aiskillstore/marketplace / skills/0xmsc/plan
plan
VerifiedGuidelines for iteratively planning tasks and changes before implementation. Use this when the user requests a non-trivial task or when you need to align on a complex implementation strategy.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 946 B |
| references/principles.md | markdown | 1.4 KB |
| skill-report.json | config | 8.2 KB |
references/principles.md
View on GitHub# Planning Principles
Implementation planning is a critical phase in the development lifecycle of an AI agent. It transforms ambiguous user requests into executable, verified actions.
## 1. The Principle of Least Surprise
Users should never be surprised by what the agent does. The plan acts as a contract. If you deviate from the plan during implementation, stop and explain why.
## 2. Iterative Planning vs. Big Design Up Front
Avoid spending hours on a perfect plan for a massive task. Instead:
1. Plan a manageable milestone.
2. Get approval.
3. Implement.
4. Plan the next milestone.
This keeps you and the user aligned and allows for early course correction.
## 3. Proactive Questioning
Don't wait for the user to find flaws. Search for them yourself.
- "What happens if this network call fails?"
- "Is this the correct naming convention for this project?"
- "Are there existing utilities that do this already?"
Presenting questions with proposed answers demonstrates competence and reduces user cognitive load.
## 4. Environment Awareness
Planning should always start with exploration. Use `ls`, `grep`, `find`, and `read_file` to understand the landscape before proposing a blueprint.
## 5. Risk Mitigation
Identify the most "dangerous" parts of your proposal (e.g., changing shared libraries, bulk file deletions) and highlight them. Propose safe verification steps for these risks.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| planning-and-task-breakdownaddyosmani/agent-skillsBreaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| screenpipethedotmack/claude-memSearch screen and audio history recorded by Screenpipe and optionally save selected context into claude-mem. Use when the user asks to recall desktop activity, a meeting, or something seen in another app through Screenpipe. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| contact-widgetnexu-io/open-designSelf-contained floating chat widget with welcome screen, social links, meeting button, and message input. Single HTML file, zero dependencies. | Stars: 108k | Updated | Claude CodeCodex | Verified | Install |
| meeting-notesnexu-io/open-designMeeting notes page — title bar with attendees, agenda checklist, decisions block, action items table with owners + dates, and a "next meeting" footer. Use when the brief mentions "meeting notes", "minutes", "1:1 notes", "all-hands recap", or "会议纪要". | Stars: 108k | Updated | Claude CodeCodex | Verified | Install |