Agent skill
scratchpad
Working memory for thinking out loud.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/scratchpad
SKILL.md
Scratchpad
Working memory for thinking out loud.
The simplest skill. Just a place to write.
[!TIP] The PLAY surface. Not everything needs structure. Sometimes just write.
What This Is
A file where you can:
- Think through problems
- Draft before committing
- Store intermediate results
- Keep notes that don't belong elsewhere
No structure required. Just write.
When to Use
- Exploring an idea before formalizing
- Working through a multi-step calculation
- Drafting text before placing it
- Temporary storage during complex tasks
Structure
scratchpad/
├── SCRATCHPAD.md # Main scratch area
└── archive/ # Old scratches (optional)
That's it. Minimal by design.
Philosophy
"The simplest tool is often the most useful."
Not everything needs structure. Sometimes you just need a place to write freely.
Contents
| File | Purpose |
|---|---|
| SKILL.md | Protocol documentation |
| scratch.md.tmpl | Scratchpad template |
The Intertwingularity
Scratchpad is the PLAY stage — think freely before structuring.
graph LR
SP[📝 scratchpad] -->|PLAY stage| PLL[🎮📚🚀 play-learn-lift]
SP -->|structures into| PL[🗂️ planning]
SP -->|structures into| RN[📓 research-notebook]
PLL -->|freeform in| SP
Dovetails With
Sister Skills
| Skill | Relationship |
|---|---|
| play-learn-lift/ | Scratchpad IS the PLAY surface |
| planning/ | When you need structure |
| research-notebook/ | For organized investigation |
| session-log/ | Scratchpad is NOT logged (ephemeral) |
Protocol Symbols
| Symbol | Link |
|---|---|
PLAY-LEARN-LIFT |
PROTOCOLS.yml |
IMPROVISE |
PROTOCOLS.yml — Write before structuring |
Navigation
| Direction | Destination |
|---|---|
| ⬆️ Up | skills/ |
| ⬆️⬆️ Root | Project Root |
| 🗂️ Sister | planning/ |
| 📓 Sister | research-notebook/ |
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?