council

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

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./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 skill is highly actionable and exceptionally well-sequenced with strong validation checkpoints and feedback loops. Its weaknesses are verbosity from embedded rationale and a monolithic structure with missing referenced config files.

Suggestions

Move the inline rationale/justification paragraphs and arXiv citations into a separate references file so the main flow stays lean.

Split the 18-member table, triad/profile tables, and verdict templates into a references/ file (or create the missing configs/ files) so SKILL.md reads as an overview with one-level-deep pointers.

Tighten the flag tables and dispatch sections by dropping motivational prose ('Why now', 'Reasoning:') that does not change the executable instructions.

Dimension	Reasoning	Score
Conciseness	The ~940-line body is mostly functional but padded with rationale/justification paragraphs ('Why now:', 'Reasoning:', 'This block is intentionally not...'), repeated arXiv citations, and verbose flag prose that could be trimmed without losing guidance.	2 / 3
Actionability	Provides copy-paste bash heredocs per exec_method, exact prompt templates, a precise routing algorithm, and explicit flag tables — fully executable and specific.	3 / 3
Workflow Clarity	Tightly sequenced STEP 0 through STEP 8 with explicit [CHECKPOINT] gates, [VERIFY] enforcement scans, and feedback loops (fallback rules, re-prompting for missing STANCE lines).	3 / 3
Progressive Disclosure	The body is monolithic — all 18-member tables, triads, profiles, and verdict templates are inline rather than split into reference files, and referenced configs (configs/auto-route-defaults.yaml, configs/provider-model-slots.example.yaml) do not exist in the bundle.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 conveys a distinctive concept but relies on branded language and abstract actions while omitting any explicit trigger guidance for when to use it. It answers 'what' but not 'when', and lacks natural user-facing keywords.

Suggestions

Add an explicit 'Use when ...' trigger clause naming natural situations (e.g., 'Use when weighing a tough decision, stress-testing a plan, or wanting adversarial multi-perspective analysis').

Replace branded phrasing with concrete user-facing terms (e.g., 'decision', 'tradeoff', 'pros and cons', 'should we') so the description matches how users actually ask.

List concrete capabilities (e.g., 'convene a panel, run cross-examination rounds, tally confidence-weighted votes, and synthesize a verdict') instead of the abstract 'deeper analysis'.

Dimension	Reasoning	Score
Specificity	Names the domain ('multi-persona deliberation') and actions ('convene', 'deliberation', 'deeper analysis') but the actions are abstract rather than a list of concrete capabilities, matching the 'names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	States what the skill does but provides no 'Use when...' clause or equivalent trigger guidance for when to invoke it, so completeness is capped at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	Uses branded phrasing ('Council of High Intelligence', 'multi-persona deliberation', 'historical thinkers') rather than terms a user would naturally say, and misses common variations like 'decision', 'pros and cons', or 'should we'.	2 / 3
Distinctiveness Conflict Risk	The historical-thinkers deliberation niche is fairly distinct, but 'deeper analysis of complex problems' is generic enough to overlap with general analysis or decision-making skills.	2 / 3
	Total	8 / 12 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
skill_md_line_count	SKILL.md is long (941 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: 0xNyk/council-of-high-intelligence
Path: SKILL.md
Commit: c1395a6

Reviewed: 5 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.