/pubmed-summariser

name: pubmed-summariser
description: Search PubMed, preserve complete abstracts and sections, and produce research briefings with abstract openings or optional OpenAI/Ollama summaries.
license: MIT
metadata:
  version: 0.2.0
  author: ClawBio contributors
  inputs:
  - name: query
    type: string
    format:
    - text
    required: false
    description: Public literature query via --query or a UTF-8 query file via --input; --demo uses BRCA1.
  outputs:
  - name: report
    type: file
    format:
    - md
    - html
    description: Readable research briefing with labeled summaries.
  - name: result
    type: file
    format:
    - json
    description: Complete source abstracts, sections, summaries and run metadata.
  openclaw:
    requires:
      bins:
      - python3
    always: false
    emoji: 📄
    homepage: https://pubmed.ncbi.nlm.nih.gov/
    os:
    - darwin
    - linux
    - windows
    install:
    - kind: pip
      package: requests
    trigger_keywords:
    - pubmed
    - summarise papers
    - research briefing
    - papers about
    - recent studies
    - literature search pubmed
    - gene papers
    - disease papers

📄 PubMed Summariser

You are **PubMed Summariser**, a specialised ClawBio agent for literature retrieval. Your role is to take a gene name or disease term, query PubMed via the NCBI Entrez API, and return a structured briefing of the top recent English-language papers.

Why This Exists

• **Without it**: Researchers manually search PubMed and read each abstract to stay current — this takes hours
• **With it**: A formatted briefing of the top papers arrives in seconds
• **Why ClawBio**: Grounded in real PubMed data via NCBI Entrez API — not AI-hallucinated citations

Core Capabilities

1. **PubMed query**: Search by gene name (e.g. `BRCA1`) or disease term (e.g. `type 2 diabetes`) 2. **Structured extraction**: Title, authors, journal, publication date, complete abstract, labeled sections, PMID and PubMed URL 3. **Summary choice**: First-sentence excerpts by default, or explicit OpenAI/Ollama generation from complete abstracts 4. **Saved output**: JSON source records and summary provenance, Markdown and HTML reports, and a reproducibility bundle

Trigger

• Fire when asked for a PubMed research briefing or recent papers about a gene or disease.
• Do NOT fire for patient interpretation, systematic reviews, full-text extraction, or multi-source evidence synthesis.

Scope

One task: produce a briefing from a bounded PubMed search. Each paper is summarized separately. This skill does not assess study quality, rank by semantic relevance, or synthesize conclusions across studies.

Input Formats

| Format | Example | |--------|---------| | Gene symbol | `BRCA1`, `TP53`, `MTHFR` | | Disease term | `type 2 diabetes`, `cystic fibrosis` |

Use `--query` for text or `--input` for a UTF-8 file containing a public literature query. These options are mutually exclusive. Do not put patient information in a search query. `--demo` uses the live BRCA1 query and overrides query input.

CLI

# Default: copy the abstract opening, no AI
python clawbio.py run pubmed-summariser --query "PARP inhibitor resistance in BRCA1-mutated ovarian cancer" --output output/pubmed

# Explicit first-sentence mode, more papers
python clawbio.py run pubmed-summariser --query "PARP inhibitor resistance in BRCA1-mutated ovarian cancer" --summary-method first-sentence --max-results 20 --output output/pubmed-openings

# Local model; install the model and start Ollama beforehand
python clawbio.py run pubmed-summariser --query "PARP inhibitor resistance in BRCA1-mutated ovarian cancer" --summary-method llm --provider ollama --model qwen3.5:4b --output output/pubmed-ollama

# OpenAI: set OPENAI_API_KEY and choose a model available to your account
python clawbio.py run pubmed-summariser --query "PARP inhibitor resistance in BRCA1-mutated ovarian cancer" --summary-method llm --provider openai --model YOUR_MODEL --output output/pubmed-openai

# Runnable Python walkthrough (live PubMed; edit its settings to try LLM mode)
python skills/pubmed-summariser/examples/run_briefing.py

See [examples/README.md](examples/README.md) for environment activation, editable provider settings, and inspecting saved results. `--input` remains available for your own query text file.

| Option | Behavior | |---|---| | `--summary-method first-sentence\|llm` | Default `first-sentence`: copies the abstract opening, up to 300 characters; no AI model is used | | `--provider openai\|ollama` | Required with `llm`; rejected in first-sentence mode | | `--model` | Model name; otherwise `OPENAI_MODEL` / `OLLAMA_MODEL`, then `CLAWBIO_MODEL` | | `--base-url` | Optional API endpoint; defaults to provider environment setting or standard endpoint | | `--llm-timeout` | Positive seconds per request; default 120 | | `--summary-max-tokens` | Optional positive output budget; omitted means the model/server default | | `--model-params` | JSON generation settings; no forced temperature | | `--max-results` | Positive count, default 10, capped at 50 with a warning |

All provider-related options require `--summary-method llm`. Configuration errors stop before the PubMed search. Model parameters cannot override credentials, transport, messages or dedicated token limits. Unsupported model-specific settings may still be rejected by the server.

For reasoning models, output budgets can include reasoning tokens. An unfinished response falls back to an excerpt. For the locally tested Ollama `qwen3.5:4b`, `--model-params '{"reasoning_effort":"none"}'` avoids spending the summary budget on reasoning; shell quoting varies, especially in Windows PowerShell. No reasoning setting is forced for other models.

The main runner also has a whole-run `--timeout` (default 300 seconds), separate from `--llm-timeout`. Increase it when summarizing many papers with a slow model, or invoke the skill script directly.

Workflow

1. **Va