By defiect
Optimizes documentation directories for AI agent navigation efficiency using parallel subagent reviews and iterative improvement cycles
Fast conciseness reviewer for documentation. Evaluates redundancy, duplication, and fluff. Spawned by docs-optimizer for conciseness audits.
Fast documentation navigation reviewer. Use this agent when evaluating documentation navigability with quick, cost-effective analysis. Spawned by the docs-optimizer skill to perform parallel reviews.
Thorough conciseness reviewer for documentation. Evaluates redundancy, duplication, and fluff with deep analysis. Spawned by docs-optimizer for conciseness audits.
Thorough documentation navigation reviewer. Use this agent when evaluating documentation navigability with detailed analysis and pattern recognition. Spawned by the docs-optimizer skill to perform parallel reviews alongside haiku-reviewer.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin that optimizes documentation directories for AI agent navigation efficiency.
This plugin helps you restructure documentation so that AI agents can find relevant information quickly. It measures success by tool calls (how many Read/Grep/Glob operations), not by whether the docs "help users."
Key insight: If an agent finds "we don't support X" in 2 tool calls, that's a success - even if the user wanted X.
Copy this plugin directory to your Claude Code plugins location:
cp -r docs-optimizer-plugin ~/.claude/plugins/
Or clone directly:
git clone [email protected]:Defiect/docs-optimizer-plugin.git ~/.claude/plugins/docs-optimizer-plugin
The skill auto-activates when you mention documentation optimization. Try:
Test questions are persisted to .claude/docs-optimizer.local.md so scores are directly comparable across rounds.
| Score | Meaning |
|---|---|
| 9-10 | Excellent - 1-2 tool calls per question |
| 7-8 | Good - 3-4 tool calls, minor detours |
| 5-6 | Acceptable - 5+ tool calls, some confusion |
| 3-4 | Poor - many wrong paths |
| 1-2 | Failing - cannot navigate reliably |
docs-optimizer-plugin/
├── .claude-plugin/
│ └── plugin.json # Plugin manifest
├── skills/
│ └── docs-optimizer/
│ ├── SKILL.md # Main skill (orchestrates workflow)
│ └── references/
│ ├── north-star.md # Core principle
│ ├── playbook.md # 4-phase methodology
│ └── scoring-rubric.md # Scoring criteria
├── agents/
│ ├── haiku-reviewer.md # Fast navigation reviewer
│ ├── sonnet-reviewer.md # Thorough navigation reviewer
│ ├── haiku-conciseness-reviewer.md # Fast conciseness reviewer
│ └── sonnet-conciseness-reviewer.md # Thorough conciseness reviewer
├── hooks/
│ ├── hooks.json # PreToolUse/PostToolUse hook config
│ ├── pre-subagent.sh # Archives reviews before subagent spawn
│ └── post-subagent.sh # Restores reviews after subagent completes
└── README.md
Optimize for AI navigation efficiency, NOT user satisfaction.
This is counterintuitive but critical. We measure:
We do NOT measure:
.claude/docs-optimizer.local.md for cross-round score comparabilitytools to allowed-tools YAML array formatdisallowedTools to reviewer agents (prevents editing source docs)allowed-tools to main skill for clarityMethodology developed through iterative testing on real documentation sets, measuring actual AI agent navigation patterns with Haiku and Sonnet reviewers.
npx claudepluginhub defiect/docs-optimizer-plugin --plugin docs-optimizerOptimizes documentation directories for AI agent navigation efficiency using parallel subagent reviews and iterative improvement cycles
Multi-agent deep research orchestrator with evidence graphs, quality gates, and publication-quality report generation.
DefiectMake a codebase agent-ready by scaffolding AGENTS.md, ARCHITECTURE.md, and docs/ structure following progressive disclosure patterns. Creates CLAUDE.md as a symlink for Claude Code compatibility.
dgalarzaDocumentation and authoring workflow router: audit docs vs code drift, sync docs after changes, optimize prompts and SKILL.md files, validate GLFM and Markdown formatting, summarize files/URLs/images with fidelity enforcement. Use when: docs are out of date, CLAUDE.md needs improving, SKILL.md needs optimizing, checking if documentation matches code, summarizing files or URLs.
Jamie-BitFlightUse this agent when you need to analyze a service or codebase component and create comprehensive documentation in CLAUDE.md files. This agent should be invoked after implementing new services, major refactoring, or when documentation needs updating to reflect the current codebase structure. Examples: <example>Context: The user has just implemented a new authentication service and wants to document it properly. user: 'I just finished implementing the auth service, can you document how it works?' assistant: 'I'll use the codebase-documenter agent to analyze the authentication service and create detailed documentation in CLAUDE.md' <commentary>Since the user has completed a service implementation and needs documentation, use the Task tool to launch the codebase-documenter agent to create comprehensive CLAUDE.md documentation.</commentary></example> <example>Context: The user wants to ensure a newly added API module is properly documented for the team. user: 'We need documentation for the new payment processing API I just added' assistant: 'Let me use the codebase-documenter agent to analyze the payment processing API and create proper documentation' <commentary>The user needs documentation for a new API module, so use the codebase-documenter agent to create CLAUDE.md files with setup instructions and architectural notes.</commentary></example>
ananddtyagiOptimize documentation for AI coding assistants and LLMs. Features c7score evaluation, llms.txt generation, question-driven restructuring, and automated quality scoring. Makes your docs perfect for Claude, Copilot, and other AI tools.
alonw0Lightweight documentation memory for AI coding agents: scaffold a docs tree, validate it, and auto-load recent context each session.
MedAdemBHAUpstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
upstash