Table of Contents

• When to Use
• Quick Start
• Two-Phase Workflow
• Phase 1: Triage (Fast Model)
• Phase 2: Execute (Main Model)
• Workflow Details
• Step 1: Candidate Detection
• Step 2: Content Analysis
• Step 3: Destination Routing
• Step 4: Generate Plan
• Source: API_REVIEW_REPORT.md
• Post-Consolidation
• Step 5: Execute Merges
• Fast Model Delegation
• Content Categories
• Merge Strategies
• Intelligent Weave
• Replace Section
• Append with Context
• Create New File
• Integration
• Example Session
• Troubleshooting
• No candidates found
• Low-quality extractions
• Merge conflicts
• Related Skills

Doc Consolidation

Extracts valuable knowledge from ephemeral LLM outputs and merges it into permanent documentation.

When To Use

Use this skill when:

• You have untracked *_REPORT.md or *_ANALYSIS.md files from Claude sessions
• Git status shows markdown files that shouldn't be committed but contain useful content
• You want to preserve insights from code reviews, refactoring reports, or API audits
• Preparing a PR and need to clean up working artifacts

Do NOT use when:

• Files are already in proper documentation locations (docs/, skills/)
• Files are intentionally temporary scratch notes
• User explicitly wants to preserve the original report format
• Source files have no extractable value (pure log output)

When NOT To Use

• Files are already in docs/ or skills/ locations
• Files are intentionally temporary scratch notes
• Source files have no extractable value
• Files are already in docs/ or skills/ locations

Quick Start

/consolidate-docs

Verification: Run the command with --help flag to verify availability.

Or invoke directly:

**Verification:** Run the command with `--help` flag to verify availability.
I have some report files that need consolidating into permanent docs.

Verification: Run the command with --help flag to verify availability.

Two-Phase Workflow

Phase 1: Triage (Fast Model)

Read-only analysis to generate a consolidation plan:

1. Detect candidates - Find untracked markdown files with LLM output markers
2. Analyze content - Extract and categorize valuable sections
3. Route destinations - Match content to existing docs or propose new files
4. Present plan - Show user what will be consolidated and where

Checkpoint: User reviews and approves plan before execution.

Phase 2: Execute (Main Model)

After approval, performs the consolidation:

1. Merge content - Weave into existing docs or create new files
2. Delete sources - Remove ephemeral files after successful merge
3. Generate summary - Report what was created/updated/deleted

Workflow Details

Step 1: Candidate Detection

Load: @modules/candidate-detection.md

Identifies files using:

• Git status (untracked .md files)
• Location (not in standard doc directories)
• Naming (ALL_CAPS non-standard names)
• Content markers (Executive Summary, Findings, Action Items)

Step 2: Content Analysis

Load: @modules/content-analysis.md

For each candidate:

• Extract sections as content chunks
• Categorize: Actionable Items, Decisions, Findings, Metrics, Migration Guides, API Changes
• Score value: high/medium/low

Step 3: Destination Routing

Load: @modules/destination-routing.md

For each valuable chunk:

• Semantic match against existing documentation
• Apply default mappings if no good match
• Determine merge strategy (weave, replace, append, create)

Step 4: Generate Plan

Present consolidation plan to user:

# Consolidation Plan

## Source: API_REVIEW_REPORT.md

| Content | Category | Value | Destination | Action |
|---------|----------|-------|-------------|--------|
| API inventory | Findings | High | docs/api-overview.md | Create |
| Action items | Actionable | High | docs/plans/2025-12-06-api.md | Create |

### Post-Consolidation
- Delete: API_REVIEW_REPORT.md

Proceed with consolidation? [Y/n]

Verification: Run the command with --help flag to verify availability.

Step 5: Execute Merges

Load: @modules/merge-execution.md

After user approval:

• Group operations by destination file
• Apply merge strategies
• Validate results (frontmatter intact, structure preserved)
• Delete source files
• Generate execution summary

Fast Model Delegation

Phase 1 tasks are delegated to haiku-class models for efficiency:

# scripts/consolidation_planner.py handles:
- scan_for_candidates()
- extract_content_chunks()
- categorize_chunks()
- score_value()
- find_semantic_matches()

Verification: Run the command with --help flag to verify availability.

Phase 2 stays on the main model for careful merge execution.

Content Categories

Category	Description	Default Destination
Actionable Items	Tasks, TODOs, next steps	docs/plans/YYYY-MM-DD-{topic}.md
Decisions Made	Architecture choices	docs/adr/NNNN-{date}-{topic}.md
Findings/Insights	Audit results, analysis	Best-match existing doc
Metrics/Baselines	Before/after comparisons	docs/benchmarks/
Migration Guides	Step-by-step procedures	docs/migration-guide.md
API Changes	Breaking changes, deprecations	CHANGELOG or api docs

Merge Strategies

Intelligent Weave

Insert content into matching existing sections, preserving style.

Use when: Destination has relevant section, content is additive.

Replace Section

Replace existing section with more detailed new content.

Use when: New content 2x+ more detailed or has later date.

Append with Context

Add new section with date and source reference.

Use when: No matching section, content doesn't fit existing structure.

Create New File

Generate complete new document.

Use when: No suitable destination exists, content warrants standalone doc.

Integration

Works with other sanctum skills:

• git-workspace-review: May suggest consolidation when untracked reports detected
• pr-prep: Warns about untracked analysis files before PR creation
• doc-updates: Can invoke for final polish after consolidation

Example Session

**Verification:** Run the command with `--help` flag to verify availability.
User: I have API_REVIEW_REPORT.md from our review session. Can you consolidate it?

Claude: I'll consolidate the report into permanent documentation.

**Phase 1: Triage**

Scanning for candidates...
- Found: API_REVIEW_REPORT.md (untracked, LLM markers detected)

Analyzing content...
- Extracted 6 content chunks
- High value: API inventory, action items, CLI recommendation
- Medium value: security assessment
- Low value: executive summary (generic)

Routing destinations...
- API inventory → docs/api-overview.md (CREATE)
- Action items → docs/plans/2025-12-06-api-consistency.md (CREATE)
- CLI naming → docs/adr/0002-cli-naming.md (CREATE ADR)
- Security → Already covered in docs/security.md (SKIP)

**Consolidation Plan**
[table shown]

Proceed? [Y/n]

User: Y

Claude: **Phase 2: Executing**

Created: docs/api-overview.md (1,247 bytes)
Created: docs/plans/2025-12-06-api-consistency.md (892 bytes)
Created: docs/adr/0002-2025-12-06-cli-naming.md (634 bytes)
Deleted: API_REVIEW_REPORT.md

Consolidation complete. Review the created files and commit when ready.

Verification: Run the command with --help flag to verify availability.

Troubleshooting

No candidates found

• Check git status for untracked files
• Files may already be in standard locations
• Try explicit file path: "Consolidate API_REVIEW_REPORT.md"

Low-quality extractions

• Source file may lack structured sections
• Content may be too generic to categorize
• Try manual extraction for unstructured reports

Merge conflicts

• Destination file structure changed
• Try APPEND strategy instead of WEAVE
• Manual intervention may be needed

Related Skills

• sanctum:doc-updates - General documentation updates
• sanctum:git-workspace-review - Pre-flight workspace analysis
• sanctum:pr-prep - Pull request preparation
• imbue:catchup - Understanding recent changes