Skills
.Work. You
Rest

safer-docs-reader

Community

Orchestrate four haiku personas to audit docs.

Content & Communication#orchestration#aggregation#review#docs#artifact#haiku
Authorchughtapan
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Cold-start auditing of a docs artifact (GitHub issue/PR body or local markdown) by orchestrating four haiku personas to produce a structured verdict and prevent context leakage, ensuring consistent review quality.

Core Features & Use Cases

  • Ephemeral orchestration: creates a temporary Team and four haiku sub-agents to read the artifact cold.
  • Structured verdicts: collects per-persona judgments and aggregates them via a severity-weighted consensus.
  • Artifact publication: posts the aggregate report back to the artifact's thread or stdout for local files.
  • Round-limited workflow: supports up to 3 rounds with explicit gating for round 3.

Quick Start

Use the skill against an artifact (issue, PR, or file) to trigger the full three-round review and publish the aggregate report.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: safer-docs-reader
Download link: https://github.com/chughtapan/safer-by-default/archive/main.zip#safer-docs-reader

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.