# Co Scientist Text Mining Nlp

> Text mining and NLP skill. Scientific text mining, named entity recognition, relation extraction, topic modeling, and biomedical NLP pipelines. Use when working with scientific text mining, named entity recognition, relation extraction.

- Skill: `nahisaho/co-scientist-text-mining-nlp` (Agent Skill)
- Install (CLI): `npx skillmds@latest add nahisaho/co-scientist-text-mining-nlp`
- Raw SKILL.md: https://api.skillmd.com/api/skills/nahisaho/co-scientist-text-mining-nlp/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: nahisaho (https://skillmd.com/u/nahisaho)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/nahisaho/co-scientist-text-mining-nlp

---


# Text mining and NLP

Text mining and NLP skill. Scientific text mining, named entity recognition, relation extraction, topic modeling, and biomedical NLP pipelines.

## Use This Skill When

- Scientific text mining.
- Named entity recognition.
- Relation extraction.
- Topic modeling.
- Biomedical NLP pipelines.

## Required Inputs

- Research objective, decision target, or hypothesis.
- Available data, source constraints, and domain assumptions.
- Required outputs, success metrics, and deadline or reproducibility constraints.

## Workflow

1. Confirm scope, assumptions, and the exact artifact set to save.
2. Apply the narrowest domain method that answers the request with defensible evidence.
3. Save code, tables, figures, and intermediate outputs to files instead of chat-only output.
4. State limitations, uncertainty, and any validation or sensitivity checks performed.
5. Append skill selection, handoff I/O, and file writes to `logs/process-log.jsonl`.

## Deliverables

- `report.md`: concise method, results, interpretation, and file inventory in the user's language.
- `results/`: structured outputs, metrics, model artifacts, or extracted findings.
- `figures/`: English-only charts, diagrams, or panels when visual output is needed.
- `data/`: processed or derived datasets when transformation occurs.

## Available Tools (MCP)

> External tools available via [ToolUniverse](https://github.com/mims-harvard/ToolUniverse) MCP server.
> Falls back to Python `requests` + public REST APIs when MCP is unavailable.

| Source | Tool | Description |
|--------|------|-------------|
| PubTator3 | `PubTator_annotate` | PubTator3 API |
| PubTator3 | `PubTator_search` | PubTator3 API |
| PubMed | `PubMed_search` | PubMed API |

## Quality Gates

- [ ] The selected method matches the scientific question and stated assumptions.
- [ ] Outputs are reproducible, saved to files, and traceable from inputs to conclusions.
- [ ] Missing data, uncertainty, bias, and hard limits are made explicit.
- [ ] `report.md` and `logs/process-log.jsonl` reference the generated artifacts.
- [ ] No essential result remains chat-only.

If any gate fails: identify the specific failing check, fix the issue, and re-validate before proceeding.

## Gotchas

- Citation style varies by journal (author-year vs numbered). Confirm target format before writing
- Claims in Discussion must trace back to specific Results. Do not introduce new data in Discussion
- Supplementary materials must be self-contained with their own figure/table numbering

## Validation Loop

1. Execute analysis and generate outputs
2. Check:
   - Method selection matches the research question and stated assumptions
   - All outputs are saved to files (no chat-only results)
   - Limitations and uncertainty are explicitly stated
   - `logs/process-log.jsonl` is updated with execution trace
3. If any check fails:
   - Identify the failing gate
   - Fix the specific issue
   - Re-run validation
4. Proceed only after all gates pass