agentsociety-hypothesis

Use when defining or revising research hypotheses, experiment groups, or comparison structure after literature review.

Quality

76%

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-hypothesis/v1.0.0/SKILL.md

Quality

Content

80%

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 concise and actionable with executable commands and concrete examples, but the workflow lacks explicit validation checkpoints and the provided bundle script is not surfaced from the SKILL.md. Adding a validation step and a pointer to scripts/hypothesis.py would round it out.

Suggestions

Insert an explicit validation checkpoint in the workflow, e.g. run `scan-modules info` to confirm names before writing SIM_SETTINGS.json, and re-validate after `hypothesis add` fails.

Reference the bundled scripts/hypothesis.py from the body (e.g. in Quick Reference or Module Selection) so the bundle is discoverable and progressive disclosure is one level deep rather than unlinked.

Dimension	Reasoning	Score
Conciseness	The body is lean throughout: compact command tables, a terse workflow graph, and a Common Mistakes table, with no padding or explanation of concepts Claude already knows. Every section earns its tokens.	3 / 3
Actionability	It provides fully executable, copy-paste-ready commands (e.g. "$PYTHON_PATH .agentsociety/bin/ags.py hypothesis add --description TEXT ..."), a concrete group JSON format, and a module-combinations table with exact class/module names.	3 / 3
Workflow Clarity	The dot flowchart gives a clear sequence (read TOPIC → clarify → scan → groups → write → sync), but there are no explicit validation checkpoints or a validate-fix-retry loop, even though writing SIM_SETTINGS.json with module names is error-prone; checkpoints are only implicit via the Common Mistakes table.	2 / 3
Progressive Disclosure	Sections are well organized, but the bundled scripts/hypothesis.py is never referenced or linked from the body, and the only "references" are workspace artifacts (TOPIC.md, HYPOTHESIS.md, SIM_SETTINGS.json, CLAUDE.md) rather than clearly signaled one-level-deep bundle references.	2 / 3
	Total	10 / 12 Passed

Description

72%

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 has strong trigger terms and a clear niche, but it leads with the use condition and never separately states what the skill does, leaving the capability only implied. Adding a concise capability clause before the "Use when" trigger would lift completeness and specificity.

Suggestions

Prefix the description with a capability statement, e.g. "Manages research hypotheses and experiment groups for AgentSociety simulations. Use when...", so "what" is stated explicitly rather than implied.

Broaden the action vocabulary beyond "defining or revising" to include concrete operations like listing, validating, and syncing hypotheses.

Dimension	Reasoning	Score
Specificity	The description names the domain and two actions ("defining or revising research hypotheses, experiment groups, or comparison structure"), but the action set is narrow and the capability is stated only via gerunds rather than as a discrete list of concrete actions.	2 / 3
Completeness	The "when" is explicit ("Use when..."), but the "what" is only implied through the gerund clause; there is no distinct capability statement such as "Manages research hypotheses...", so the what-and-when pair is not both clearly answered.	2 / 3
Trigger Term Quality	It surfaces natural terms a user in this domain would actually say — "research hypotheses", "experiment groups", "comparison structure", "after literature review" — giving good coverage of the relevant vocabulary.	3 / 3
Distinctiveness Conflict Risk	The "after literature review" qualifier and the hypothesis/experiment-group niche give it a clear position in a research pipeline, making conflict with adjacent skills unlikely.	3 / 3
	Total	10 / 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-hypothesis/v1.0.0/SKILL.md
Commit: 1832bcb

Reviewed: about 6 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.