literature-review

Use when writing literature review sections - guides searching, organizing, and synthesizing academic sources

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%Weight 40%Scale 1-3

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

The skill delivers strong actionable commands and a well-gated, validation-rich workflow for literature reviews, but it is undercut by heavy redundancy (the same script usage repeated in three sections) and progressive-disclosure problems where referenced bundle files (scripts/, references/) do not actually exist.

Suggestions

Deduplicate the scholar_search.py usage, BibTeX/APA output examples, and database tables into a single canonical section, removing the repeated coverage across MCP-INTEGRATION, §1.0, and 场景0.

Create the referenced scripts/scholar_search.py and scripts/pdf_parser.py (or a references/ file documenting them) so that the in-body paths resolve to real bundle files, or remove the references if the scripts are not bundled.

Move the detailed script usage and output-format reference tables into a separate references/ file, keeping SKILL.md as a concise overview that links one level deep to the details.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient domain-specific guidance but is tightened poorly - scholar_search.py usage, BibTeX/APA output examples, and database tables are repeated across three separate sections (MCP-INTEGRATION, §1.0, 场景0); not 1 because it avoids explaining concepts Claude already knows, not 3 because of substantial redundant padding.	2 / 3
Actionability	It provides concrete, copy-paste-ready commands such as 'python scripts/scholar_search.py "..." --format bibtex -o refs.bib', curl-based DOI verification, and pdf_parser invocations with specific flags; fully executable guidance matching the top anchor.	3 / 3
Workflow Clarity	A clearly sequenced multi-step process with a checklist, a hard-gate requiring an evidence-claim map before drafting, explicit citation-verification feedback loops (verify DOI -> fix -> re-validate), and a final citation checklist; matches the anchor for explicit validation steps and feedback loops.	3 / 3
Progressive Disclosure	The body heavily references scripts/scholar_search.py, scripts/pdf_parser.py, and a 'verification' skill, but the scripts/, references/, and assets/ directories do not exist - referenced paths are not real files - and detailed script usage that should be split out is inlined redundantly; not 1 because sections are organized with headings, not 3 because no appropriate file splitting and referenced bundles are missing.	2 / 3
	Total	10 / 12 Passed

Description

85%Weight 40%Scale 1-3

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, well-formed description that states three concrete actions and pairs them with an explicit 'Use when' trigger, giving it strong completeness and distinctiveness. The only weakness is narrow trigger-term coverage, relying on a single natural phrase.

Suggestions

Broaden trigger terms to include common variations users might say, e.g. 'Use when writing literature review sections, related work, or research reviews, or when organizing and synthesizing academic sources'.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions - 'searching, organizing, and synthesizing academic sources' - matching the anchor for listing several specific actions; it is not at 2 because it goes beyond naming only a domain and partial actions.	3 / 3
Completeness	It explicitly answers both 'what' ('guides searching, organizing, and synthesizing academic sources') and 'when' ('Use when writing literature review sections') with an explicit Use-when clause; not 2 because the trigger is explicit rather than merely implied.	3 / 3
Trigger Term Quality	'literature review sections' is a natural user keyword but coverage is limited to that single phrase, missing common variations such as 'related work' or 'research review'; not 3 because variations are missing, not 1 because the term is genuinely natural.	2 / 3
Distinctiveness Conflict Risk	'literature review sections' carves a clear niche with a distinct trigger unlikely to conflict with unrelated skills; not 2 because the domain is sufficiently specific rather than broadly overlapping.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
referenced_paths_exist	Referenced path issues: 22 missing	Warning

	Total	14 / 16 Passed

Repository: Norman-bury/research-writing-skill
Path: skills/literature-review/SKILL.md
Commit: 6f79595

Reviewed: 10 days 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.