Skills-Agent / rules
Cursor rule4 starsChanged 33 days agoMITView on GitHub
Create concrete implementation plans with milestones, task breakdowns, and estimates. Use when the user wants to plan, organize work, or create a roadmap. Triggers: plan, milestone, breakdown, roadmap, estimate, kế hoạch, lên kế hoạch, phân chia công việc.
We split this plan.mdc into the rules it gives an agent
7 rules. About 0 are common, 3 are distinctive, and 4 are 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.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
START: Read .ai-memory.md from project root.
- Very specific: line 11
END: Update .ai-memory.md using Memory Compaction Rules with: plan summary, phases/tasks, key risks, and first recommended action.
- Distinctive: line 29
If any answer is unclear, ASK before proceeding.
- Distinctive: line 63
Prefer task sizes that can be completed and reviewed quickly.
- Distinctive: line 65
Always read and update the memory file.
- Very specific: line 68
After completing, read .kiro/skills/_scripts/checklist.md for cross-cutting quality checks.
- Very specific: line 76
All code snippets and example files referenced or produced by this skill must be UTF-8 encoded.
≈ “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: "Create concrete implementation plans with milestones, task breakdowns, and estimates. Use when the user wants to plan, organize work, or create a roadmap. Triggers: plan, milestone, breakdown, roadmap, estimate, kế hoạch, lên kế hoạch, phân chia công việc." encoding: "UTF-8" agents: [project-planner, orchestrator] globs: "" alwaysApply: false --- ## Memory Protocol **START**: Read `.ai-memory.md` from project root. Check existing plans, milestones, project structure, tech stack, ongoing work, and past decisions. **END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: plan summary, phases/tasks, key risks, and first recommended action. ## Goal Turn a request into an actionable plan with clear phases and tasks. ## Agent Routing - For architecture planning → read `.kiro/skills/agents/agents/project-planner.md` and apply its knowledge - For multi-domain coordination → read `.kiro/skills/agents/agents/orchestrator.md` and apply its knowledge - For technical feasibility → read the relevant specialist agent file: - Backend: `.kiro/skills/agents/agents/backend-specialist.md` - Frontend: `.kiro/skills/agents/agents/frontend-specialist.md` - Database: `.kiro/skills/agents/agents/database-architect.md` ## Socratic Gate Before planning, verify: 1. What is the desired outcome? (specific deliverable) 2. What constraints exist? (time, resources, tech stack) 3. What is already built vs needs to be built? If any answer is unclear, ASK before proceeding. ## Workflow 1. **Read Memory** — Load `.ai-memory.md` for project context and history. 2. Define the objective and acceptance criteria. 3. Break the work into phases and tasks. 4. Note file areas, systems, or modules likely to change. 5. Estimate complexity and highlight risky items. 6. End with a recommended first task. 7. **Update Memory** — Save plan details to `.ai-memory.md`. ## Output format - Objective - Acceptance criteria - Phases (with tasks under each) - File areas / modules affected - Risks (with mitigation) - Recommended first action ## Checklist - [ ] Objective clearly stated - [ ] Acceptance criteria defined - [ ] Phases broken down - [ ] Tasks are specific and actionable - [ ] Complexity estimated per task - [ ] Risks identified with mitigation - [ ] First action recommended - [ ] Memory file updated - [ ] Clean code chuẩn (Standard clean code applied) - [ ] Cập nhật đầy đủ tất cả các file liên quan (All related files fully updated) ## Rules - Plans should be specific enough to execute. - Prefer task sizes that can be completed and reviewed quickly. - Minimize blast radius: call out the smallest set of files likely to change; if scope is unclear, ASK. - Always read and update the memory file. ## Quality Gate After completing, read `.kiro/skills/_scripts/checklist.md` for cross-cutting quality checks. ## Related Skills - `/brainstorm` → read `.kiro/skills/brainstorm/SKILL.md` — Explore options before planning - `/create` → read `.kiro/skills/create/SKILL.md` — Execute planned tasks - `/orchestrate` → read `.kiro/skills/orchestrate/SKILL.md` — Coordinate complex plans across teams ## Encoding All code snippets and example files referenced or produced by this skill must be UTF-8 encoded. When applicable, include `encoding: "UTF-8"` in SKILL.md front-matter and ensure saved files use UTF-8 (no BOM).
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 repository96 other files it gives its agents.
- .cursor/rules/agents.mdcCursor rule
- .cursor/rules/brainstorm.mdcCursor rule
- .cursor/rules/clean.mdcCursor rule
- .cursor/rules/create.mdcCursor rule
- .cursor/rules/debug.mdcCursor rule
- .cursor/rules/deploy.mdcCursor rule
- .cursor/rules/enhance.mdcCursor rule
- .cursor/rules/explain.mdcCursor rule
- .cursor/rules/instructions.mdcCursor rule
- .cursor/rules/integrate.mdcCursor rule
- .cursor/rules/motion-ui.mdcCursor rule
- .cursor/rules/orchestrate.mdcCursor rule
- .cursor/rules/preview.mdcCursor rule
- .cursor/rules/status.mdcCursor rule
- .cursor/rules/test.mdcCursor rule
- .cursor/rules/ui-ux-pro-max.mdcCursor rule
- agentsSkill
- brainstormSkill
- cleanSkill
- createSkill
- debugSkill
- deploySkill
- enhanceSkill
- explainSkill
- integrateSkill
- motion-uiSkill
- orchestrateSkill
- planSkill
- previewSkill
- statusSkill
- testSkill
- ui-ux-pro-maxSkill
- agentsSkill
- brainstormSkill
- cleanSkill
- createSkill
- debugSkill
- deploySkill
- enhanceSkill
- explainSkill
- integrateSkill
- motion-uiSkill
- orchestrateSkill
- planSkill
- previewSkill
- statusSkill
- testSkill
- ui-ux-pro-maxSkill
- agentsSkill
- brainstormSkill
- cleanSkill
- createSkill
- debugSkill
- deploySkill
- enhanceSkill
- explainSkill
- integrateSkill
- motion-uiSkill
- orchestrateSkill
- planSkill
- 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.
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.

