Menu
Configure the research pack runtime by checking Python dependencies and helping the user populate local API-key environment files.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Run lint.mjs --json, summarize findings by severity, offer to apply --fix for auto-fixable checks (L01/L03/L06/L07/L09), self-check re-run to confirm 0 errors, and surface advisory warnings for user attention. Use this whenever the user asks to "check the wiki", "run lint", "verify the graph", "are there broken links?", "what's wrong with the wiki?", "health check", or "are there missing reverse links?". Also fires for: weekly review requests, before committing wiki changes, after a bulk ingest session, or any time the user wants to know the structural state of the wiki.
Guided wiki page authoring and refactoring: apply user-directed edits to a wiki page with schema validation and bidirectional-edge integrity preserved. Use this whenever the user asks to update, fix, revise, rewrite, correct, or clean up a wiki page — even if they don't say "edit". Also fires for: "fix the reverse link on X", "update the summary for Y", "set importance to 4 on Z", "the lint check found a missing link in ...", or any request that modifies one wiki page without ingesting a new source.
Turn a raw source file into structured wiki pages: source page, concept and person stubs, wiki.mjs-managed graph edges, citation edges, and a log entry. Pauses at four checkpoints (draft, lint, verify, finalize) so you can review before the work is committed to the wiki — accept, revise, or quit at any checkpoint without losing progress. Resumable across sessions. Use this whenever the user says "ingest", "add", "file", "process", "summarize into the wiki", "create a wiki page for", or drops a filename from raw/sources/. Also fires for: "I added a PDF to raw/sources/", "add this paper to the wiki", "parse this article", "what should I do with raw/sources/X?", or any request to bring a new source into the wiki graph. Also accepts Mode B input — paper title, arxiv ID, or URL, without a local file path. Examples: "ingest paper 2604.03501v2", "ingest arxiv:2604.03501", "ingest https://arxiv.org/abs/2604.03501". The skill fetches the PDF automatically in that case. Also handles whole books, theses, and other 50+ p
Check that wiki notes match the sources they cite. Flags statements that appear in a wiki page but are not supported by the cited material, statements that contradict other parts of the same page, and (with --external) statements contradicted by current web search results. Reports findings for the user to review; never edits notes automatically. Run on one page (`/lumi-verify <slug>`), the whole wiki (`/lumi-verify --all`), or only recently-changed pages (`--since <date>`). Use after AI adds new wiki pages, before sharing or exporting the wiki, or as a periodic health check on older pages. Trigger on phrases like "verify", "fact-check the wiki", "is this page accurate?", "check sources", "retro verify". Operates on sources/* pages in v0.9; other page types are skipped.
Ingest one book chapter into the wiki and extract character mentions, theme tags, and plot beats into the graph. Use whenever the user wants to ingest, file, or process a chapter — including phrasings like "I just finished chapter 3", "add this chapter to the wiki", "file chapter 2 of [book]", or "track what happened in chapter 5".
Answer questions from what the wiki already knows, citing the wiki pages behind every claim so the user can open and verify them. Reads only — never changes the wiki unless the user explicitly asks to save the answer as a page. Use this whenever the user asks a question whose answer should come from the wiki — even if they don't say "ask". Also fires for: "what does the wiki say about X", "compare X and Y from what we've ingested", "summarize the wiki's coverage of X", "what concepts relate to Y", "find all sources that mention Z", "what have we learned about X", or any synthesis or retrieval request over accumulated wiki content. If a question could be answered from raw/ but isn't in the wiki yet, surface the gap, list the matching raw/ files so the user can open them directly, and suggest /lumi-ingest instead of reading raw/.
| name | lumi-research-setup |
| description | Configure the research pack runtime by checking Python dependencies and helping the user populate local API-key environment files. |
| allowed-tools | ["Bash","Read","Write"] |
You prepare the local workspace to use research pack tools. This is runtime setup for optional fetchers; it is not the Lumina installer.
Read README.md first. The installer may create .env.example, but it must not
create .env with secrets. This skill can help the user create or update .env
after they provide values.
.env.example and _lumina/tools/requirements.txt.python3 _lumina/tools/init_discovery.py --help
python3 _lumina/tools/fetch_arxiv.py --help
python3 _lumina/tools/fetch_s2.py --help
python3 _lumina/tools/fetch_openalex.py --help
python3 _lumina/tools/fetch_unpaywall.py --help
python3 _lumina/tools/fetch_core.py --help
python3 _lumina/tools/fetch_deepxiv.py --help
python3 _lumina/tools/fetch_wikipedia.py --help
python3 _lumina/tools/resolve_pdf.py --help
Report missing optional keys by name only. Never print secret values. For each missing key, tell the user what the provider is for, whether it is required or optional, and where to register:
| Key | Provider | Required? | Register at |
|---|---|---|---|
| (none) | arXiv | no key | Public XML API at export.arxiv.org — no signup |
SEMANTIC_SCHOLAR_API_KEY | Semantic Scholar | optional | https://www.semanticscholar.org/product/api (request form; raises rate limits from ~100/5min to higher tier) |
OPENALEX_API_KEY | OpenAlex | optional | https://openalex.org/settings/api (free key; enables the daily API budget and usage tracking). Report presence as "set" / "unset" only; never display the value. |
UNPAYWALL_EMAIL | Unpaywall | required for Unpaywall step in resolve_pdf ladder | Free — supply any email you own. The ladder skips Unpaywall gracefully when this is unset (the rest of the ladder still runs). |
CORE_API_KEY | CORE | optional | https://core.ac.uk/services/api (free tier ≈1000 req/day). When unset, resolve_pdf skips CORE silently. On 429 the ladder skips CORE for the remainder of the run. |
DEEPXIV_TOKEN | DeepXiv | optional | https://deepxiv.com (sign up, copy token from account settings; enables full-text PDF + semantic search) |
Wikipedia fetcher uses the public REST API and needs no key.
If the user asks you to write .env, preserve existing keys and write only
the provided values.
Run a harmless smoke check for the selected provider when credentials are available.
wiki/ or raw/..env is unchanged unless the user supplied values and asked you to write it.wiki/, raw/, index, graph, or log files are changed.