CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

aris-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.

Quality

80%

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/aris-research-lit/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 body delivers a well-sequenced, highly actionable multi-source research workflow with graceful degradation at every step and a properly separated domain reference file. Its main weaknesses are redundant documentation of the sources directive and missing error-recovery feedback loops in the workflow.

Suggestions

Merge the Overrides block and the Source Selection examples into a single `— sources:` section to eliminate the duplicated directive documentation and save tokens.

Add a short failure path for the download and research-wiki steps (e.g., what to do when a PDF fails the >10 KB check or add_edge errors), giving the workflow explicit error-recovery feedback loops.

Move the 25-line ARIS_INFRA discovery script and the arXiv/S2 de-duplication rules into a reference file, keeping SKILL.md as a leaner overview with one-level-deep pointers.

DimensionReasoningScore

Conciseness

The `— sources:` directive is documented twice (the Overrides block and again with 8 examples under Source Selection), and the 25-line ARIS_INFRA discovery script carries heavy commentary — content that could be tightened. It avoids anchor 2 because there is no explanation of concepts Claude already knows; the core content is dense and mission-driven.

3 / 5

Actionability

Provides concrete Glob patterns, executable bash with specific flags (`--max 10`, `--fields-of-study "Computer Science,Engineering"`, `--publication-types`), exact research_wiki.py commands, and an output table schema. Minor gap: the `SCRIPT=""` fallback would make `python3 "" search ...` error out before the documented WebSearch fallback; MCP tool-name flexibility is explicitly justified.

4 / 5

Workflow Clarity

Steps 0a–6 are clearly sequenced with explicit skip conditions at every stage ("Skip this step entirely if... MCP is not configured") and some verification for the batch download ("> 10 KB", 1-second rate limiting, skip papers already in the local library). Not anchor 5 because there are no error-recovery feedback loops (e.g., what to do when add_edge or a download fails).

4 / 5

Progressive Disclosure

Clear section structure with a well-signaled, one-level-deep reference (references/communications-lit-review.md, verified to exist in the bundle). Minor gaps: the detailed arXiv/S2 de-duplication rules and the long infra-locating script are inlined in SKILL.md rather than split out, keeping it short of anchor 5.

4 / 5

Total

15

/

20

Passed

Description

87%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 well-constructed: it states concrete capabilities in third person and pairs them with an explicit 'Use when' clause containing natural trigger phrases a user would actually say. Its only weakness is modest synonym coverage (e.g., no "survey", "prior work", or "citations").

DimensionReasoningScore

Specificity

"Search and analyze research papers", "find related work", "summarize key ideas" list several specific concrete actions. It falls short of anchor 5 because coverage is not comprehensive — capabilities like multi-source search (Zotero/local/web) or BibTeX export are unmentioned — but exceeds anchor 3 since more than 1-2 actions are named.

4 / 5

Completeness

Explicitly answers both: what ("Search and analyze research papers, find related work, summarize key ideas") and when ("Use when user says 'find papers', 'related work', 'literature review', 'what does this paper say', or needs to understand academic papers") with concrete trigger phrases, matching the anchor 5 example structure.

5 / 5

Trigger Term Quality

Natural user phrases "find papers", "related work", "literature review", and "what does this paper say" provide good keyword coverage. Not anchor 5 because common synonyms such as "survey papers", "prior work", "cite", or "citations" are missing.

4 / 5

Distinctiveness Conflict Risk

"research papers", "academic papers", "literature review", and "related work" carve out a clear academic-literature-research niche with distinct triggers and minimal conflict risk against generic search, summarization, or document skills.

5 / 5

Total

18

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

OpenLAIR/dr-claw

Path

skills/aris-research-lit/SKILL.md

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.