skill-council

Run a configurable multi-LLM council with personas, budget caps, synthesis, veto gates, and optional implementation handoff.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/skill-council/SKILL.md

Quality

Content

77%

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

The content is highly actionable and well-sequenced with explicit validation checkpoints and gates, but it leans verbose by inlining a full clarification interaction and flag tables that would benefit from extraction into referenced bundle files, which are currently absent.

Suggestions

Move the full AskUserQuestion JavaScript block and the flag-translation tables into a references/ file (e.g. CLARIFICATION.md) and link to it one level deep, keeping only the essentials inline to improve conciseness and progressive disclosure.

Add a brief 'Use when...' trigger line near the top of the body so the when-to-use intent is explicit in the content as well as the description.

Dimension	Reasoning	Score
Conciseness	The body is mostly task-focused and avoids explaining concepts Claude already knows, but the full inline AskUserQuestion JavaScript block and repeated flag-translation tables add bulk that could be referenced from a bundle file instead of inlined.	2 / 3
Actionability	It provides concrete, copy-paste-ready guidance: the exact orchestrate.sh invocation with environment fallback, explicit runner flags, and a full AskUserQuestion call with answer-to-flag mappings.	3 / 3
Workflow Clarity	The phases are clearly sequenced (Phase 0A clarification -> Phase 0 preflight -> procedure -> gates), with explicit validation checkpoints such as re-checking budget before each phase, quorum rules, and ratify/veto gates for risky operations.	3 / 3
Progressive Disclosure	No bundle files exist in references/, scripts/, or assets/, and the body is a single monolithic document inlining a large clarification block and full flag tables rather than offloading them to one-level-deep referenced files.	2 / 3
	Total	10 / 12 Passed

Description

65%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and distinctive about the council's features, but it omits any explicit 'Use when...' trigger guidance, so it answers 'what' well while leaving 'when' only implied. Adding a trigger clause would lift completeness.

Suggestions

Append a 'Use when...' clause (e.g. 'Use when the user wants a multi-LLM council, panel review, or second-opinion discussion across personas') to make when-to-use explicit and raise completeness to 3.

Add common natural trigger terms like 'second opinion', 'panel', or 'multi-model review' alongside 'council' to broaden natural-language matching.

Dimension	Reasoning	Score
Specificity	Names several concrete capabilities — 'personas', 'budget caps', 'synthesis', 'veto gates', and 'implementation handoff' — which are specific functional features rather than vague language.	3 / 3
Completeness	It clearly answers what the skill does, but there is no 'Use when...' clause or equivalent trigger guidance, so when-to-use is only implied — capping completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	'Multi-LLM council' and 'council' are domain terms a user might say, but common natural variations like 'second opinion', 'multi-model review', or 'panel' are absent and jargon like 'veto gates' is technical.	2 / 3
Distinctiveness Conflict Risk	The council/quorum/persona framing is a distinct niche unlikely to be confused with single-task skills, and the trigger terms are specific enough to avoid broad conflicts.	3 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: nyldn/claude-octopus
Path: skills/skill-council/SKILL.md
Commit: 9f39f0c

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.