product-docs-first
Skill9 starsChanged 27 days agoMITView on GitHub
Use when starting a new app and the operator wants product documentation designed before code, OR docs/<app>/product.md exists. Ingests operator research and the North Star, then designs per-app product docs that planning builds from. If no product.md exists and the operator did not ask to create one, this skill does nothing (silent no-op) — do NOT auto-create. Not for mid-implementation edits.
In this repository119 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/fusebase-flow-always.mdcCursor rule
- .cursor/rules/fusebase-flow-implementation.mdcCursor rule
- .cursor/rules/fusebase-flow-security.mdcCursor rule
- .cursor/rules/fusebase-flow-specs.mdcCursor rule
- .cursor/rules/fusebase-flow-validation.mdcCursor rule
- api-explorationSkill
- app-api-contract-testingSkill
- app-backendSkill
- app-business-docsSkill
- app-dev-practicesSkill
- app-e2e-testsSkill
- app-quality-patternsSkill
- app-routingSkill
- app-secretsSkill
- app-sidecarSkill
- app-ui-designSkill
- business-logic-guardianSkill
- client-vs-internalSkill
- code-reviewSkill
- comment-policySkill
- communicationSkill
- design-discovery-ideationSkill
- dev-debug-logsSkill
- documentation-budgetSkill
- file-uploadSkill
- find-wasted-codeSkill
- find-wasted-effortSkill
- fusebase-cliSkill
- fusebase-dashboardsSkill
- fusebase-flow-health-checkSkill
- fusebase-gateSkill
- fusebase-portal-specific-appsSkill
- git-history-diagnosticSkill
- git-workflowSkill
- handling-authentication-errorsSkill
- handoffSkill
- implementation-planningSkill
- invite-with-passwordSkill
- lightweight-laneSkill
- liveness-disciplineSkill
- managed-integrationsSkill
- mcp-gate-debugSkill
- module-size-disciplineSkill
- north-starSkill
- phase-auditSkill
- product-apps-decompositionSkill
- product-ownerSkill
- project-onboardingSkill
- release-deploy-reportingSkill
- remote-logsSkill
- repo-onboarding-context-mapSkill
- requirements-specificationSkill
- role-disciplineSkill
- security-permissions-reviewSkill
- skill-authoringSkill
- smoke-testingSkill
- task-delegationSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
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
- Very specific: line 50
Gate: If no docs/<app>/product.md and no operator request to create one → exit silently.
- Distinctive: line 78
Do not auto-create product docs unprompted.
- Distinctive: line 79
Do not write code (FR-01) — this designs the product, not the implementation.
- Distinctive: line 80
Do not invent product intent the operator didn't supply.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Product Docs First
Style: Mode-B-lite. Artifact-gated — acts only when
docs/<app>/product.mdexists or the operator asks to create one.
Purpose
Design product documentation per app before writing code, so planning and implementation build from a clear product intent instead of guessing. Ingests operator research and the North Star (if present).
When to invoke
- Operator starts a new app and says "design the product docs first", "write product documentation", "what should this app do".
docs/<app>/product.mdalready exists (read it to ground planning).- Operator dropped research in
docs/<app>/research/and asks to turn it into product docs.
Do not invoke when
- No
docs/<app>/product.mdAND the operator did not ask to create one → silent no-op; do not auto-create. - Mid-implementation edits (planning already done).
- Small bug fixes, refactors, copy-only changes, narrow technical tickets, or already-scoped implementation work with no long-lived product-intent change → do not expand product docs (FR-23 /
flow-skills/documentation-budget/SKILL.md).
Required inputs
| Input | Where it lives | If missing |
| Product intent (operator answers) | chat | ask in chat (FR-19); do not invent |
| Research (optional) | docs/<app>/research/ | proceed without; note it |
| North Star (optional) | docs/north-star.md | proceed; align if present |
| Template | templates/product.md | stop; template missing |
Procedure
- Gate. If no
docs/<app>/product.mdand no operator request to create one → exit silently. - Ingest any research + the North Star; summarize, cite, never invent domain facts.
- Design the product doc from
templates/product.md: purpose, users, core jobs, key screens/flows, data, the apps this product breaks into (feedsproduct-apps-decomposition), non-goals. - Write
docs/<app>/product.mdwithlast_updatedtoday (only operator-provided content). - Hand to planning (
implementation-planning) grounded in the product doc. - Ambiguity → ask operator (FR-19).
Output artifacts
| Artifact | Path | Mode |
| Product doc | docs/<app>/product.md | Mode B |
Failure cases
| Failure | Detection | Response |
| Artifact absent + no request | step 1 | silent no-op |
| Vague product intent | can't fill sections | capture only what's given; no fabrication |
| Template missing | step 4 | stop; report missing templates/product.md |
Escalation path
- Domain expertise needed →
skill-authoring(domain-expert mode). - Vision conflict →
north-star/ ask operator (FR-11).
Anti-patterns
- Do not auto-create product docs unprompted.
- Do not write code (FR-01) — this designs the product, not the implementation.
- Do not invent product intent the operator didn't supply.
Clean-room note
Original Fusebase Flow content. See docs/source-map.md. No third-party code, prompts, or skill files copied.
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.

