readwise
This skill should be used when the user asks to "search Readwise", "find highlights", "get quotes from my reading", "add highlights to notebook", "search my annotations", "get full document text", "fetch article content", "add tagged documents to notebook", or needs to query their Readwise library.
What this skill does
# Readwise
<EXTREMELY-IMPORTANT>
## IRON LAW: Main Chat NEVER Calls Readwise CLI
**EVERY READWISE OPERATION MUST GO THROUGH LIBRARIAN. This is not negotiable.**
Main chat MUST NOT:
- Run `readwise` CLI commands directly
- Run `readwise-custom` CLI commands directly
- "Just quickly check" highlights
**If you're about to do anything Readwise in main chat, STOP. Spawn a librarian sub-agent instead.**
</EXTREMELY-IMPORTANT>
### Permission Model
| Context | Readwise CLI | readwise-custom CLI |
|---------|-------------|-------------------|
| Main chat | **FORBIDDEN** | **FORBIDDEN** |
| Librarian sub-agent | ALLOWED | ALLOWED |
### Red Flag Detection
```
STOP if you catch yourself thinking:
- "Let me quickly search Readwise..."
- "I'll just run readwise reader-search-documents..."
- "I'll just run readwise-custom search..."
These thoughts in MAIN CHAT = VIOLATION. Delegate instead.
```
### Correct Pattern
```
User: "Search my Readwise for proxy advisor articles"
MAIN CHAT RESPONSE:
Task(subagent_type="workflows:librarian", prompt="Search Readwise for proxy advisor articles and summarize findings")
NEVER IN MAIN CHAT:
readwise readwise-search-highlights --vector-search-term "proxy advisors"
readwise-custom search "proxy advisors"
```
---
## Two CLIs
| CLI | Binary | Use for |
|-----|--------|---------|
| **Official** (`@readwise/cli`) | `readwise` | Search, list, get, save, move, tags, highlights CRUD, export, daily review |
| **Custom** (`~/projects/readwise-cli/`) | `readwise-custom` | Chat/RAG, ghostreader, file upload (PDF/EPUB), prune, keyword highlight search |
---
## Tag-Based Workflow
<EXTREMELY-IMPORTANT>
**When user mentions items were added by tag, NEVER use semantic search.**
### Trigger Phrases
- "we added items tagged X"
- "I thought we added X to NLM"
- "items tagged [tag]"
- "documents with tag [tag]"
### Required Workflow
```
User mentions tagged items or NLM content
│
▼
┌──────────────────────────────────┐
│ 1. CHECK NLM FIRST │ ← MANDATORY
│ nlm list │
│ nlm chat <id> │
└──────────────────────────────────┘
│
Not in NLM?
▼
┌──────────────────────────────────┐
│ 2. USE readwise for tagged items │
│ readwise reader-list-documents│
│ --tag "X" │
│ NOT search! │
└──────────────────────────────────┘
```
</EXTREMELY-IMPORTANT>
---
## Quick Reference
### Official CLI (`readwise`)
| Need | Command |
|------|---------|
| Semantic search highlights | `readwise readwise-search-highlights --vector-search-term "query"` |
| Search documents (hybrid) | `readwise reader-search-documents --query "query"` |
| Documents by tag | `readwise reader-list-documents --tag "X"` |
| Full document (markdown) | `readwise reader-get-document-details --document-id <id>` |
| List all tags | `readwise reader-list-tags` |
| Save URL | `readwise reader-create-document --url <url>` |
| Move documents | `readwise reader-move-documents --document-ids <id> --location archive` |
| Bulk edit metadata | `readwise reader-bulk-edit-document-metadata --documents '[...]'` |
| Export library | `readwise reader-export-documents` |
| Daily review | `readwise readwise-get-daily-review` |
Add `--json` to any command for machine-readable output.
### Custom CLI (`readwise-custom`)
| Need | Command |
|------|---------|
| RAG chat over highlights | `readwise-custom chat "question"` |
| Keyword search highlights | `readwise-custom highlights --search "term"` |
| Prune stale docs | `readwise-custom prune` |
| Upload PDF/EPUB | `readwise-custom upload <file>` |
| Ghostreader | `readwise-custom ghostread summarize <id>` |
| Full document (HTML) | `readwise-custom get <id> --html` |
**Sub-skills with detailed reference:**
| Skill | Purpose |
|-------|---------|
| `readwise-search` | Vector + fulltext highlight search |
| `readwise-docs` | Document CRUD (list, get, save, move, bulk edit, export) |
| `readwise-chat` | GPT-5.1 RAG chat over highlights (fallback — prefer search + Claude synthesis) |
| `readwise-prune` | Two-pass stale document cleanup |
---
## Batch Add to NLM (by tag)
```bash
uv run python3 /Users/vwh7mb/projects/workflows/skills/readwise/scripts/readwise_to_nlm.py \
--tag "proxy advisors" --tag "disclosure" \
--notebook <notebook-id>
```
Add `--dry-run` to preview. Add `--verbose` for detailed output.
## Anti-Pattern: Never Fetch from Source URL
**WRONG:** Search Readwise, find document, fetch from original URL (fails for paywalled content).
**RIGHT:** Search Readwise, get full text FROM READWISE using `readwise reader-get-document-details --document-id <id>`.
If a document is in Readwise, the full text is already there. Never go back to the source URL.
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.