literature-review

1# Literature review
2 
3A literature question has two halves: finding the papers a domain expert would point to, and turning them into something more useful than a reading list — a synthesis that says what's established, what's contested, what's new, and where the holes are. Both halves can fail quietly and look like competent output until someone checks.
4 
5## Setup (any agent, no API key)
6 
7This is a **pure skill** — `kernel.py` is deterministic Python (plain HTTP/stdlib calls to CrossRef and OpenAlex) and _you_ (the base model) do all the reasoning: the finding, the synthesis, the prose. There is no `host` runtime and no LLM API. Load the helpers once per session in a Python cell:
8 
9```python
10exec(open("<this skill's directory>/kernel.py").read())
11```
12 
13Nothing auto-loads it outside Claude Science. Then call the helpers directly — `verify_dois`, `crossref_lookup`, `search_openalex`, `expand_citations`, `extract_dois`, `style_pass`. If a helper name is not defined, you haven't exec'd `kernel.py`.
14 
15Configuration is via environment variables, not a host — no LLM key is involved:
16 
17- `OPENALEX_API_KEY` — required for the OpenAlex-backed steps (`search_openalex`, `expand_citations`); free at https://openalex.org/settings/api.
18- `HOST_USER_EMAIL` — optional contact email for the CrossRef/doi.org polite pool (falls back to `git config user.email`; never sent to OpenAlex).
19 
20## Read the request for what it's actually asking
21…