council

Convene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls. Use when multiple valid paths exist and you need structured disagreement before choosing.

Quality

80%

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

Quality

Content

82%Weight 40%Scale 1-5

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

This is a well-crafted, action-oriented skill: the subagent prompt template, verdict format, anti-anchoring mechanism, and bias guardrails are concrete and immediately executable. The workflow is clearly sequenced and appropriately scoped away from code review and planning. Remaining gains are trimming minor duplication and considering whether the example/follow-up detail belongs in reference files.

Dimension	Reasoning	Score
Conciseness	The body is lean and imperative throughout — tables for When/When NOT to Use, a copy-paste prompt template, and a verdict output template with no padding or explanations of concepts Claude already knows. Not 5 because of minor duplication: the opening four-advisor list restates the Roles table, and the "Role emphasis" bullets largely repeat the lens column.	4 / 5
Actionability	The prompt shape block ("You are the [ROLE] on a four-voice decision council... Respond with: 1. Position...") is copy-paste ready with clear placeholders, the verdict markdown template is fully specified, and the Example section concretely demonstrates the common case. This matches the fully-executable anchor for an instruction-only skill.	5 / 5
Workflow Clarity	A clearly sequenced six-step workflow (extract question → gather context → form Architect position → launch three voices → synthesize → present verdict) with checkpoints such as the clarifying-question gate in step 1 and the bias guardrails in step 5. Not 5 because there is no explicit verification of verdict quality, though this is a decision skill, not a destructive or batch operation, so no cap applies.	4 / 5
Progressive Disclosure	The single-file body is well-sectioned with clear headers and no nested references (no bundle files exist to score against). Good structure with most content appropriately inline; not 5 because at ~200 lines, the Example and Multi-Round Follow-up sections could arguably live in one-level-deep reference files to keep SKILL.md a tighter overview.	4 / 5
	Total	17 / 20 Passed

Description

78%Weight 40%Scale 1-5

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

A strong description: it explicitly states both what the skill does and when to use it, with concrete and natural trigger phrasing in third person. The main weakness is that it names only one concrete action, leaving the mechanics (surfaces tradeoffs, challenges premises, delivers a synthesized verdict) implicit.

Suggestions

Add one or two more concrete outcome verbs to the what-clause, e.g. "Convene a four-voice council that surfaces tradeoffs, challenges premises, and delivers a synthesized go/no-go recommendation."

Include common user phrasings as triggers, such as "second opinion", "devil's advocate", or "pros and cons", to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	"Convene a four-voice council" names the domain ("ambiguous decisions, tradeoffs, and go/no-go calls") and one concrete action, but does not list several specific actions. It sits at the 'domain and 1-2 concrete actions, not comprehensive' anchor — below 4 because there is only a single action verb, and above 2 because the objects of the action are concretely enumerated.	3 / 5
Completeness	Both parts are explicit: the what is "Convene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls" and the when is "Use when multiple valid paths exist and you need structured disagreement before choosing". This matches the anchor for clear, concrete what-and-when with explicit trigger phrasing.	5 / 5
Trigger Term Quality	Good natural phrases users would say: "ambiguous decisions", "tradeoffs", "go/no-go", "multiple valid paths", "structured disagreement". Not 5 because common synonyms like "second opinion", "devil's advocate", or "pros and cons" are missing; clearly above 3 since several natural, varied trigger terms are present.	4 / 5
Distinctiveness Conflict Risk	The four-voice council for structured disagreement is a distinct niche with its own triggers, giving minimal conflict risk. Not 5 because "decisions" and "tradeoffs" are broad terms with minor overlap risk against planning/architecture-type skills.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/council/SKILL.md
Commit: c70874f

Reviewed: 1 day 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.