Use when creating or revising a custom environment module, when an experiment needs an environment class that does not yet exist in the workspace, or when the module design must fit a simulation budget.
SkillScore64Maintained
Automatic
◆AI Engineer pack
Last verified 8/15/2026
What it changes
Passed 10 of 16 test cases with the skill, and 2 of 16 without it.
Without skill14%
With skill64%
Checks it passed that the model alone missed
The @tool decorator specifies the readonly parameter
The frontmatter explicitly defines both name and description keys
The command passes parameters specifying the target file or class name
and 16 more in the full report
11 fixed3 passed either way8 still failing0 broke
Pass-rate lift
+50 pp
Tokens
+90%
Agent turns
0%
Response time
-21%
Model gemini-3.6-flashMeasured 8/15/2026v114 of 22 cases passed with skill · 16 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 11
Prompt
Which helper script inside the AgentSociety framework resolves source dependencies for custom environment modules?
What was checked, without and with the skill
Checked
Without skill
With skill
The response specifies .agentsociety/bin/ags.py create-env-module-resolve-sources
Missed
Passed
case-16 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md113 lines6 filesincludes scripts
Create Environment Module
Overview
Create or repair a custom EnvBase environment module under custom/envs. Guides requirements intake through validation, producing a single .py file with properly decorated tools.
When to Use
User asks to create a new environment or simulation module (e.g. "social media module", "voting environment", "market simulation")
experiment-config needs an environment module that does not yet exist in the workspace
User wants to add or modify @tool-decorated methods on an existing custom env
The simulation scale, step budget, or runtime budget should influence the module design
Do NOT use when:
The env module already exists and only needs registration (use scan-modules instead)
The task is about agent skills, not environment modules
Use when starting or resuming an AgentSociety research workspace, deciding which research skill to invoke next, checking current pipeline state, or sizing a simulation before configuration and module creation.