monorepo-template / quality
Cursor rule19 starsChanged 16 days agoApache-2.0View on GitHub
Final reports to the user - STE-flavored English, verbatim identifiers, a plain-text diagram only when structure needs one
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 4,144 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 repository59 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .agents/skills/vercel-react-best-practices/AGENTS.mdAGENTS.md
- hooks/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- hooks/CLAUDE.mdCLAUDE.md
- .cursor/rules/backend/hono-gateway.mdcCursor rule
- .cursor/rules/backend/ports.mdcCursor rule
- .cursor/rules/backend/service-bindings.mdcCursor rule
- .cursor/rules/backend/workers-cache.mdcCursor rule
- .cursor/rules/backend/workers-config.mdcCursor rule
- .cursor/rules/contracts/contracts.mdcCursor rule
- .cursor/rules/core/agent-instructions.mdcCursor rule
- .cursor/rules/core/boundaries.mdcCursor rule
- .cursor/rules/core/guardrails.mdcCursor rule
- .cursor/rules/core/turborepo.mdcCursor rule
- .cursor/rules/core/worktrees.mdcCursor rule
- .cursor/rules/frontend/react.mdcCursor rule
- .cursor/rules/frontend/tailwind.mdcCursor rule
- .cursor/rules/frontend/tanstack-query.mdcCursor rule
- .cursor/rules/frontend/tanstack-router.mdcCursor rule
- .cursor/rules/frontend/vite-config.mdcCursor rule
- .cursor/rules/ops/cd.mdcCursor rule
- .cursor/rules/ops/changesets.mdcCursor rule
- .cursor/rules/ops/ci.mdcCursor rule
- .cursor/rules/ops/previews.mdcCursor rule
- .cursor/rules/ops/quality-report.mdcCursor rule
- .cursor/rules/ops/release.mdcCursor rule
- .cursor/rules/quality/code-style.mdcCursor rule
- .cursor/rules/quality/comments.mdcCursor rule
- .cursor/rules/quality/knip.mdcCursor rule
- .cursor/rules/quality/lint-config.mdcCursor rule
- .cursor/rules/quality/markdown-style.mdcCursor rule
- .cursor/rules/quality/naming.mdcCursor rule
- .cursor/rules/quality/simplicity.mdcCursor rule
- .cursor/rules/quality/testing.mdcCursor rule
- .cursor/rules/quality/typescript-config.mdcCursor rule
- .cursor/rules/tests/front-react.mdcCursor rule
- .cursor/rules/tests/hono-workers.mdcCursor rule
- cfSkill
- changesetSkill
- front-vitestSkill
- git-commitSkill
- honoSkill
- monorepo-agent-setupSkill
- pnpmSkill
- react-doctorSkill
- reviewSkill
- review-stackSkill
- run-appSkill
- security-auditSkill
- skills-updateSkill
- tanstack-configSkill
- tanstack-querySkill
- tanstack-routerSkill
- turborepoSkill
- ui-ux-design-best-practicesSkill
- vercel-react-best-practicesSkill
- workers-best-practicesSkill
- skills-updateSkill
The file
We split this reporting.mdc into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Write in STE-flavored English: the ASD-STE100 structural rules, not its dictionary.
- Distinctive: line 12
Keep every hedge and condition as found: "may fail" never becomes "fails".
≈ “Common” is an estimate: at least 1 in 5 of the 6,668 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: "Final reports to the user - STE-flavored English, verbatim identifiers, a plain-text diagram only when structure needs one" alwaysApply: true --- # Reporting Applies to the report to the user at the end of a task or a step. It does not apply to code, commit messages, changesets, docs, or a subagent whose prompt sets an output format. - Write in STE-flavored English: the ASD-STE100 structural rules, not its dictionary. Active voice, one fact per sentence, at most 20 words for a step and 25 for a description, no semicolons, no phrasal verbs, no noun cluster longer than three words. - Give each thing one name for the whole report. Never rotate synonyms. - Keep every hedge and condition as found: "may fail" never becomes "fails". State a skipped or failed check plainly, with its command. - Order: the result first, then the verification (exact command and outcome), then open items. Put three or more steps or items in a list. - Add a diagram only when prose hides structure: a flow across three or more components, a before/after layout, a state change. Draw it in a fenced `text` block with box-drawing characters, because terminals do not render Mermaid. Never draw a diagram that repeats a list. - Paths, identifiers, commands, and error text stay verbatim in backticks. The STE limits do not apply inside them.
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.