llm-council

Query multiple LLM models in parallel from CodeAct and cross-reference their responses

Quality

57%

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/llm-council/SKILL.md

Quality

Content

65%

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 with executable, copy-paste-ready code and a clear synthesis workflow. Its main weaknesses are mild token redundancy from repeated council lineups and a missing error-recovery feedback loop for the batch operation.

Suggestions

Add an explicit feedback loop for batch failures (e.g., when a slot returns 'Error: ...', decide whether to retry with a fallback model or proceed and note the gap).

De-duplicate the council lineup by defining COUNCIL once and reusing it in the full example to save tokens.

Consider extracting the per-backend compatibility table and default lineups into a reference file so the main body stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is dense and free of padding about concepts Claude already knows, but the council lineup is repeated across the 'Default council line-up' and 'Full example' sections and the backend table could be tightened.	2 / 3
Actionability	Provides fully executable llm_query/llm_query_batched code, concrete model lists, explicit API signatures, and a copy-paste-ready full example.	3 / 3
Workflow Clarity	The 'After collecting responses' section gives a clear 4-step sequence, but the batch operation lacks an explicit validate/fix/retry feedback loop, which the scoring notes say caps batch workflows at 2.	2 / 3
Progressive Disclosure	The skill is self-contained and well-sectioned, but the substantial inline API reference is content that could be split out, and no external references are signaled.	2 / 3
	Total	9 / 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 concretely states the skill's core actions but lacks an explicit 'when to use' trigger clause, which limits both completeness and trigger-term quality. It is distinct enough to avoid most conflicts yet could be sharpened with natural user keywords.

Suggestions

Add a 'Use when ...' clause naming natural triggers such as 'second opinion', 'compare models', or 'diverse perspectives'.

Expand the action list slightly to name more concrete capabilities (e.g., 'synthesize a unified answer, flag disagreements').

Replace technical phrasing like 'cross-reference their responses' with user-friendly terms to improve trigger term quality.

Dimension	Reasoning	Score
Specificity	Phrases 'Query multiple LLM models in parallel' and 'cross-reference their responses' name the domain plus two concrete actions, but the action list is not comprehensive enough for a 3.	2 / 3
Completeness	It clearly states what the skill does but provides no 'Use when...' trigger clause, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	'multiple LLM models' and 'cross-reference' are relevant but the description omits natural user phrasings like 'second opinion' or 'compare models', leaving common variations missing.	2 / 3
Distinctiveness Conflict Risk	The parallel multi-model querying niche is reasonably specific, but 'cross-reference responses' is generic enough that it could overlap with related analysis 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nearai/ironclaw
Path: skills/llm-council/SKILL.md
Commit: b60038b

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.