agentsociety-hypothesis

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

Quality

80%

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

90%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 tight, highly actionable skill body that uses tables and a workflow graph instead of prose. The main gap is an explicit validation/retry loop around the destructive add/delete operations.

Suggestions

Add an explicit "validate after add" checkpoint (e.g. run `hypothesis get` or `--json` verification) with a fix-and-retry note to reach workflow clarity 5.

Optionally move the full command-flag reference into a REFERENCES file and keep only the headline commands inline.

Surface the scan-modules validation step as a required (not optional) checkpoint when module names are uncertain.

Dimension	Reasoning	Score
Conciseness	The body is lean: command tables, a compact dot workflow, and a JSON example with no padding or explanation of concepts Claude already knows; every section earns its place.	5 / 5
Actionability	Exact CLI invocations with all flags, a copy-paste group JSON format, and a common-module-combinations table give fully executable, copy-paste-ready guidance for the common cases.	5 / 5
Workflow Clarity	A clear dot-graph sequence plus a Common Mistakes table provides most checkpoints, but the destructive add/delete path lacks an explicit validate-and-retry feedback loop.	4 / 5
Progressive Disclosure	Well-organized single-file sections with no nested references; the command/module reference is reasonably inline and could optionally be split, leaving minor organization gaps.	4 / 5
	Total	18 / 20 Passed

Description

70%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, third-person trigger description with a clear use-when clause and a recognizable niche. It is slightly light on enumerated concrete actions and synonyms, keeping it just short of the top anchors.

Suggestions

Add one or two more concrete verbs (e.g. "document", "validate") to lift specificity toward 5.

Include a common synonym or file term (e.g. "HYPOTHESIS.md") to broaden natural trigger coverage.

Lead with a short what-clause before the "Use when" clause so both halves are equally explicit.

Dimension	Reasoning	Score
Specificity	"defining or revising research hypotheses, experiment groups, or comparison structure" names the domain and a couple concrete actions but stops short of a comprehensive action list.	3 / 5
Completeness	The "Use when..." clause gives an explicit when, and the what (defining/revising hypotheses, groups, comparison structure) is embedded but concrete; the what could be slightly more explicit.	4 / 5
Trigger Term Quality	"research hypotheses, experiment groups, comparison structure" are natural phrases users would say, with good though not exhaustive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	The "after literature review" niche and research-hypothesis framing make it mostly distinct from sibling pipeline skills with only minor overlap risk.	4 / 5
	Total	15 / 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-hypothesis/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.