The description introduces an interesting concept (multi-LLM debate for code review) but fails to provide actionable trigger guidance and relies on jargon rather than natural user language. It lacks explicit 'when to use' criteria and doesn't enumerate specific concrete actions the skill performs.

Suggestions

Add an explicit 'Use when...' clause with natural trigger terms like 'review my code', 'get multiple perspectives', 'architecture decision', 'design feedback'

Replace jargon like 'craftsmanship council' with concrete actions: 'Simulates multiple expert reviewers debating code quality, architecture decisions, and design tradeoffs'

Include common user phrases that would trigger this skill: 'second opinion on code', 'compare approaches', 'pros and cons of design'

Dimension	Reasoning	Score
Specificity	Names the domain (multi-LLM, code review, design questions) and mentions some features (live progress, debate mode), but lacks concrete actions like 'reviews code', 'generates feedback', or 'compares implementations'.	2 / 3
Completeness	Describes what it is (a multi-LLM council with debate mode) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'code review' and 'design questions' that users might say, but 'craftsmanship council' and 'multi-LLM' are jargon unlikely to appear in natural user requests. Missing common variations like 'review my code', 'architecture feedback', 'PR review'.	2 / 3
Distinctiveness Conflict Risk	The 'multi-LLM council' and 'debate mode' concepts are somewhat distinctive, but 'code review' and 'design questions' are broad enough to potentially overlap with general code review or architecture skills.	2 / 3
	Total	7 / 12 Passed

Implementation

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is well-organized and concise, with good progressive disclosure that keeps the overview lean while pointing to detailed protocol documentation. However, actionability suffers from delegating all concrete workflow steps to an external file without providing any inline examples of actual CLI usage or expected output formats.

Suggestions

Add a minimal inline example showing a complete CLI invocation (e.g., `$STAR_CHAMBER_PATH/bin/star-chamber --file src/main.py --provider openai`) with expected output format

Include a brief summary of the key workflow steps (Steps 0-4) inline, even if details are in PROTOCOL.md, so Claude has immediate context without file reads

Dimension	Reasoning	Score
Conciseness	The content is lean and efficient, avoiding unnecessary explanations. It assumes Claude understands concepts like LLM providers, CLI flags, and git changes without over-explaining.	3 / 3
Actionability	Provides concrete path setup with bash example, but delegates the actual protocol to an external file (PROTOCOL.md). The skill itself lacks executable examples of CLI invocation or expected outputs.	2 / 3
Workflow Clarity	References Steps 0-4 in PROTOCOL.md but doesn't show the workflow inline. The path setup is clear, but the actual multi-step process is hidden behind a file reference without summarizing key checkpoints.	2 / 3
Progressive Disclosure	Excellent structure with clear overview, well-organized argument table, and explicit one-level-deep reference to PROTOCOL.md for detailed steps. Navigation is straightforward.	3 / 3
	Total	10 / 12 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Reviewed

2 months ago

Table of Contents

Discovery Implementation Validation