wiki-enrich
wiki-enrich completes scaffolded research papers by fetching content from multiple sources and rewriting 10 fillable TODO sections into concise prose. It preserves protected sections like Connections and Abstract (original), respects the --force flag for selective overwrites, and caps batches at 20 papers per run to manage token budgets.
wiki-enrich fills TODO sections in research wiki papers with LLM-generated summaries from external sources.
AI-generated summary based on this skill's SKILL.md
Install
wanshuiyin/Auto-claude-code-research-in-sleep/wiki-enrich · repository language: Python
git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep
cp -r Auto-claude-code-research-in-sleep/skills/wiki-enrich ~/.claude/skills/wiki-enrichFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How does wiki-enrich fill paper TODO sections in research wiki?
wiki-enrich automatically completes scaffolded research papers by fetching content from multiple sources and rewriting up to 10 fillable TODO sections into concise prose. It preserves protected sections like Connections and Abstract (original), respects the --force flag for selective overwrites, and caps batches at 20 papers per run to manage token budgets.
What sources does wiki-enrich use to enrich wiki papers automatically?
wiki-enrich enriches paper scaffolds left by ingest_paper with content drawn from arxiv and external sources. It batch populates wiki paper sections by converting paper abstracts into structured wiki sections, automating the tedious documentation process while maintaining research wiki integrity.
Can wiki-enrich auto-fill research wiki scaffolds selectively?
Yes. wiki-enrich respects the --force flag to enable selective overwrites of existing content. Without the flag, it skips already-filled sections; with --force, you can target specific papers or sections for re-enrichment while preserving protected areas like Connections and the original Abstract.
What are wiki-enrich's batch processing limits?
wiki-enrich caps batches at 20 papers per run to manage token budgets effectively. This prevents excessive API consumption while allowing efficient bulk enrichment of research wiki papers from arxiv and other sources in a single operation.
Which wiki paper sections does wiki-enrich protect from overwriting?
wiki-enrich preserves protected sections including Connections and Abstract (original) to maintain manually curated content and source integrity. All other fillable TODO sections can be auto-completed unless the --force flag is used to enforce selective overwrites.
SKILL.md
rendered from the published skill — quoted content, verbatim
Wiki Enrich: Fill Paper TODO Sections (Karpathy LLM-Wiki)
Target: $ARGUMENTS
Why this skill exists
ingest_paper (called by /research-lit, /arxiv, /alphaxiv, /deepxiv, /semantic-scholar, /exa-search) only renders the per-paper scaffold — frontmatter + abstract + 10 fillable _TODO._ placeholder sections (plus two protected sections: ## Connections is graph-summary and ## Abstract (original) is auto-populated when --arxiv-id is given). No downstream skill in ARIS fills those 10 sections; the wiki sits as TODO until someone reads each paper.
This contradicts the Karpathy LLM-wiki design
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 1 file
skills/wiki-enrich/SKILL.md