council

Convene the Council of High Intelligence — multi-persona deliberation with historical thinkers for deeper analysis of complex problems.

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/council/SKILL.md

Quality

Content

58%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.

The skill delivers clear, actionable prompt templates and a well-sequenced 3-round deliberation workflow with enforcement checkpoints. Its main weaknesses are a monolithic, oversized SKILL.md that should be split into referenced files and broken links to a non-existent agents/ directory.

Suggestions

Move the 11-member table, polarity pairs, and full triad/profile definitions into reference files (e.g., MEMBERS.md, PROFILES.md) and link to them from a lean overview, improving both conciseness and progressive disclosure.

Create the referenced agents/ directory with the per-member council-{name}.md agent definitions (or remove the reference if the agents are meant to be created on demand) so the Round 1 template's path actually resolves.

Add a brief validation/verification checkpoint after Round 3 before synthesis (e.g., confirm dissent quota and counterfactual pass were satisfied) to push workflow clarity to 5.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with tight prompt templates, but the 11-member table, polarity pairs, three profiles, and full triad tables are bulky reference material that could be split out of the main SKILL.md.	3 / 5
Actionability	Provides concrete, copy-paste-ready prompt templates for each round plus explicit subagent_type and intervention triggers, with only minor gaps (e.g., no concrete example of populated execution metadata).	4 / 5
Workflow Clarity	The 3-round deliberation protocol is clearly sequenced with anti-recursion/anti-convergence enforcement acting as validation checkpoints; minor gap is that routing/validation is described narratively rather than as a checklist.	4 / 5
Progressive Disclosure	The body is a single monolithic SKILL.md with all 11 member bios, triad tables, and three profiles inlined; it references an agents/ directory and configs/ example that do not exist in the bundle, so the one-level-deep split is not actually present.	2 / 5
	Total	13 / 20 Passed

Description

53%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.

The description clearly communicates what the skill does and carves out a distinctive niche, but it omits any explicit trigger ('Use when...') guidance and the action list is only moderately specific. Missing trigger guidance is the primary weakness per the rubric.

Suggestions

Append an explicit 'Use when...' clause naming concrete trigger phrases (e.g., 'Use when tackling complex, high-stakes decisions, multi-stakeholder tradeoffs, or when you want adversarial cross-checking of an analysis').

Add 1-2 more concrete actions or outcomes (e.g., 'synthesizes a verdict with consensus, dissent, and recommended next steps') to lift specificity from 3 toward 4-5.

Include natural user-facing synonyms ('hard decisions', 'stress-test an idea', 'red-team my reasoning') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('multi-persona deliberation with historical thinkers') and a couple concrete actions ('Convene', 'deliberation', 'deeper analysis'), but coverage is not comprehensive.	3 / 5
Completeness	A clear 'what' is present, but there is no 'when'/'Use when' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Contains some relevant keywords ('complex problems', 'deeper analysis', 'multi-persona deliberation') but misses natural synonyms and the common phrasings a user would actually say.	3 / 5
Distinctiveness Conflict Risk	The niche (historical-thinker council deliberation) is clearly distinct from other skills with only minor overlap risk against generic analysis skills.	4 / 5
	Total	13 / 20 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: 0xRabbidfly/Eric-Cartman
Path: .claude/skills/council/SKILL.md
Commit: a052af0

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.