CtrlK
BlogDocsLog inGet started
Tessl Logo

research-lit

Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers.

58

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/skills-codex/research-lit/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

52%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 skill is highly actionable with a clear multi-step workflow and good validation checkpoints, but it badly violates token economy: five near-identical resolver blocks and explanatory prose pad the body, and the referenced shared-reference files do not exist in the bundle. Progression disclosure is undermined both by the missing referenced files and by content that should have been split out.

Suggestions

Extract the repeated $ARXIV_REPO/fetcher resolver bash block into a single shared reference (e.g. shared-references/fetcher-resolution.md) and link to it instead of inlining it five times.

Add the referenced files (fan-out-pattern.md, integration-contract.md, output-composition.md) to the bundle under shared-references/ so the links resolve, or remove the dead links.

Cut the 'Why use Semantic Scholar?' / 'Why use Gemini?' / 'Why use OpenAlex?' explanatory paragraphs — Claude already knows what these sources are; keep only the invocation contract and dedup rules.

DimensionReasoningScore

Conciseness

The 27KB body is noticeably verbose: the same $ARXIV_REPO/fetcher resolver bash block is repeated nearly verbatim across five sources, and 'Why use X?' prose explains retrieval concepts Claude already knows.

2 / 5

Actionability

Provides concrete, executable bash resolver chains, specific MCP tool invocations, and CLI commands with real flags; placeholders like QUERY/ARXIV_ID are justified substitution points rather than pseudocode.

4 / 5

Workflow Clarity

Clear numbered sequence (Step 0a-0c, 1-6) with explicit graceful-degradation checkpoints (WARN emissions, 'stop and ask user' for requested-but-unavailable sources); the fan-out/dedup sub-flow has implicit rather than enumerated checkpoints.

4 / 5

Progressive Disclosure

References three one-level-deep files (fan-out-pattern.md, integration-contract.md, output-composition.md) but none exist in the bundle — references/, scripts/, assets/, and ../shared-references/ are all absent — and the inlined 27KB of repeated resolver boilerplate belongs in those missing files.

2 / 5

Total

12

/

20

Passed

Description

83%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 is strong: it states concrete actions, provides explicit natural-language triggers for both what and when, and is clearly distinguishable from adjacent skills. The main weakness is specificity, where it lists several actions but not the full breadth of what the skill does (citation export, source ranking, output composition).

Suggestions

Add a phrase covering output deliverables (e.g., 'export BibTeX citations, produce a structured literature table') to lift specificity toward comprehensive coverage.

Consider naming a concrete output artifact or two so the 'what' spans the full skill lifecycle from search to deliverable.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Search and analyze research papers, find related work, summarize key ideas' — but stops short of comprehensive coverage (no mention of citation export, ranking, or output formats).

4 / 5

Completeness

Explicitly answers both what ('Search and analyze research papers, find related work, summarize key ideas') and when ('Use when user says ...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Quotes natural user phrases ('find papers', 'related work', 'literature review', 'what does this paper say') with good synonym coverage; no file extensions, but the skill has no file-type trigger so this is appropriate.

4 / 5

Distinctiveness Conflict Risk

Carves a clear research-literature-review niche with distinctive natural-language triggers; minor overlap risk with a generic paper-handling skill but mostly distinct.

4 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 4 suspicious

Warning

Total

15

/

16

Passed

Repository
wanshuiyin/Auto-claude-code-research-in-sleep
Reviewed

Table of Contents

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.