working-backwards SKILL.md skillA

working-backwards from teambrilliant/dev-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add teambrilliant/dev-skills/working-backwards@git:20261008.81e7416

Pins git:20261008.81e7416 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
teambrilliant/dev-skills
Path
skills/working-backwards/SKILL.md
Versions recorded
7
Latest version
git:20261008.81e7416, committed Oct 8, 2026
First version recorded
Jun 9, 2026
Size
4,041 bytes
Repository stars
5
License
none declared

Write an Amazon-style PR-FAQ (mock press release + FAQ) to pressure-test a product idea customer-first and kill weak ideas on paper. Use when someone says "write a PR-FAQ", "PRFAQ", "press release", "working backwards", "start from the customer", "draft the launch announcement", "is this idea clear enough to build", or has a fuzzy idea and wants clarity on what and why. NOT for testing risky assumptions with experiments (product-discovery) or build plans (shaping-work / write-plan).

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

# Working Backwards

Start from the customer and the desired end-state, write it down, and iterate on
the *document* until the thinking is clear — long before any engineering. The
artifact is a **PR-FAQ**: a one-page mock press release + an FAQ of the hard
questions. Most PR-FAQs are never built — **killing a weak idea cheaply on paper
is the point, not a failure.**

Why writing: prose forces clarity that slides and good intentions can't. If you
can't write a compelling, honest press release for it, you don't understand it
yet — and neither will the customer.

References:
- `references/pr-faq-template.md` — the press-release + FAQ structure, section by section.
- `references/six-page-narrative.md` — the prose-memo / silent-read discipline (for proposals & reviews beyond a launch).
- `references/input-metrics.md` — input-vs-output metrics, DMAIC, the WBR (how you'd *measure* it once live).

## When to use this vs. its neighbors

- **product-thinker** decided *should we?* → use Working Backwards to force the *customer end-state* into focus.
- Idea is fuzzy / stakeholders disagree on what it even is → write the PR-FAQ; the draft surfaces the disagreement.
…

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_ispk2zs3miw4etme/3e7cd8ebe76c0a846b2c1d653f80ff4a21c1953413ff8086b0d5b7436691dfa1.json

Then /plugin install working-backwards@markdownregistry-ispk2zs3miw4etme in Claude Code. It installs git:20261008.81e7416, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add teambrilliant/dev-skills/working-backwards@sha256:3e7cd8ebe76c0a84

The line at the top of this page pins the label git:20261008.81e7416, 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_ispk2zs3miw4etme.svg)](https://markdownregistry.com/a/art_ispk2zs3miw4etme)

4 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 teambrilliant/dev-skills/working-backwards 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 working-backwards from somewhere else? Ask it: where did my working-backwards 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 7 versions of this file, between Jun 9, 2026 and Oct 8, 2026, about one every 20 days.

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

versioncommittedcommitsizeaudit
git:20261008.81e7416 latest2026-10-08 81e7416 4,041 BA view · diff
git:20261008.8e403b12026-10-08 8e403b1 4,218 BA view · diff
git:20260927.b9558d02026-09-27 b9558d0 4,153 BA view · diff
git:20260807.eadd9582026-08-07 eadd958 4,703 BA view · diff
git:20260707.e955c582026-07-07 e955c58 4,421 BA view · diff
git:20260707.6dcc6882026-07-07 6dcc688 4,413 BA view · diff
git:20260609.b690cd72026-06-09 b690cd7 4,263 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 (4041 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

teambrilliant/dev-skills · 5 stars · license none declared · pushed 2026-10-26 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ispk2zs3miw4etme
GET https://markdownregistry.com/api/v1/resolve?ref=teambrilliant/dev-skills/working-backwards
GET https://markdownregistry.com/api/v1/blob/3e7cd8ebe76c0a846b2c1d653f80ff4a21c1953413ff8086b0d5b7436691dfa1

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 teambrilliant/dev-skills

CLAUDE.md CLAUDE.md file
teambrilliant/dev-skills · CLAUDE.md
git:20261008.865c794 · audit A · 5 stars
execute-plan SKILL.md skill
teambrilliant/dev-skills · skills/execute-plan/SKILL.md · Execute an approved plan from thoughts/plans/ to completion — every phase, every check, every acceptance criterion —…
git:20261026.069feb8 · audit A · 5 stars
explain SKILL.md skill
teambrilliant/dev-skills · skills/explain/SKILL.md · Explain a plan, a shape, a shipped change, code, or the last message so it's impossible to misunderstand — an ASCII…
git:20261008.81e7416 · audit A · 5 stars
product-discovery SKILL.md skill
teambrilliant/dev-skills · skills/product-discovery/SKILL.md · Validate whether a product idea will actually work before committing engineering — find what you don't know, design the…
git:20260927.b9558d0 · audit A · 5 stars
product-primitives SKILL.md skill
teambrilliant/dev-skills · skills/product-primitives/SKILL.md · Break down complex products, features, or systems into fundamental primitives and building blocks from a software…
git:20260507.c5d07e6 · audit A · 5 stars
product-thinker SKILL.md skill
teambrilliant/dev-skills · skills/product-thinker/SKILL.md · Use for product decisions, user behavior analysis, and UX evaluation. Trigger when the user wants to: evaluate whether…
git:20261008.81e7416 · audit A · 5 stars
qa-test SKILL.md skill
teambrilliant/dev-skills · skills/qa-test/SKILL.md · Browser-based QA verification after any implementation. Use when someone says "QA this", "test this in browser"…
git:20260927.b9558d0 · audit A · 5 stars
shaping-work SKILL.md skill
teambrilliant/dev-skills · skills/shaping-work/SKILL.md · Shape rough ideas into clear, actionable work definitions. Use this skill whenever someone has an unstructured idea…
git:20261008.81e7416 · audit A · 5 stars
strategic-thinker SKILL.md skill
teambrilliant/dev-skills · skills/strategic-thinker/SKILL.md · Use for cross-domain strategic reasoning, approach selection, and systems-level analysis. Trigger when the user wants…
git:20261008.81e7416 · audit A · 5 stars
write-plan SKILL.md skill
teambrilliant/dev-skills · skills/write-plan/SKILL.md · Write a technical implementation plan to thoughts/plans/ before coding starts (separate from the harness's plan mode)…
git:20261008.81e7416 · audit A · 5 stars

Every file in teambrilliant/dev-skills

Other files named working-backwards

working-backwards SKILL.md skill
5hirish/duct · .agents/skills/working-backwards/SKILL.md · Amazon-style PR/FAQ for a user-facing Duct feature. A customer press release and FAQ written on the issue before any…
git:20261110.451b27e · audit A · 10 stars
working-backwards SKILL.md skill
vandanaajaydubey111/great-pm · skills/working-backwards/SKILL.md · Amazon's Working Backwards / PR-FAQ method — start from the customer problem and desired outcome, write the internal…
git:20260721.86de099 · audit A · 3 stars
working-backwards SKILL.md skill
vandanaajaydubey111/great-pm · plugins/great-pm/skills/working-backwards/SKILL.md · Amazon's Working Backwards / PR-FAQ method — start from the customer problem and desired outcome, write the internal…
git:20260920.2cbc56d · audit A · 3 stars

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