plan-project
Skill1 starsChanged 8 months agoMITView on GitHub
Research-backed comprehensive project planning. Use when planning a new project or initiative. Triggered by "make a plan", "I want to start a project", "break down tasks", or "create a roadmap".
7 other projects use a version of this.
Adopted by
Most recently taken up by
- anivar/agentic-sdlctheir own version, first seen Nov 16, 2026
- mattolson/agent-sandboxtheir own version, first seen Oct 8, 2026
- KodingDev/skillstheir own version, first seen Oct 2, 2026
- pi247/classic-PM-skillstheir own version, first seen Aug 21, 2026
- link7373/agentic-pmotheir own version, first seen Aug 9, 2026
- YUVARAJ-R-ai/my-claude-skillstheir own version, first seen Jun 30, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- mattolson/agent-sandbox★ 212same name
- MooseDesign1/DDD-DesignDrivenDevelopment★ 9same name
- KodingDev/skills★ 2same name
- YUVARAJ-R-ai/my-claude-skills★ 2same name
- link7373/agentic-pmo★ 1same name
- pi247/classic-PM-skills★ 1same name
- anivar/agentic-sdlc★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- brainstormSkill
- evaluateSkill
- learningSkill
- notebookSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 28
If NOTEBOOK_PATH is set, search for past entries related to the project goal:
- Distinctive: line 32
Read up to 3 matching entries (frontmatter + first 200 characters of body)
- Very specific: line 39
Create a team with the following teammates using their agent definitions from .claude/agents/:
- Distinctive: line 66
After the team completes its discussion, create the final output:
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Plan Project Skill
A workflow that creates an Agent Team of Researcher and Planner to create actionable project plans through iterative research and planning refinement.
Workflow
Step 1: Understand the Goal
Accurately understand the project goal/objective presented by the user. Clarify:
- Project goal (what to achieve)
- Scope (what's included, what's not)
- Known constraints (timeline, budget, personnel, tech stack, etc.)
- Definition of success (what does success look like)
Confirm with the user if ambiguous.
Step 2: Retrieve Past Notebook Context
If NOTEBOOK_PATH is set, search for past entries related to the project goal:
- Grep
$NOTEBOOK_PATH/plans/and$NOTEBOOK_PATH/research/for keywords from the goal - Also search for entries where the project name matches the
project:frontmatter - Read up to 3 matching entries (frontmatter + first 200 characters of body)
- Include the retrieved content as context when creating the team
Skip this step if zero matches or NOTEBOOK_PATH is not set.
Step 3: Create Agent Team
Create a team with the following teammates using their agent definitions from .claude/agents/:
Teammates:
researcher— gathers background knowledge and best practicesplanner— creates structured plans with tasks and dependencies
Team instructions:
Project goal: [User's goal]
Constraints: [User's constraints]
[Past Notebook context if found]
Collaboration protocol:
1. Researcher investigates: similar projects, best practices, pitfalls, required tech/resources, risks
2. Planner creates initial plan (phases, milestones, tasks, dependencies, risks)
3. Researcher reviews the plan for feasibility gaps — flags unrealistic estimates, missing risks, or overlooked dependencies based on research findings
4. Planner refines the plan based on Researcher's feedback
5. Continue iterating until both agree the plan is realistic and actionable (aim for 2-3 rounds)
Rules:
- Output language: Use the language specified by OUTPUT_LANGUAGE env var. If not set, match the user's language (default: English)
- If NOTEBOOK_PATH is set: Researcher saves to $NOTEBOOK_PATH/research/, Planner saves to $NOTEBOOK_PATH/plans/
- Each agent writes its own deliverables with structured frontmatterStep 4: Format the Plan
After the team completes its discussion, create the final output:
## Project Plan: [Project Name]
### Planning Summary
[How the plan evolved through researcher-planner discussion]
### Overview
- **Goal**: ...
- **Scope**: ...
- **Estimated Duration**: ...
- **Success Criteria**: ...
---
### Phase 1: [Phase Name] (duration estimate)
**Milestone**: [Completion criteria]
| # | Task | Depends On | Estimate | Notes |
|---|------|-----------|----------|-------|
| 1.1 | ... | - | ... | ... |
| 1.2 | ... | 1.1 | ... | ... |
### Phase 2: [Phase Name] (duration estimate)
...
---
### Risk Management
| Risk | Severity | Probability | Mitigation |
|------|----------|-------------|------------|
| ... | High/Med/Low | High/Med/Low | ... |
### Lessons from Research
- [Learnings from similar projects]
- [Pitfalls to avoid]
### Next Steps
- Start with the first task of Phase 1
- Regular `/learning` retrospectives recommendedOutput Format
Present the following to the user:
- Brief summary of the team planning process
- Project overview
- Detailed plan by phase (with tasks, dependencies, and estimates)
- Risk management table
- Lessons from research
- Next steps
- Notebook save notification if applicable
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.

