skills / rules
Cursor rule176 starsChanged 13 days agoMITView on GitHub
Terse documentation mode — strip fluff from skill docs and agent prose
We split this token-optimization.mdc into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
Does NOT apply to: user-project code, CLI commands, YAML frontmatter, commit messages.
≈ “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: Terse documentation mode — strip fluff from skill docs and agent prose
alwaysApply: true
---
Skill docs and agent prose in this repo follow terse mode: drop articles, filler, hedging, preamble, and subject padding ("You should run" → "Run"). Keep technical terms exact, tables unchanged, numbered rules numbered, section headers for navigation. Strip code-block comments when surrounding prose already explains intent; keep comments on non-obvious behavior or in `assets/templates/`. Deduplicate format boilerplate (e.g. XAML `xmlns`) — include full once per file, then `<!-- standard xmlns omitted -->`.
Full reference: `.claude/rules/token-optimization.md`.
Does NOT apply to: user-project code, CLI commands, YAML frontmatter, commit messages. Safety override for security warnings, irreversible actions, multi-step sequences.
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 repository39 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- skills/uipath-genome/CLAUDE.mdCLAUDE.md
- skills/uipath-rpa/CLAUDE.mdCLAUDE.md
- .cursor/rules/content-quality.mdcCursor rule
- .cursor/rules/pr-review.mdcCursor rule
- .cursor/rules/skill-review.mdcCursor rule
- .cursor/rules/skill-structure.mdcCursor rule
- manage-skill-flavorsSkill
- uipath-activity-migratorSkill
- uipath-adminSkill
- uipath-agentsSkill
- uipath-aopsSkill
- uipath-api-workflowSkill
- uipath-automationhubSkill
- uipath-coded-appsSkill
- uipath-connector-builderSkill
- uipath-feedbackSkill
- uipath-functionsSkill
- uipath-genomeSkill
- uipath-governanceSkill
- uipath-human-in-the-loopSkill
- uipath-insightsSkill
- uipath-ixpSkill
- uipath-knowledge-bundlesSkill
- uipath-maestro-bpmnSkill
- uipath-maestro-caseSkill
- uipath-maestro-flowSkill
- uipath-mcp-serversSkill
- uipath-plannerSkill
- uipath-platformSkill
- uipath-process-miningSkill
- uipath-reviewSkill
- uipath-rpaSkill
- uipath-rulesSkill
- uipath-solutionSkill
- uipath-tasksSkill
- uipath-testSkill
- uipath-troubleshootSkill
- uipath-vertical-solutionsSkill
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.