agentsociety-literature-search

Use when academic literature needs to be gathered or refreshed for a research topic, especially at the beginning of a project.

Quality

74%

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-literature-search/v1.0.0/SKILL.md

Quality

Content

86%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.

The content is highly actionable and well-structured, with executable command tables and appropriately offloaded reference material. Its only weak spot is workflow_clarity, where the batch search workflow has a verification step but no explicit validate-and-retry loop, and minor conciseness gains are available in the inline index contract.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient — command tables, parameter tables, and a tight workflow with minimal concept explanation — but the inline Index Contract JSON schema and some repeated full-text guidance add minor bulk that could be trimmed or pushed to a reference.	4 / 5
Actionability	The Quick Reference table provides copy-paste-ready, fully executable commands covering the common cases (basic search, year range, multi-query, full-text download/register/mark), and parameters are fully specified, matching the 'fully executable, copy-paste ready, common cases covered' anchor.	5 / 5
Workflow Clarity	An explicit 8-step Recommended Workflow with a verification checkpoint ('Inspect papers/literature_index.json and full_texts/ after the command completes') covers this batch operation, but it lacks a true validate→fix→retry feedback loop, so it sits below the anchor-5 checklist.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled, one-level-deep references to references/data-sources.md and references/full-text-retrieval.md (both real files), with detail (full-text retrieval, enriching notes) appropriately split out and easy to navigate.	5 / 5
	Total	18 / 20 Passed

Description

62%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.

The description has a clear 'Use when...' trigger and a recognizable niche, but its action verbs are generic and it underuses the natural trigger terms (papers, survey, related work) that the body actually lists. It is solid but leaves specificity and trigger coverage on the table.

Suggestions

Add concrete actions to the description, e.g. 'Search, gather, and catalog academic literature across arXiv, CrossRef, and OpenAlex into the papers/ directory.'

Fold in natural user trigger terms already present in the body: 'papers', 'related work', 'survey', or 'background research'.

Tighten the 'when' clause with the concrete signals (e.g. 'when TOPIC.md does not yet exist or needs enrichment').

Dimension	Reasoning	Score
Specificity	Names the domain ('academic literature') and two actions ('gathered or refreshed'), but the verbs are generic and no concrete mechanisms are named, matching the 'domain + 1-2 concrete actions, not comprehensive' anchor.	3 / 5
Completeness	It has an explicit 'Use when...' clause and a stated what ('academic literature needs to be gathered or refreshed for a research topic'), but the 'what' is moderately vague and the 'when' ('especially at the beginning of a project') could be more specific, landing between anchors 4 and 5.	4 / 5
Trigger Term Quality	Includes natural terms 'academic literature' and 'research topic', but omits common synonyms users would actually say ('papers', 'related work', 'survey', 'background research') that appear only in the body, fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'Academic literature' is a clear niche with distinct triggers and low overlap risk with sibling skills (hypothesis, experiment-config), though the description alone does not fully differentiate it from a general research skill.	4 / 5
	Total	14 / 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-literature-search/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.