logic-review

Solid

Review stable chapter or manuscript drafts for paragraph flow, transitions, argument continuity, and repeated rhetorical functions before editing. Use after the author-approved spine is stable; route structural drift back to thesis-control.

AI & Automation 38 stars 7 forks Updated 3 days ago MIT

Install

View on GitHub

Quality Score: 83/100

Stars 20%
53
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# /logic-review — Paragraph Logic Review ## Purpose Find paragraphs that may need a topic sentence, a clearer transition, merging, re-ordering, or removal of duplicated argumentative work. The deterministic script flags mechanical candidates; the agent separately reviews rhetorical functions without redefining the manuscript spine. ## Trigger Words This skill activates on: `logic review`, `flow check`, `paragraph logic`, `/logic-review`. ## Workflow 1. Run: `python3 scripts/audit-logic.py --base-dir . --json` 2. Confirm that the research object, core question, intended use, primary experiment, headline claim, and evidence boundary are stable under the active `/thesis-control` contract. If they are not, stop the language pass and route the issue to drift control or revision escalation. 3. Read the flagged paragraphs and nearby context. 4. Label each relevant sentence or paragraph by its main function: `problem`, `gap`, `method`, `evidence`, `interpretation`, `boundary`, or `transition`. 5. Flag duplicated functions and monotonous sequences, especially repeated `evidence -> disclaimer` endings. Prefer deleting or consolidating repeated argumentative work over generating synonymous wording. 6. Check boundary placement. Scope must remain aligned across the paper, but full limitation prose need not be repeated after every result. Preserve essential local qualifiers and concentrate fuller study-boundary language in the abstract ending, Methods bo...

Details

Author
yha9806
Repository
yha9806/academic-writing-toolkit
Created
5 months ago
Last Updated
3 days ago
Language
Python
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category