/api/v1/blob/c79b74df842bb41e9761141c7591e06483b6acba2a4a5b38a79053678f7330cb

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 me2resh/apexyard

accessibility-audit SKILL.md skill
me2resh/apexyard · .claude/skills/accessibility-audit/SKILL.md · WCAG 2.2 AA audit — perceivable, operable, understandable, robust criteria. Deep-dive for /launch-check accessibility.
git:20261015.37f5689 · audit A · 551 stars
agdr SKILL.md skill
me2resh/apexyard · .claude/skills/agdr/SKILL.md · Browse / search / show / stats AgDRs across the portfolio — recalls "have we decided this before?".
git:20261015.37f5689 · audit A · 551 stars
analytics-audit SKILL.md skill
me2resh/apexyard · .claude/skills/analytics-audit/SKILL.md · Analytics audit — SDK config, event naming, funnel completeness, dashboards. Deep-dive for /launch-check analytics.
git:20261015.37f5689 · audit A · 551 stars
approve-architecture SKILL.md skill
me2resh/apexyard · .claude/skills/approve-architecture/SKILL.md · Record per-PR architecture-review approval for design-artifact PRs (required by the architecture gate). ONLY on an…
git:20261015.37f5689 · audit A · 551 stars
approve-design SKILL.md skill
me2resh/apexyard · .claude/skills/approve-design/SKILL.md · Record per-PR design-review approval (UI merge gate). ONLY on an explicit per-PR designer "approved".
git:20261015.37f5689 · audit A · 551 stars
approve-merge SKILL.md skill
me2resh/apexyard · .claude/skills/approve-merge/SKILL.md · Record per-PR CEO approval and merge in one turn. ONLY on an explicit per-PR "approved" — never on umbrella "go".
git:20261022.74bff5f · audit A · 551 stars
audit-deps SKILL.md skill
me2resh/apexyard · .claude/skills/audit-deps/SKILL.md · Audit dependencies for vulnerabilities, outdated packages, and license compliance.
git:20261022.74bff5f · audit A · 551 stars
bug SKILL.md skill
me2resh/apexyard · .claude/skills/bug/SKILL.md · Create a structured bug ticket (Given/When/Then scenario, repro steps, severity).
git:20261022.74bff5f · audit A · 551 stars
c4 SKILL.md skill
me2resh/apexyard · .claude/skills/c4/SKILL.md · Generate C4 L1 (Context) + L2 (Container) Mermaid diagrams from a project's codebase. Structurizr DSL escape hatch…
git:20261015.37f5689 · audit A · 551 stars
challenge SKILL.md skill
me2resh/apexyard · .claude/skills/challenge/SKILL.md · Invoke The Contrarian (Naqid) to steelman-then-challenge an idea, feature, decision, or plan — surfaces assumptions…
git:20261015.37f5689 · audit A · 551 stars
code-review SKILL.md skill
me2resh/apexyard · .claude/skills/code-review/SKILL.md · Review a PR for quality, security, and standards compliance. Invokes the Code Reviewer agent (Rex).
git:20261022.74bff5f · audit A · 551 stars
codify-rule SKILL.md skill
me2resh/apexyard · .claude/skills/codify-rule/SKILL.md · Turn a review comment that caught a Rex-miss into a draft handbook entry — Y/N gate, source-PR footer, bucket-routed.
git:20261015.37f5689 · audit A · 551 stars

Every file in me2resh/apexyard

Other files named write-spec

write-spec SKILL.md skill
dzhng/skills · skills/plan/write-spec/SKILL.md · Break large features into independently verifiable, human-reviewable slices under a feature directory in specs/. Use…
git:20261110.a7712c1 · audit A · 1,507 stars
write-spec SKILL.md skill
accountgo/accountgo · .agents/skills/write-spec/SKILL.md · Write a feature spec or PRD from a problem statement or feature idea. Use when turning a vague idea or user request…
git:20261029.31a77b6 · audit A · 448 stars
write-spec SKILL.md skill
dzhng/duet-agent · .agents/skills/write-spec/SKILL.md · Break large features into independently verifiable, human-reviewable slices under a feature directory in specs/. Use…
git:20261028.649a3d2 · audit A · 53 stars
write-spec SKILL.md skill
eltmon/overdeck · sync-sources/skills/write-spec/SKILL.md · Compatibility redirect: /write-spec has been renamed to /pan-plan
git:20260918.7b95344 · audit A · 36 stars
write-spec SKILL.md skill
hassan-mohiddin/freeflow · .skill-eval/qualification/subjects/neutral/write-spec/SKILL.md · Use when turning settled discovery, explicit requirements, validated design direction, or source evidence into a…
git:20260712.138f16f · audit A · 5 stars
write-spec SKILL.md skill
ninjasln-labs/agent-skills · write-spec/SKILL.md · Write a feature spec or PRD from a problem statement or feature idea. Use when turning a vague idea or user request…
v1.2.0 · audit A · 4 stars

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