simulate-elite-experts

Simulate high-stakes reasoning by modeling how top experts in the relevant domain would think, disagree, and converge on a decision. Use when users ask to role-play strongest minds, compare elite viewpoints, or ask: what would be a good group of people to explore X, and what would they say. Trigger for prompts like "think like world-class experts", "simulate top domain specialists", "role-play strongest domain people", and "use four-lens dialogue".

Quality

89%

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

85%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.

A well-structured, highly actionable reasoning skill with clear validation gates, feedback loops, and clean progressive disclosure to real bundle files. The main weakness is redundant restatement of the 4-role/4-round/7-section constraint.

Suggestions

Consolidate the repeated 'exactly 4 roles, 4 rounds, 7 sections' constraint into one Hard Constraint section and reference it once elsewhere rather than restating it six times, to recover token budget.

Move the preflight/postflight checklists into a single 'Self-check' subsection and cross-reference it from the workflow to reduce scattered repetition.

Consider pulling the Real-Person Scoring Matrix into references/ (e.g. references/scoring-matrix.md) and keeping only the passing rules inline, since the body is already long.

Dimension	Reasoning	Score
Conciseness	Dense and mostly earning its place, but the hard constraint 'exactly 4 roles / 4 rounds / 7 sections' is restated six or more times (Fixed Four-Lens, Output Contract Guardrail, Controlled Execution Profiles, Required Output Sections, Output Contract), which could be tightened.	3 / 5
Actionability	Highly executable for an instruction-only skill: numeric scoring-matrix thresholds (>=5/6, >=2/2, confidence 0.6), a deterministic fallback order, a named 7-section output scaffold, failure modes with recovery actions, and profiles — copy-paste-ready guidance covering common cases.	5 / 5
Workflow Clarity	A 6-step workflow with explicit validation checkpoints (preflight/postflight checklists, scoring-matrix gate, guardrail self-check) and feedback loops (FM1-FM5 recovery actions, 'rerun candidate selection') for a structured-output generation process.	5 / 5
Progressive Disclosure	Overview SKILL.md points to verified one-level-deep bundle files — references/eval-rubric.md, eval-cases.md, output-templates.md, output-templates-zh.md and scripts/lint_response.ps1 — clearly signaled under dedicated Evaluation and Output Contract sections, with templates/eval material appropriately split out.	5 / 5
	Total	18 / 20 Passed

Description

95%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.

A strong, third-person description that clearly states both capability and explicit trigger conditions with natural user phrasings. Slight room only on specificity, where the concrete actions remain somewhat conceptual.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — 'modeling how top experts...would think, disagree, and converge on a decision', 'role-play strongest minds', 'compare elite viewpoints' — but they stay at a conceptual level with minor coverage gaps (e.g., the four-lens structure is only hinted at via 'use four-lens dialogue').	4 / 5
Completeness	Explicitly answers both what ('Simulate high-stakes reasoning by modeling how top experts...would think, disagree, and converge on a decision') and when ('Use when users ask to role-play strongest minds... Trigger for prompts like...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural phrasings users would actually say — 'think like world-class experts', 'simulate top domain specialists', 'role-play strongest domain people', 'compare elite viewpoints', 'use four-lens dialogue' — with multiple synonyms (experts/specialists/strongest minds/domain people).	5 / 5
Distinctiveness Conflict Risk	Clear niche — elite-expert viewpoint simulation via a fixed four-lens dialogue — with distinctive triggers ('four-lens dialogue', 'simulate top domain specialists') that minimize overlap with generic role-play skills.	5 / 5
	Total	19 / 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/ai_life_os
Path: skills/simulate-elite-experts/SKILL.md
Commit: 61ead80

Reviewed: 1 day 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.