one-man-startup / rules
Cursor rule16 starsChanged 2 days agoMITView on GitHub
The checklist a feature passes twice - the design pass before architect and designer start, the build pass before any developer does. Use before routing a confirmed spec to design, and before handing any ticket to a developer agent.
We split this skill-readiness-gate.mdc into the rules it gives an agent
6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Build pass: every line, and no blocking review finding open.
- Distinctive: line 27
Every behaviour in the spec has a requirement row, and every row cites a testable outcome.
- Very specific: line 28
No question in p1-open-questions.md blocks this feature.
- Very specific: line 31
If the feature stores data: design.md names the source of truth, retention and deletion.
- Very specific: line 32
If it has a client and a server: contract.md exists and both sides build against it.
- Very specific: line 38
If the feature touches existing code: docs/work/<id>/spec-audit.md (skills/spec-audit/) says "delegate" or "delegate with review", and any …
≈ “Common” is an estimate: at least 1 in 5 of the 6,350 Cursor rule 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
---
description: "The checklist a feature passes twice - the design pass before architect and designer start, the build pass before any developer does. Use before routing a confirmed spec to design, and before handing any ticket to a developer agent."
alwaysApply: false
---
<!-- Generated by tools/sync_adapters.py from skills/readiness-gate/SKILL.md. Edit the source, not this file. -->
# Readiness gate
The gate has two passes, because lines 5 to 7 are the architect's own output (TPL-82):
- **Design pass:** lines 1 to 4 and 8 to 10. It opens `agentic-workflow`, `architect`,
`product-designer`, `legal` and `security`.
- **Build pass:** every line, and no blocking review finding open. It opens the developers.
Report each line as met or not met, with the file that shows it, in
`docs/work/<id>/readiness.md`. One "not met" keeps that pass shut. When the build pass opens,
the file gets the line `Build pass: open` with the date; until then
`tools/checks/gate_check.py` fails any change to product code. The release adds
`Build pass: closed <date>`, so a shipped feature does not open the gate for later work.
The fix track has no readiness gate. The orchestrator writes `Fix: open <row id> <date>` in
the fix's `docs/work/<id>/readiness.md` when it routes the fix, and `qa` adds
`Fix: closed <row id> <date>` with its PASS (TPL-120). At `[gates] level` light the check skips.
1. `docs/work/<id>/spec.md` exists and the founder confirmed it (the date is in `status.md`).
2. Every behaviour in the spec has a requirement row, and every row cites a testable outcome.
3. No question in `p1-open-questions.md` blocks this feature.
4. The success number and its read date are in the spec, and so is the review focus: the
likeliest real-world failures, each with a row.
5. If the feature stores data: `design.md` names the source of truth, retention and deletion.
6. If it has a client and a server: `contract.md` exists and both sides build against it.
7. `tickets.md` slices the work so each ticket is buildable and testable alone, with blocking
edges, and each ticket cites its rows.
8. The constitution in `AGENTS.md` is not broken by the plan. Where the plan bends a rule, the
reason is written down and the founder accepted it.
9. The reviews this feature needs (`legal`, `security`) are scheduled in `status.md`.
10. If the feature touches existing code: `docs/work/<id>/spec-audit.md` (`skills/spec-audit/`)
says "delegate" or "delegate with review", and any listed silent fills are in the brief.
A pass that opens says what it read. "Looks ready" is not a pass.
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 3,978 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository120 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/agent-agentic-workflow.mdcCursor rule
- .cursor/rules/agent-android-dev.mdcCursor rule
- .cursor/rules/agent-architect.mdcCursor rule
- .cursor/rules/agent-backend-dev.mdcCursor rule
- .cursor/rules/agent-dashboard.mdcCursor rule
- .cursor/rules/agent-debugger.mdcCursor rule
- .cursor/rules/agent-desktop-dev.mdcCursor rule
- .cursor/rules/agent-devops.mdcCursor rule
- .cursor/rules/agent-explainer-writer.mdcCursor rule
- .cursor/rules/agent-feasibility.mdcCursor rule
- .cursor/rules/agent-growth.mdcCursor rule
- .cursor/rules/agent-ios-dev.mdcCursor rule
- .cursor/rules/agent-legal.mdcCursor rule
- .cursor/rules/agent-optimizer.mdcCursor rule
- .cursor/rules/agent-orchestrator.mdcCursor rule
- .cursor/rules/agent-platform-architect.mdcCursor rule
- .cursor/rules/agent-platform-designer.mdcCursor rule
- .cursor/rules/agent-product-designer.mdcCursor rule
- .cursor/rules/agent-qa.mdcCursor rule
- .cursor/rules/agent-researcher.mdcCursor rule
- .cursor/rules/agent-reviewer.mdcCursor rule
- .cursor/rules/agent-rollback.mdcCursor rule
- .cursor/rules/agent-security.mdcCursor rule
- .cursor/rules/agent-setup.mdcCursor rule
- .cursor/rules/agent-social-media.mdcCursor rule
- .cursor/rules/agent-web-dev.mdcCursor rule
- .cursor/rules/skill-bug-fix.mdcCursor rule
- .cursor/rules/skill-commit.mdcCursor rule
- .cursor/rules/skill-context-budget.mdcCursor rule
- .cursor/rules/skill-cost-audit.mdcCursor rule
- .cursor/rules/skill-decision-log.mdcCursor rule
- .cursor/rules/skill-experiment.mdcCursor rule
- .cursor/rules/skill-founder-voice.mdcCursor rule
- .cursor/rules/skill-frontend-design.mdcCursor rule
- .cursor/rules/skill-gates.mdcCursor rule
- .cursor/rules/skill-grilling.mdcCursor rule
- .cursor/rules/skill-handoff.mdcCursor rule
- .cursor/rules/skill-human-design.mdcCursor rule
- .cursor/rules/skill-human-steps.mdcCursor rule
- .cursor/rules/skill-karpathy-guidelines.mdcCursor rule
- .cursor/rules/skill-known-reds.mdcCursor rule
- .cursor/rules/skill-legal-review.mdcCursor rule
- .cursor/rules/skill-new-feature.mdcCursor rule
- .cursor/rules/skill-observability.mdcCursor rule
- .cursor/rules/skill-ordered-steps.mdcCursor rule
- .cursor/rules/skill-performance.mdcCursor rule
- .cursor/rules/skill-release.mdcCursor rule
- .cursor/rules/skill-requirement-first.mdcCursor rule
- .cursor/rules/skill-safe-data-write.mdcCursor rule
- .cursor/rules/skill-setup.mdcCursor rule
- .cursor/rules/skill-single-source.mdcCursor rule
- .cursor/rules/skill-spec-audit.mdcCursor rule
- .cursor/rules/skill-tailoring.mdcCursor rule
- .cursor/rules/skill-twin-check.mdcCursor rule
- .cursor/rules/skill-verified-claims.mdcCursor rule
- .cursor/rules/skill-verify-green.mdcCursor rule
- bug-fixSkill
- commitSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

