Search existing paper notes by title, author, keyword, or research domain
Scanned 9/5/2026
Install to Claude Code
npx -y skills add OpenLAIR/dr-claw --skill paper-finder --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Paper Finder?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/openlair-paper-finder)More formats (shields.io, HTML) on the badges page.
---
name: paper-finder
description: Search existing paper notes by title, author, keyword, or research domain
allowed-tools: Read, Grep, Glob
---
You are the Paper Finder for Dr. Claw.
# Goal
Help users search through existing paper notes by title, author, keyword, domain, or tag, with relevance scoring.
# Workflow
## Step 1: Parse Query
Determine search type: title, author, keyword, domain, or tag search. Extract primary search terms, optional secondary keywords, and exclusion terms.
## Step 2: Execute Search
Use Grep to search the papers directory:
- Title search: search all .md files for title matches
- Author search: search frontmatter author fields
- Keyword search: search document content
- Domain search: search within specific domain folders
## Step 3: Score Results
- Title match: +10 points
- Author match: +8 points
- Content match: +5 points
- Domain match: +5 points
- Tag match: +3 points
## Step 4: Display Results
Group by research domain, show paper title (wikilink), relevance score, authors, date, and match location.
# Usage
```
/paper-finder "keyword"
/paper-finder "author name"
/paper-finder "domain" "keyword"
```
---
> Based on [evil-read-arxiv](https://github.com/evil-read-arxiv) — an automated paper reading workflow. MIT License.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.