product-spec
Skill0 starsChanged 14 days agoMITView on GitHub
Turn an idea or an existing codebase into a concrete product spec - who it is for, the core job, every user flow with happy and unhappy paths, non-goals, success metric, stack and data model - written to PRODUCT.md and as flow rows in READINESS.md. Use at the start of /ship, when a goal says "build X" without a spec, or when flows are unclear. Decides instead of asking; asks at most three questions once.
12 other projects use a version of this.
Adopted by
Most recently taken up by
- idaibin/skillstheir own version, first seen Nov 8, 2026
- edilson-silva/codridetheir own version, first seen Oct 15, 2026
- matiopala/skillstheir own version, first seen Oct 15, 2026
- arfar-x/agent-skillstheir own version, first seen Oct 13, 2026
- gonimar/claude-web-studiotheir own version, first seen Sep 27, 2026
- sunnybhara/claude-startertheir own version, first seen Aug 14, 2026
Used with
Projects with it also use code-review.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
GoogleSkillcode-review
Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.
Also in 3 projects that use this
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- firatcand/founder-skills★ 37same name
- Hassaan146/claude-skills★ 18same name
- arfar-x/agent-skills★ 14same name
- yasunori0418/skills★ 9same name
- idaibin/skills★ 6same name
- gonimar/claude-web-studio★ 4same name
- levinchang/productdesign-skills★ 4same name
- vndee/engineering-skills★ 3same name
- edilson-silva/codride★ 2same name
- matiopala/skills★ 2same name
2 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- hireSkill
- learnSkill
- owner-actionsSkill
- portfolioSkill
- production-readySkill
- qa-flowsSkill
- release-gatesSkill
- run-companySkill
- shipSkill
- ux-ui-reviewSkill
- workspaceSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 10 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 26
Before writing flows, study how the best two or three products in this category do the core job (their screens, copy and pricing) and …
- Distinctive: line 29
Before the first build row, a pre-mortem: three "this failed because" lines, each becoming a flow, a release gate or a non-goal.
- Very specific: line 31
Write the READINESS rows now: | F1 | <flow> | <surfaces> | todo | | |.
- Distinctive: line 32
Keep user-facing copy in the product's language (Hebrew products stay Hebrew.
“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Product spec
Output: PRODUCT.md (under 150 lines) and the ## Flows table of READINESS.md. Write both before building.
PRODUCT.md sections
- Press release (working backwards): five sentences a customer would read on launch day (who, the problem, what changes for them, a quote, how to start) and the three hardest FAQ answers. If it does not convince, change the product before writing flows.
- One line:
<product> helps <who> <do the job> without <the pain>. - Who: the first user, in one paragraph. If the owner is the first user, say so.
- Core job: the one thing the product must do well. Everything else is secondary.
- Flows (5 to 12): each in user words, with the unhappy path next to it. Examples: "Sign up with email, lands on a useful first screen; wrong password shows a clear error; forgotten password resets by email." Include: first run, the core job, empty/loading/error states, payment if any, settings, data export/delete, sign out, each bot command or integration.
- Non-goals: what v1 will not do. Cutting is a decision, write it down.
- Success metric: one number the owner can check weekly.
- Stack and hosting: what the repo uses, or the owner's default stack if PRODUCT.md or OWNER.md names one, else the simplest thing that ships (for example Next.js + Postgres) for a new idea. Run/test/deploy commands.
- Data model: entities and their key fields, in a short table. Privacy notes (what is personal data, retention).
- Decisions: a dated list of choices you made for the owner (name, pricing, copy, scope). The owner can overturn any of them later.
- Open questions (max 3): only things that change the build and that you cannot decide. Ask them once in the report; proceed with your best guess meanwhile and mark the guess.
Rules
- Before writing flows, study how the best two or three products in this category do the core job (their screens, copy and pricing) and record in Decisions what you copy, improve or skip, with links.
- Existing project: derive flows from the code (routes, screens, commands, webhooks, emails, settings), README and old plans. Do not invent features the code does not have; do add missing unhappy paths.
- A flow is worth a row only if a user would notice it missing or broken.
- Before the first build row, a pre-mortem: three "this failed because" lines, each becoming a flow, a release gate or a non-goal.
- Order rows by value: core job, money, sign up/onboarding, data safety, everything else. That order is the build order.
- Write the READINESS rows now:
| F1 | <flow> | <surfaces> | todo | | |. - Keep user-facing copy in the product's language (Hebrew products stay Hebrew; English default otherwise).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.