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

87%

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

Quality

Content

100%

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

The body is a well-organized, actionable CLI reference with executable commands, a sequenced workflow that includes verification and error recovery, and clean one-level-deep references to real bundle files. It is token-efficient without sacrificing clarity.

Dimension	Reasoning	Score
Conciseness	The body is a dense, table-driven CLI reference with no concept padding Claude already knows; every section (Quick Reference, Parameters, Index Contract, Common Mistakes) earns its place. Not 2 because there is no fluff or unnecessary explanation, only minor redundancy between the Quick Reference and full-text helper tables.	3 / 3
Actionability	Commands like `$PYTHON_PATH .agentsociety/bin/ags.py literature-search "query" --year-from 2020 --year-to 2024` are fully executable, with exact env var names and flag tables — copy-paste ready. Not 2 because guidance is concrete and complete rather than pseudocode.	3 / 3
Workflow Clarity	The 8-step Recommended Workflow is clearly sequenced with a precondition check (confirm `.env`), a verification step (inspect `papers/literature_index.json` after completion), and an error-recovery fallback (failed PDFs → Optional Full-Text Retrieval plus the Common Mistakes table). Not 2 because validation/verification checkpoints are present for this batch download operation.	3 / 3
Progressive Disclosure	The overview points to one-level-deep references (`references/data-sources.md`, `references/full-text-retrieval.md`), both of which exist in the bundle and are clearly signaled inline and in a References section. Not 2 because content is appropriately split with easy navigation rather than dumped inline.	3 / 3
	Total	12 / 12 Passed

Description

75%

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 an explicit trigger and a clear, distinctive niche, but its action vocabulary is abstract and its trigger-term coverage omits common user phrasings. Strengthening specificity and trigger terms would round it out.

Suggestions

Add concrete actions to the description, e.g. "Search arXiv, CrossRef, and OpenAlex for academic papers and save results to the papers/ directory."

Broaden trigger terms to include natural user phrasings such as "papers", "related work", "survey", or "background research".

Dimension	Reasoning	Score
Specificity	The phrase "academic literature needs to be gathered or refreshed" names the domain and two actions, but stops short of concrete operations like searching arXiv/CrossRef or saving to papers/. Not 3 because it does not list multiple specific concrete actions; not 1 because it is not vague like "Helps with documents".	2 / 3
Completeness	The explicit "Use when academic literature needs to be gathered or refreshed for a research topic, especially at the beginning of a project" answers both what (gather/refresh literature) and when (beginning of a project). Not 2 because the trigger is explicit rather than merely implied.	3 / 3
Trigger Term Quality	"academic literature" and "research topic" are natural terms a user might say, but common variations such as "papers", "related work", "survey", or "background research" are missing. Not 3 because coverage of natural terms is incomplete; not 1 because relevant natural keywords are present.	2 / 3
Distinctiveness Conflict Risk	Academic literature search is a clear niche with distinct triggers ("academic literature", "research topic", "beginning of a project") and is unlikely to fire for unrelated skills. Not 2 because it does not overlap meaningfully with generic skills.	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-literature-search/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.