From example-skills
Enforce the Orchestrator Voice Constitution during text generation. Provides voice constraints, anti-pattern awareness, and scoring guidance. Use when writing or reviewing prose-heavy documents (READMEs, design docs, essays, manifestos).
npx claudepluginhub organvm-iv-taxis/a-i--skills --plugin document-skillsThis skill uses the workspace's default tool permissions.
You have access to the Orchestrator Voice Constitution and Rulebook in this skill's references/ directory. Use them to guide your writing.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Designs, implements, and audits WCAG 2.2 AA accessible UIs for Web (ARIA/HTML5), iOS (SwiftUI traits), and Android (Compose semantics). Audits code for compliance gaps.
You have access to the Orchestrator Voice Constitution and Rulebook in this skill's references/ directory. Use them to guide your writing.
Activate when writing or editing prose-heavy documents: READMEs, design docs, vision documents, essays, manifestos, CLAUDE.md files, or any text that represents the orchestrator's voice.
Default discourse sequence: opening distinction → field definition → layering → formalization → governance → extension
Identity invariants (always preserve):
Top anti-patterns (never use):
If voice-scorer CLI is installed:
voice-scorer score path/to/doc.md # Heuristic score
voice-scorer score --deep path/to/doc.md # Deep LLM scoring
voice-scorer diff path/to/doc.md # Voice erosion check
See references/VOICE_CONSTITUTION.md and references/VOICE_RULEBOOK.md for complete governance rules.