make-plan
/make-plan
Create a work plan using memory context from past sessions. Use when the user says "make a plan", "what should we do next", "plan this out", "give me a roadmap", "help me prioritize", "what's the next step", "plan the sprint", or any request to organize upcoming work. Memory ensures the plan is grounded in what's already done, decided, and known to be broken.
- Author
- msapps-mobile ↗
- Repository
- claude-plugins ↗
- Licence
- MIT
- Last repository change
- 26.10.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 26.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Create a work plan using memory context from past sessions. Use when the user says "make a plan", "what should we do next", "plan this out", "give me a roadmap", "help me prioritize", "what's the next step", "plan the sprint", or any request to organize upcoming work. Memory ensures the plan is grounded in what's already done, decided, and known to be broken.
Triggers from the description
Original author description
Create a work plan using memory context from past sessions. Use when the user says "make a plan", "what should we do next", "plan this out", "give me a roadmap", "help me prioritize", "what's the next step", "plan the sprint", or any request to organize upcoming work. Memory ensures the plan is grounded in what's already done, decided, and known to be broken.
How it works
- Planning Workflow
- Planning Tips
SKILL.md preview
---
name: make-plan
description: >
Create a work plan using memory context from past sessions. Use when the user
says "make a plan", "what should we do next", "plan this out", "give me a
roadmap", "help me prioritize", "what's the next step", "plan the sprint",
or any request to organize upcoming work. Memory ensures the plan is grounded
in what's already done, decided, and known to be broken.
---
# make-plan: Memory-Grounded Planning
A good plan starts from the current state, not a blank slate. Memory tells you
what's been decided, what's blocking progress, and what was left mid-session.
## Planning Workflow
### 1. Load context from memory
```bash
# What was done recently?
python3 {SKILL_DIR}/scripts/memory_store.py timeline --hours 168 --limit 30
# What's in progress / blocked?
COWORK_MEM_DB=~/mnt/.claude/.cowork-mem/memory.db \
python3 {SKILL_DIR}/scripts/vector_search.py "in progress blocked next step" --limit 10
# What did the last session summary say?
python3 {SKILL_DIR}/scripts/memory_store.py search "session summary" --type summary --limit 5
```
### 2. Check for known errors or constraints
```bash
python3 {SKILL_DIR}/scripts/memory_store.py search "error bug blocked" --type error --limit 5
```
### 3. Build the plan
Structure the plan as:
- **Context**: What we know from memory (1-3 bullets, specific)
- **Goal**: What we're trying to accomplish
- **Steps**: Numbered, specific, actionable — reference actual files and systems
- **Blockers**: Known issues from memory that affect the plan
- **Open questions**: Things we'd need to investigate
### 4. Save the plan as a decision
```bash
python3 {SKILL_DIR}/scripts/memory_store.py add decision \
"Plan: <summary of steps>" --tags "plan,session-goal"
```
## Planning Tips
- Plans built from memory are more accurate than plans from scratch — use it
- Surface blockers from memory explicitly; don't let them be surprises mid-sprint
- If memory has conflicting decisions, flag it for the user to resolve
- Short plans (3-5 steps) are better than exhaustive ones — you can always plan the next thing after
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · msapps-mobile/claude-plugins | 100 | MIT |
| nigelng/nng-kit | 100 | MIT |
| thedotmack/claude-mem | 100 | Apache-2.0 |
| Heapy/kortex | 100 | Apache-2.0 |
| chicago-joe/manymems | 100 | Apache-2.0 |
| TalonT-Org/AutoSkillit | 100 | MIT |
Database snapshot: 13.11.2026 · package version b4750a226d87 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90sprint-planning
Produces a structured sprint plan from team availability, backlog items, and sprint goals. Use when a PM needs to plan an upcoming sprint - including capacity calculation, backlog scoping, dependency identification, and sprint plan document generation. Triggers on "plan the… - 100dx-create-sprint-logs
Use when someone needs a sprint log written at the end of a sprint, one per workstream, for the squad that picks the work up next. Triggers on "write the sprint log", "log this sprint", "sprint handover", "what did we ship this sprint", or a request to record a sprint before… - 90sprint
Turn a scoped backlog item into a sprint plan, broken into parallelisable tasks for agent teams. Use when asked to plan a sprint, break work down into tasks, or work out what can run in parallel. - 90sprint
Turn a scoped backlog item into a sprint plan, broken into parallelisable tasks for agent teams. Use when asked to plan a sprint, break work down into tasks, or work out what can run in parallel. - 100planner
Create comprehensive, phased implementation plans with sprints and atomic tasks. Use when user says: "make a plan", "create a plan", "plan this out", "plan the implementation", "help me plan", "design a plan", "draft a plan", "write a plan", "outline the steps", "break this down… - 95sprint-planner
Analyze design docs, calculate velocity from recent work, and create realistic sprint plans with day-by-day breakdowns. Use when user asks to "plan sprint", "create sprint plan", or wants to estimate development timeline.