CtrlK
BlogDocsLog inGet started
Tessl Logo

consciousness-council

Run a multi-perspective Mind Council deliberation on any question, decision, or creative challenge. Use this skill whenever the user wants diverse viewpoints, needs help making a tough decision, asks for a council/panel/board discussion, wants to explore a problem from multiple angles, requests devil's advocate analysis, or says things like "what would different experts think about this", "help me think through this from all sides", "council mode", "mind council", or "deliberate on this". Also trigger when the user faces a dilemma, trade-off, or complex choice with no obvious answer.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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 body is a well-structured, actionable guide with a clear phased workflow and useful validation feedback loop. Its main weaknesses are some motivational/marketing prose that competes with the token budget and an orphaned reference file with no navigation from the body.

Suggestions

Remove or condense the "Why This Exists" section and the attribution/marketing footer; Claude does not need the collective-intelligence rationale to run the Council.

Link to references/advanced-configurations.md from the body (e.g., add an "Advanced configurations" pointer near the Council Configurations section) so the bundled reference is discoverable instead of orphaned.

Tighten the prose between the archetype table and the templates (e.g., "These are starting points — adapt based on the specific question. The goal is productive disagreement, not consensus.") to reduce restated guidance.

DimensionReasoningScore

Conciseness

The archetype table, templates, and selection heuristics are lean, but the "Why This Exists" prose and research-influence commentary (e.g. "It's not roleplay. It's structured epistemic diversity") plus the marketing-style attribution footer add motivation Claude largely already knows and could be trimmed.

2 / 3

Actionability

Copy-paste-ready output templates (the 🎭 member and ⚖️ synthesis blocks), explicit archetype selection heuristics keyed to question type, and concrete "critical rules" give specific, executable guidance rather than vague direction.

3 / 3

Workflow Clarity

A clearly sequenced three-phase process (Summon → Deliberation → Synthesis) with an explicit feedback loop ("If everyone agrees, the Council has failed — go back and sharpen the tensions") and quality gates around the "Core Tension" synthesis element.

3 / 3

Progressive Disclosure

Sections are reasonably well organized, but the bundled references/advanced-configurations.md is never referenced or linked from the body, so it is orphaned and undiscoverable; content that could be split out remains inline rather than signaled one level deep.

2 / 3

Total

10

/

12

Passed

Description

100%

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 strong across all dimensions: third-person voice, concrete actions, abundant natural trigger terms, and explicit what/when guidance. It is one of the better-constructed descriptions in the reference set.

DimensionReasoningScore

Specificity

Names several concrete capabilities ("Run a multi-perspective Mind Council deliberation", "diverse viewpoints", "devil's advocate analysis", "explore a problem from multiple angles"), matching the anchor listing multiple specific actions rather than a single vague action.

3 / 3

Completeness

Explicitly answers both what ("Run a multi-perspective Mind Council deliberation") and when ("Use this skill whenever..." and "Also trigger when..."), satisfying the top anchor with explicit triggers.

3 / 3

Trigger Term Quality

Includes a rich set of natural phrasings users would actually say, including quoted variants like "council mode", "mind council", "deliberate on this", "help me think through this from all sides", and "devil's advocate analysis".

3 / 3

Distinctiveness Conflict Risk

The branded "Mind Council / council mode" framing with distinctive trigger phrasings carves a clear niche unlikely to collide with other skills, though a few broader terms ("tough decision", "dilemma") have minor overlap.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
K-Dense-AI/scientific-agent-skills
Reviewed

Table of Contents

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.