agentsociety-create-env-module

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.

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./extension/skills/agentsociety-create-env-module/v1.0.0/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete commands, paths, and a well-sequenced validated workflow, but it loses conciseness through triple restatement of the no-inheritance rule and references stage/subagent-prompt files that are not present in the bundle.

Suggestions

Remove the inline No-Inheritance explanation from the Runtime Contract and Common Mistakes sections, keeping a single authoritative statement that points to references/pitfalls.md P5.

Either add the referenced stages/*.md and subagent-prompts/*.md files to the bundle or drop the references, since pointing at non-existent files weakens progressive disclosure.

Collapse the duplicated metaclass explanation so each point appears once and links to its reference.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with tables and bulleted contracts, but the No-Inheritance Rule is restated three times (Runtime Contract, its own section, and Common Mistakes) and several pitfalls are summarized inline despite a referenced pitfalls.md, so it could be tightened.	2 / 3
Actionability	It provides concrete copy-paste CLI invocations with flags (ags.py create-env-module-validate with --file, --class-name, etc.), exact output paths, and explicit class-construction rules, matching the fully executable anchor.	3 / 3
Workflow Clarity	A clear sequenced digraph (intake -> clarify -> design -> generate -> validate -> archive) plus an explicit validate step and a validate -> fix -> retry feedback loop give it explicit checkpoints for a risky code-generation operation.	3 / 3
Progressive Disclosure	References are signaled one level deep and real (pitfalls.md, persistence-patterns.md, runtime-sources.md), but the stage files (stages/.md) and subagent-prompts/.md are referenced with no corresponding bundle files, and the No-Inheritance rule is duplicated inline rather than kept solely in its reference.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 clearly answers both what the skill does and when to use it via an explicit 'Use when' clause, but its action language and trigger terms are more technical than natural, limiting specificity and trigger-term quality.

Suggestions

List concrete actions the skill performs (e.g. 'designs, generates, and validates a custom EnvBase .py module') to reach the level-3 specificity anchor.

Add natural user-phrased triggers (e.g. 'social media module', 'voting environment', 'market simulation') alongside the technical terms to improve trigger-term quality.

Sharpen the niche wording to distinguish it from scan-modules (registration) and experiment-config (experiment assembly).

Dimension	Reasoning	Score
Specificity	Names the domain ('custom environment module') and actions ('creating or revising'), but the actions are general rather than a list of multiple concrete operations, so it falls short of the level-3 anchor.	2 / 3
Completeness	It states what the skill does ('creating or revising a custom environment module') and gives an explicit 'Use when' clause with three concrete trigger conditions, satisfying both what and when.	3 / 3
Trigger Term Quality	Relevant terms like 'environment module', 'environment class', and 'simulation budget' are present, but the phrasing is technical and lacks common user-spoken variations, matching the 'some relevant keywords but missing variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The 'custom environment module' niche is fairly specific, but 'environment module' overlaps with sibling skills like scan-modules and experiment-config, so it could still trigger for adjacent tasks.	2 / 3
	Total	9 / 12 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-create-env-module/v1.0.0/SKILL.md
Commit: 1832bcb

Reviewed: about 5 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.