scratch-workspace
Use when creating temporary files, drafts, experiments, or any content that should not be committed to version control. Ensures proper placement in .claude/.scratch with gitignore configuration.
What this skill does
# Scratch Workspace Management
This skill covers proper use of the `.claude/.scratch/` directory for temporary, exploratory, and draft work.
## Purpose
The scratch workspace provides a gitignored location for:
- Draft implementations
- Experimental code
- Temporary test files
- Planning documents
- Any work-in-progress that shouldn't be committed
## Setup Checklist
Before creating scratch files:
1. **Ensure directory exists**
```bash
mkdir -p .claude/.scratch
```
2. **Verify gitignore**
Check `.gitignore` contains:
```
.claude/.scratch
```
If missing, add it:
```bash
echo '.claude/.scratch' >> .gitignore
```
## Directory Structure
Organize scratch files by purpose:
```
.claude/
├── .scratch/
│ ├── drafts/ # Work-in-progress implementations
│ │ └── feature-x.ts
│ ├── experiments/ # Exploratory code
│ │ └── perf-test.js
│ ├── notes/ # Planning and notes
│ │ └── architecture.md
│ └── temp/ # Truly temporary files
└── settings.json # Claude settings (NOT scratch)
```
## Best Practices
### DO
- Create subdirectories for organization
- Use descriptive file names
- Clean up when work is complete
- Move finalized code to proper project locations
### DON'T
- Put sensitive data in scratch (still on disk)
- Use scratch for files that should be committed
- Leave stale scratch files indefinitely
- Put scratch files outside `.claude/.scratch/`
## Workflow
### Starting Exploratory Work
```bash
# Create scratch area
mkdir -p .claude/.scratch/experiments
# Work on experiment
# ... create files in .claude/.scratch/experiments/
```
### Promoting to Real Code
When scratch work is ready:
1. Review and refine the code
2. Move to appropriate project location
3. Delete scratch version
4. Commit the promoted code
### Cleanup
Periodically clean scratch:
```bash
# Review what's in scratch
ls -la .claude/.scratch/
# Remove old experiments
rm -rf .claude/.scratch/experiments/old-test/
```
## Integration with Other Tools
### With Git
The `.claude/.scratch` directory is gitignored, so:
- `git status` won't show scratch files
- `git add .` won't stage scratch files
- Scratch files won't appear in commits
### With IDE
Most IDEs will show `.claude/.scratch` in the file tree. You can:
- Add to IDE's exclude patterns
- Keep visible for easy access
- Use IDE's "mark as excluded" feature
## Common Patterns
### Draft Implementation
```
.claude/.scratch/drafts/
└── new-feature/
├── index.ts
├── types.ts
└── test.ts
```
### Performance Experiment
```
.claude/.scratch/experiments/
└── perf-comparison/
├── approach-a.ts
├── approach-b.ts
└── benchmark.ts
```
### Architecture Notes
```
.claude/.scratch/notes/
└── refactor-plan.md
```
## Troubleshooting
### Scratch files appearing in git status
```bash
# Verify gitignore entry
grep -r ".claude/.scratch" .gitignore
# If missing, add it
echo '.claude/.scratch' >> .gitignore
```
### Directory doesn't exist
```bash
mkdir -p .claude/.scratch
```
### Accidentally committed scratch files
```bash
# Remove from tracking but keep locally
git rm -r --cached .claude/.scratch
git commit -m "chore: remove scratch files from tracking"
```
Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.