simulate-elite-experts

通过模拟相关领域顶级专家的思考、分歧与收敛，辅助高复杂度、高风险决策。用于用户要求模拟顶尖人物、比较强势观点，或询问“应该找哪些优秀人物来讨论某个问题，以及他们可能会怎么说”。适用于“用世界级专家视角思考”“模拟顶级领域专家”“扮演最强领域人物”和“使用四视角对话”等请求。

Quality

81%

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

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 content is highly actionable and clearly sequenced with strong validation checkpoints, and its bundle references are real and well signaled. The main weaknesses are conciseness (repeated restatement of profile/section/round counts) and progressive disclosure (a body heavier than a lean overview, with spec detail that could be split into references).

Suggestions

Consolidate the role/round/section counts that currently appear in four separate sections into a single canonical table referenced by the others to reduce redundancy and token cost.

Move the detailed Blind-Spot Gated Overlay Workflow and the per-profile section enumerations into a dedicated reference file, keeping SKILL.md as a lean overview with signaled links.

Trim or fold the repeated preflight/postflight and scoring-matrix rules into one guardrail section to tighten the body without losing the validation logic.

Dimension	Reasoning	Score
Conciseness	The body is substantive (hard constraints, matrices, guardrails) rather than padded with basics Claude already knows, but role/round/section counts are restated across four sections ('Fixed Four-Lens Composition', 'Output Contract Guardrail', 'Controlled Execution Profiles', 'Required Output Sections') and could be tightened, matching the mostly-efficient-with-some-redundancy anchor.	3 / 5
Actionability	Provides copy-paste-ready scaffolds — numeric scoring thresholds ('>= 5/6'), confidence tag formats, per-profile section lists, preflight/postflight checklists, and an exact 5-question self-check template — fully executable guidance covering common cases.	5 / 5
Workflow Clarity	A clearly sequenced 7-step workflow with a Gate 0 pre-check, mode selection, scoring-matrix validation, anonymous meta-review, and per-failure-mode recovery actions provides explicit validation steps, feedback loops, and checklists.	5 / 5
Progressive Disclosure	Real, clearly signaled one-level-deep references and scripts ('references/eval-rubric.md', 'scripts/lint_response.py') are present and navigable, but the body is a dense ~440-line spec that inlines detail (overlay workflow, repeated section-count tables) an overview would offload, leaving minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

82%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 cleanly states what the skill does and when to use it, with several natural trigger phrases and a distinct niche that minimizes conflict risk. Its only real weakness is specificity: the stated actions are somewhat abstract rather than a comprehensive enumeration of concrete operations.

Dimension	Reasoning	Score
Specificity	Names the domain ('辅助高复杂度、高风险决策') and 2-3 actions ('模拟...思考、分歧与收敛') but the actions are abstract rather than a comprehensive list of concrete operations, matching the anchor that names the domain and 1-2 concrete actions without full coverage.	3 / 5
Completeness	Explicitly answers both what ('通过模拟...辅助...决策') and when ('用于...适用于...等请求') with concrete quoted trigger phrases, matching the anchor that clearly covers both.	5 / 5
Trigger Term Quality	Enumerates several natural user phrasings ('模拟顶尖人物','比较强势观点','用世界级专家视角思考','四视角对话') with synonym coverage, giving good keyword coverage but not the exhaustive multi-surface-form breadth of the top anchor.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (elite-expert four-lens deliberation for high-stakes decisions) with distinctive triggers ('四视角对话','模拟顶尖人物') and minimal overlap with other skills.	5 / 5
	Total	17 / 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: ooooooooooooooooooop/agent-tools
Path: skills/simulate-elite-experts/SKILL.md
Commit: 915f189

Reviewed: 14 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.