agentsociety-run-experiment

Use when experiment configuration already exists and a simulation run needs to be started, monitored, or stopped.

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

92%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 skill body with executable commands, a clear validated workflow graph, and proper offloading of advanced detail to a one-level reference. Only minor conciseness gains remain from light duplication between the Quick Reference and Start sections.

Dimension	Reasoning	Score
Conciseness	The body is largely lean tables and executable commands with no concept-explaining fluff, but the Quick Reference and Start sections repeat some command material and a few lines could be trimmed, fitting 'efficient; minor instances that could be trimmed' rather than the perfectly lean 5.	4 / 5
Actionability	Provides copy-paste-ready commands for every action (start, status, stop, list, resume, direct CLI, batch sizing) with concrete flags and examples covering the common cases, matching the 'fully executable; copy-paste ready' anchor.	5 / 5
Workflow Clarity	A DOT graph lays out check -> start -> status with completed/stop/failed/fix branches, plus explicit validation (env validation, status checks, resume drift warning, kill -TERM guidance) and a fix -> check feedback loop, matching the top anchor for clear sequence with validation and error-recovery feedback.	5 / 5
Progressive Disclosure	The overview points to a real one-level-deep reference (references/programmatic-api.md, confirmed present) with bulk programmatic detail offloaded there, and sections are well-organized for navigation, matching the 'clear overview with well-signaled one-level-deep references' anchor.	5 / 5
	Total	19 / 20 Passed

Description

87%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 concise, well-scoped description that clearly answers both what it does and when to use it, with concrete action verbs and a distinct triggering precondition. Minor room to add natural synonyms (status, logs, run experiment) and broaden action coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (simulation runs) and three concrete actions ('started, monitored, or stopped'), but coverage of the broader experiment-lifecycle domain is slightly narrow, fitting the 'several specific actions; minor gaps' anchor rather than the comprehensive 5.	4 / 5
Completeness	It explicitly states what the skill does (start, monitor, stop runs) and when to use it ('Use when experiment configuration already exists and a simulation run needs to be started...'), satisfying the anchor for clearly answering both what and when with concrete triggers.	5 / 5
Trigger Term Quality	Includes natural terms like 'simulation run' and 'started, monitored, or stopped' a user might say, but is missing common variations such as 'experiment status', 'logs', or 'run experiment', matching the 'good coverage; a few natural terms missing' anchor.	4 / 5
Distinctiveness Conflict Risk	The 'configuration already exists' precondition plus the run-lifecycle scope carve a clear niche distinct from config and analysis skills, with minimal conflict risk.	5 / 5
	Total	18 / 20 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: tsinghua-fib-lab/AgentSociety
Path: extension/skills/agentsociety-run-experiment/v1.0.0/SKILL.md
Commit: 13e28b5

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.