carloscape/octorato/long-document-revision-protocol
Claude Code and agent skill by carloscape/octorato
- community
Checking that the SKILL.md file is still in the repository.
Long Document Revision Protocol
Install
npx vskill@latest install carloscape/octorato/long-document-revision-protocolSKILL.md
Long Document Revision Protocol
What
A comprehensive checklist and workflow for revising technical documents exceeding 1,000 lines, integrating all document quality skills into a single actionable process.
Why
Long documents (1,000+ lines) have unique failure modes:
- Invisible drift: Changes in one section contradict another section 500 lines away
- Reference rot: Cross-references break as structure evolves
- Status decay: Markers become stale as content changes
- Voice fragmentation: Different sections read like different authors
- Structural erosion: Hierarchy breaks down over multiple edit sessions
No single skill addresses all these risks. This protocol orchestrates all document quality skills into a coherent revision workflow.
The Protocol
Phase 1: Pre-Revision Assessment (5 minutes)
Before making changes, understand the document state:
Phase 2: Make Changes
Apply your edits with awareness:
Phase 3: Post-Revision Verification (10-15 minutes)
After completing edits, run the full coherence suite:
Phase 4: Final Validation
Quick automated checks:
Quick Reference Card
For routine edits, use this abbreviated checklist:
When to Use Full Protocol
| Situation | Protocol Level | |
|---|---|---|
| Fix a typo | None needed | |
| Update a number | Quick reference card | |
| Add a paragraph | Quick reference card | |
| Add a section | Phases 2-4 | |
| Merge documents | Full protocol | |
| Major restructure | Full protocol | |
| Pre-publish review | Full protocol |
Integration with Git Workflow
Real-World Example
From the Acme Corp TDD revision session:
Revision scope: Add 366 lines (§6 Charter Deliverables) + update 7 table rows
Protocol execution:
- Pre-revision: 2,701 lines, 55 findings, 8 deliverables with 6 at ⚠️
- Changes: Inserted §6.1–§6.6, updated Charter Traceability table
- Post-revision:
- Coherence: New sections reference existing findings (no contradictions)
- References: §6.1–§6.6 all resolve, Finding #refs valid
- Markers: All 8 rows now ✅, closing note updated
- Deduplication: Key facts reference §2.5.2, §3.2 (not duplicated)
- Voice: Matched existing formal-neutral, evidence-backed style
- Structure: §6 hierarchy clean, no empty sections
- Validation: Node.js script confirmed 8 GREEN rows, 0 stale markers
Result: 3,067 lines, fully coherent, all deliverables addressed.
Related Skills
38_document_semantic_coherence.md— Contradiction prevention39_cross_reference_integrity.md— Reference management40_status_marker_hygiene.md— Marker accuracy41_content_deduplication_discipline.md— Single source of truth42_voice_and_cadence_consistency.md— Writing style43_structural_completeness_verification.md— Document structure
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/long-document-revision-protocol/SKILL.md
Popularity
- Repository stars
- 17
- Repository forks
- 7
- 7-day trend score
- 14
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/carloscape/octorato/long-document-revision-protocol)