RW Paper Extractor

Startup

1. Read

   references/standalone.md

   ,

   references/method.md

   and

   references/standards.md

   .
2. Read the materials provided by the user in this session; if no materials are provided, only complete the parts allowed by current evidence.
3. Retrieve

   references/atoms.jsonl

   when rule-based judgments are needed; read

   references/cases.md

   when encountering similar tasks.
4. Read

   references/domain-guide.md

   when selecting methods or tools, and use

   assets/worksheet.md

   to organize deliverables.
5. Read

   references/acceptance.md

   .

   references/behavior-tests.json

   is only used for testing and not as factual information for user tasks.
6. When current literature, APIs, report specifications and journal requirements may change, open the official links in

   references/source-map.md

   to verify and record the date.

Work Phases

1. Confirm the extraction purpose, research type, available full text and supplementary materials.
2. Establish stable identifiers such as title, authors, year, source, DOI, PMID for the paper.
3. Select fields according to the research type, and first record the version of the extraction schema.
4. Extract research questions, design, samples, variables, methods, results, limitations and funding disclosures.
5. Save page numbers, paragraphs, tables, figures or supplementary material locations for key fields.
6. Perform a second check to distinguish between missing, unreported, not applicable and undeterminable items.

Operation Rules

• The extraction schema is determined by subsequent usage; do not use the same empty form for all papers.
• Titles and abstracts can only provide information that they actually report.
• Separate the statement types of Methods, Results and Discussion sections.
• Do not write authors' explanations as measured results.
• Do not infer randomization, blinding, model settings or missing data handling without the full text.
• Denominators, units, time points and analysis sets in tables and figures must be extracted together.
• Do not mix adjusted and unadjusted results.
• Distinguish between primary, secondary, exploratory and post-hoc analyses.
• Unreported, zero events and not applicable are not the same value.
• Test the form with two papers of different structures before batch extraction.
• Retain confidence levels and review status for machine-extracted fields.
• Retain the original value, modified value and reason when modifying key fields.

Output

• Structured paper cards or batch tables.
• Original text locations, confidence levels and review status.
• Missing items, conflicts and materials to be supplemented.

Stop Conditions

• Do not fill in full-text exclusive fields when the full text is not accessible.
• Key fields that cannot be located in the original text cannot be marked as verified.
• Do not bypass access restrictions to obtain papers.
• Do not automatically judge that a study was not implemented due to missing items in report specifications.

Standalone Operation

• By default, do not read private workspaces, personal corpus directories or preset research-lab.
• Files, texts, links and data provided by the user are input for the current task, not installation dependencies.
• When the network is unavailable, continue using stable methods within the Skill; mark parts requiring current facts as pending verification.
• Can connect with other research Skills in this package if they exist; when installed alone, directly return instructions for the next step without stopping the current task.

Source Discipline

• Separate user materials, public sources, current inferences and unknown items.
• Report specifications only check report transparency, not automatically prove design quality.
• Public source abstracts are stored within the Skill; return to official pages when needing versions, fees, policies, APIs or current journal requirements.
• Do not generate non-existent papers, data, DOIs, tool operation results or journal requirements.