council

Run a model-diverse subagent council to investigate the same problem from multiple perspectives, compare findings, and produce a final recommendation. Use this skill whenever the user asks for a council, second opinions, multiple agents/models to evaluate one question, parallel investigation, red-team/blue-team comparison, or help deciding between competing technical approaches.

Quality

90%

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

Quality

Content

81%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 body is a well-sequenced, actionable orchestration playbook with explicit checkpoints and a usable output template. The main room for improvement is trimming a few restated points and possibly externalizing the lengthy model-selection guidance.

Suggestions

Trim restated guidance such as 'The user needs the distilled recommendation, not every intermediate detail' and consolidate the duplicate read-only/worktree cautions in step 2 and the Practical notes.

Consider moving the model-roster selection guidance (step 2) into a references file, keeping SKILL.md focused on the workflow and decision criteria.

Soften hard-coded model IDs (Opus 4.7, GPT 5.5, Kimi 2.6, GLM 5.1) or label them clearly as illustrative, since they date quickly and may not resolve in every harness.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence (no preamble about what subagents or councils are), but a few sentences restate the obvious — e.g. 'The user needs the distilled recommendation, not every intermediate detail' — and the roster guidance is somewhat lengthy.	4 / 5
Actionability	Concrete and executable: a default three-member roster with specific model families, named angle combinations, a 7-item structured-report checklist, and a copy-ready final-answer template. Minor gaps: the example model IDs are illustrative rather than guaranteed valid IDs.	4 / 5
Workflow Clarity	A clear 6-step sequence (Frame → Choose → Brief → Ask → Collect → Synthesize) with explicit checkpoints — 'wait for approval before calling run_agents', 'send a focused follow-up question... rather than launching a replacement' — and a feedback loop for incomplete reports.	5 / 5
Progressive Disclosure	Well-organized into clearly headed sections with the template fenced inline; no bundle files exist so structure stands on sectioning alone. Slightly under a 5 only because some of the roster/model-selection guidance could arguably live in a reference file.	4 / 5
	Total	17 / 20 Passed

Description

100%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 is exemplary: it states the capability concretely, gives explicit trigger guidance with natural synonyms, and occupies a distinct niche. It hits every anchor at the top level.

Dimension	Reasoning	Score
Specificity	Names the domain (model-diverse subagent council) and lists multiple concrete actions — 'investigate the same problem from multiple perspectives, compare findings, and produce a final recommendation' — covering the full workflow.	5 / 5
Completeness	Explicitly answers both what ('Run a model-diverse subagent council... synthesize... recommendation') and when ('Use this skill whenever the user asks for...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases users would actually say: 'council, second opinions, multiple agents/models to evaluate one question, parallel investigation, red-team/blue-team comparison, or help deciding between competing technical approaches.'	5 / 5
Distinctiveness Conflict Risk	'model-diverse subagent council' is a clear niche with distinct triggers; the multi-model/council framing is unlikely to collide with other skills.	5 / 5
	Total	20 / 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: warpdotdev/common-skills
Path: .agents/skills/council/SKILL.md
Commit: b811c24

Reviewed: ~3 hours 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.