edit-contract

Solid

Create a spine card and edit contract before a substantive chapter edit, and escalate after three failed revision attempts on the same issue.

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

# /edit-contract — Bounded Chapter Edits One file per contract at `contracts/{chapter}-{slug}.md`. No other ledgers. ## When to use Before a substantive edit (rewriting more than one paragraph, changing what a section claims, restructuring). Not for typo fixes or single-sentence edits. ## Contract file format ```markdown # Edit Contract: {chapter} — {short goal} ## Spine card - Section role: {what this section must keep doing in the argument} - Core claim (must not broaden): {one sentence} - Sources in scope: {list; their roles — support / background / challenge} - Forbidden: {claims that must NOT appear; scope that must NOT leak in} ## Scope - May change: {files/sections} - Must not change: {adjacent sections, quoted spans, other chapters} ## Attempts - [ ] Attempt 1: {date} — {outcome: accepted / revise / rejected, one line why} - [ ] Attempt 2: … - [ ] Attempt 3: … ``` ## Workflow 1. Draft the contract from the user's request and the current section; show it; the user approves or amends it **in conversation** before any edit. 2. Make the edit within Scope. After the edit, restate in one short table: what changed, whether the core claim broadened (quote before/after if it did), and whether anything Forbidden appeared. 3. Record the attempt line. The user's accept/revise/reject decision in conversation is the gate — the file records it, it does not grant it. ## Three-strike escalation After **three recorded failed attempts on the same contract** (not ...

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