Paper Garden — Development skill for Claude Code
Ingest a paper into the knowledge garden.
How to install Paper Garden
Installs to ~/.claude/skills/genliusrocks-paper_garden-paper-garden/SKILL.md
mkdir -p ~/.claude/skills/genliusrocks-paper_garden-paper-garden && curl -fsSL https://raw.githubusercontent.com/genliusrocks/paper_garden/HEAD/commands/paper-garden.md -o ~/.claude/skills/genliusrocks-paper_garden-paper-garden/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Paper Garden does
Ingest a paper into the knowledge garden.
$ARGUMENTS is an arXiv URL, arXiv paper ID, or local PDF path.
Repo and Config
- Repo root:
__PAPER_GARDEN_REPO__ - Config:
__PAPER_GARDEN_REPO__/skills/paper-garden/paper_garden.toml - All
uv runcommands must run from the repo root.
First-Time Setup
Read the config file. If it is missing, empty, or has no `garden_dir` / `language` keys:
- Ask the user: garden directory (default
./paper_garden) and language (defaulten). - Run:
Alternatives in Development
- PaperSpine — PaperSpine is a motivation-driven skill for learning from strong academic papers, building a paper’s central a 5k ★
- Ars Abstract — ARS academic-paper abstract-only mode — bilingual abstract + keywords 4.5k ★
- Mono Color Skill — One-ink editorial print image skill — warm paper, halftone photography, active negative space, and restrained 3k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Paper Read
Read one or more papers from the knowledge garden by their IDs and answer a question.
Paper Trail Ingest All
Batch INGEST across the entire vault. Scans all SOTAs, identifies those with bibliographic sections containing
Paper Trail Ingest
Ingest the citations of one SOTA into the registry. Extracts bibliographic sections, parses citations via the
Obsidian Ingest
Ingest a source into the vault — the vault rewrites itself around new knowledge. Every ingest updates entities
Claude Ingest Skill
Claude Code skill: Ingest documents into atomic knowledge notes with semantic deduplication
Memory Ingest
Process new raw content into the agent memory knowledge base. Creates source/concept/entity pages, cross-links
Related Agents
Finding Extractor
Extracts atomic, testable findings from a single research paper. Invoked alongside lite-drafter and metadata-e
Kb Corpus Curator
Register, ingest and verify a source in this knowledge base through the kb- mise tasks, and close the loop wit
Bd Lit Distill
Distils one paper into the knowledge/source/papers/ format. Extracts parameters, equations and verification va