TextNLPClassifierApp/graphify-out/2026-08-19/GRAPH_REPORT.md

Graph Report - TextNLPClassifierApp (2026-08-19)

Corpus Check

• 45 files · ~42,078 words
• Verdict: corpus is large enough that graph structure adds value.

Summary

• 310 nodes · 284 edges · 40 communities (34 shown, 6 thin omitted)
• Extraction: 100% EXTRACTED · 0% INFERRED · 0% AMBIGUOUS
• Token cost: 0 input · 0 output

Community Hubs (Navigation)

• Tasks: [FEATURE NAME]
• Execution Steps
• common.ps1
• What You Must Do When Invoked
• speckit-analyze/SKILL.md
• 4. Detection Passes (Token-Efficient Analysis)
• Feature Specification: [FEATURE NAME]
• rules/graphify.md
• speckit-plan/SKILL.md
• speckit-specify/SKILL.md
• speckit-tasks/SKILL.md
• Core Principles
• Core Principles
• graphify reference: extra exports and benchmark
• Ponytail
• Implementation Plan: [FEATURE]
• Ponytail Help
• speckit-checklist/SKILL.md
• speckit-clarify/SKILL.md
• speckit-implement/SKILL.md
• graphify reference: query, path, explain
• speckit-constitution/SKILL.md
• create-new-feature.ps1
• ponytail-audit/SKILL.md
• Ponytail Gain
• ponytail-review/SKILL.md
• speckit-taskstoissues/SKILL.md
• [CHECKLIST TYPE] Checklist: [FEATURE NAME]
• graphify reference: add a URL and watch a folder
• graphify reference: commit hook and native CLAUDE.md integration
• graphify reference: incremental update and cluster-only
• ponytail-debt/SKILL.md
• graphify reference: GitHub clone and cross-repo merge
• graphify reference: transcribe video and audio
• extraction-spec.md
• workflows/graphify.md

God Nodes (most connected - your core abstractions)

1. Tasks: [FEATURE NAME] - 13 edges
2. What You Must Do When Invoked - 12 edges
3. /graphify - 10 edges
4. graphify reference: extra exports and benchmark - 8 edges
5. Ponytail - 8 edges
6. Ponytail Help - 7 edges
7. Execution Steps - 7 edges
8. 4. Detection Passes (Token-Efficient Analysis) - 7 edges
9. Execution Steps - 7 edges
10. Core Principles - 6 edges

Surprising Connections (you probably didn't know these)

• None detected - all connections are within the same source files.

Import Cycles

• None detected.

Communities (40 total, 6 thin omitted)

Community 0 - "Tasks: [FEATURE NAME]"

Cohesion: 0.07 Nodes (26): Dependencies & Execution Order, Format: [ID] [P?] [Story] Description, Implementation for User Story 1, Implementation for User Story 2, Implementation for User Story 3, Implementation Strategy, Incremental Delivery, MVP First (User Story 1 Only) (+18 more)

Community 1 - "Execution Steps"

Cohesion: 0.12 Nodes (15): 1. Initialize Convergence Context, 2. Load Artifacts (Progressive Disclosure), 3. Build the Intent Inventory, 4. Assess the Codebase and Classify Findings, 5. Assign Severity, 6. Present the In-Session Findings Summary, 7. Append Convergence Tasks (or report converged), 8. Provide Next Actions (Handoff) (+7 more)

Community 2 - "common.ps1"

Cohesion: 0.23 Nodes (13): Find-SpecifyRoot(), Format-SpecKitCommand(), Get-CurrentBranch(), Get-FeaturePathsEnv(), Get-InvokeSeparator(), Get-NormalizedPriority(), Get-Python3Command(), Get-RepoRoot() (+5 more)

Community 3 - "What You Must Do When Invoked"

Cohesion: 0.08 Nodes (24): For /graphify add and --watch, For /graphify query, For the commit hook and native CLAUDE.md integration, For --update and --cluster-only, /graphify, Honesty Rules, Interpreter guard for subcommands, Part A - Structural extraction for code files (+16 more)

Community 4 - "speckit-analyze/SKILL.md"

Cohesion: 0.15 Nodes (12): 7. Provide Next Actions, 8. Offer Remediation, 9. Check for extension hooks, Analysis Guidelines, Context, Context Efficiency, Goal, Operating Constraints (+4 more)

Community 5 - "4. Detection Passes (Token-Efficient Analysis)"

Cohesion: 0.15 Nodes (13): 1. Initialize Analysis Context, 2. Load Artifacts (Progressive Disclosure), 3. Build Semantic Models, 4. Detection Passes (Token-Efficient Analysis), 5. Severity Assignment, 6. Produce Compact Analysis Report, A. Duplication Detection, B. Ambiguity Detection (+5 more)

Community 6 - "Feature Specification: [FEATURE NAME]"

Cohesion: 0.15 Nodes (12): Assumptions, Edge Cases, Feature Specification: [FEATURE NAME], Functional Requirements, Key Entities (include if feature involves data), Measurable Outcomes, Requirements (mandatory), Success Criteria (mandatory) (+4 more)

Community 8 - "speckit-plan/SKILL.md"

Cohesion: 0.18 Nodes (10): Completion Report, Done When, Key rules, Mandatory Post-Execution Hooks, Outline, Phase 0: Outline & Research, Phase 1: Design & Contracts, Phases (+2 more)

Community 9 - "speckit-specify/SKILL.md"

Cohesion: 0.18 Nodes (10): Completion Report, Done When, For AI Generation, Mandatory Post-Execution Hooks, Outline, Pre-Execution Checks, Quick Guidelines, Section Requirements (+2 more)

Community 10 - "speckit-tasks/SKILL.md"

Cohesion: 0.18 Nodes (10): Checklist Format (REQUIRED), Completion Report, Done When, Mandatory Post-Execution Hooks, Outline, Phase Structure, Pre-Execution Checks, Task Generation Rules (+2 more)

Community 11 - "Core Principles"

Cohesion: 0.18 Nodes (10): Core Principles, Governance, [PRINCIPLE_1_NAME], [PRINCIPLE_2_NAME], [PRINCIPLE_3_NAME], [PRINCIPLE_4_NAME], [PRINCIPLE_5_NAME], [PROJECT_NAME] Constitution (+2 more)

Community 12 - "Core Principles"

Cohesion: 0.18 Nodes (10): Core Principles, Governance, [PRINCIPLE_1_NAME], [PRINCIPLE_2_NAME], [PRINCIPLE_3_NAME], [PRINCIPLE_4_NAME], [PRINCIPLE_5_NAME], [PROJECT_NAME] Constitution (+2 more)

Community 13 - "graphify reference: extra exports and benchmark"

Cohesion: 0.22 Nodes (8): graphify reference: extra exports and benchmark, Step 6b - Wiki (only if --wiki flag), Step 7 - Neo4j export (only if --neo4j or --neo4j-push flag), Step 7a - FalkorDB export (only if --falkordb or --falkordb-push flag), Step 7b - SVG export (only if --svg flag), Step 7c - GraphML export (only if --graphml flag), Step 7d - MCP server (only if --mcp flag), Step 8 - Token reduction benchmark (only if total_words > 5000)

Community 14 - "Ponytail"

Cohesion: 0.22 Nodes (8): Boundaries, Intensity, Output, Persistence, Ponytail, Rules, The ladder, When NOT to be lazy

Community 15 - "Implementation Plan: [FEATURE]"

Cohesion: 0.22 Nodes (8): Complexity Tracking, Constitution Check, Documentation (this feature), Implementation Plan: [FEATURE], Project Structure, Source Code (repository root), Summary, Technical Context

Community 16 - "Ponytail Help"

Cohesion: 0.25 Nodes (7): Configure Default Mode, Deactivate, Levels, More, Ponytail Help, Skills, Update

Community 17 - "speckit-checklist/SKILL.md"

Cohesion: 0.25 Nodes (7): Anti-Examples: What NOT To Do, Checklist Purpose: "Unit Tests for English", Example Checklist Types & Sample Items, Execution Steps, Post-Execution Checks, Pre-Execution Checks, User Input

Community 18 - "speckit-clarify/SKILL.md"

Cohesion: 0.29 Nodes (6): Completion Report, Done When, Mandatory Post-Execution Hooks, Outline, Pre-Execution Checks, User Input

Community 19 - "speckit-implement/SKILL.md"

Cohesion: 0.29 Nodes (6): Completion Report, Done When, Mandatory Post-Execution Hooks, Outline, Pre-Execution Checks, User Input

Community 20 - "graphify reference: query, path, explain"

Cohesion: 0.33 Nodes (5): For /graphify explain, For /graphify path, graphify reference: query, path, explain, Step 0 — Constrained query expansion (REQUIRED before traversal), Step 1 — Traversal

Community 21 - "speckit-constitution/SKILL.md"

Cohesion: 0.33 Nodes (5): Outline, Post-Execution Checks, Pre-Execution Checks, Scope Guard, User Input

Community 23 - "ponytail-audit/SKILL.md"

Cohesion: 0.40 Nodes (4): Boundaries, Hunt, Output, Tags

Community 24 - "Ponytail Gain"

Cohesion: 0.40 Nodes (4): Boundaries, Honesty boundary, Ponytail Gain, Scoreboard

Community 25 - "ponytail-review/SKILL.md"

Cohesion: 0.40 Nodes (4): Boundaries, Examples, Format, Scoring

Community 26 - "speckit-taskstoissues/SKILL.md"

Cohesion: 0.40 Nodes (4): Outline, Post-Execution Checks, Pre-Execution Checks, User Input

Community 27 - "[CHECKLIST TYPE] Checklist: [FEATURE NAME]"

Cohesion: 0.40 Nodes (4): [Category 1], [Category 2], [CHECKLIST TYPE] Checklist: [FEATURE NAME], Notes

Community 28 - "graphify reference: add a URL and watch a folder"

Cohesion: 0.50 Nodes (3): For /graphify add, For --watch, graphify reference: add a URL and watch a folder

Community 29 - "graphify reference: commit hook and native CLAUDE.md integration"

Cohesion: 0.50 Nodes (3): For git commit hook, For native CLAUDE.md integration, graphify reference: commit hook and native CLAUDE.md integration

Community 30 - "graphify reference: incremental update and cluster-only"

Cohesion: 0.50 Nodes (3): For --cluster-only, For --update (incremental re-extraction), graphify reference: incremental update and cluster-only

Community 31 - "ponytail-debt/SKILL.md"

Cohesion: 0.50 Nodes (3): Boundaries, Output, Scan

Knowledge Gaps

• 212 isolated node(s): graphify, Usage, What graphify is for, Step 0 - GitHub repos and multi-path merge (only if a URL or several paths), Step 1 - Ensure graphify is installed (+207 more) These have ≤1 connection - possible missing edges or undocumented components.
• 6 thin communities (<3 nodes) omitted from report — run graphify query to explore isolated nodes.

Suggested Questions

Questions this graph is uniquely positioned to answer:

• Why does Execution Steps connect 4. Detection Passes (Token-Efficient Analysis) to speckit-analyze/SKILL.md? High betweenness centrality (0.004) - this node is a cross-community bridge.
• What connects graphify, Usage, What graphify is for to the rest of the system? 212 weakly-connected nodes found - possible documentation gaps or missing edges.
• Should Tasks: [FEATURE NAME] be split into smaller, more focused modules? Cohesion score 0.07407407407407407 - nodes in this community are weakly interconnected.
• Should Execution Steps be split into smaller, more focused modules? Cohesion score 0.125 - nodes in this community are weakly interconnected.
• Should What You Must Do When Invoked be split into smaller, more focused modules? Cohesion score 0.08 - nodes in this community are weakly interconnected.