CtrlK
BlogDocsLog inGet started
Tessl Logo

parallel-web

Use Parallel CLI for web search, URL extraction, deep research, structured data enrichment, entity discovery, and recurring web monitoring. Best for requests that explicitly need current web evidence, academic-source discovery, repeated entity lookups, exhaustive reports, or ongoing change tracking.

69

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

Well-structured, executable skill body with a clean routing table pointing to real one-level reference files and concrete command examples. Slightly padded by the academic-source-priority section and minor validation gaps for destructive monitor operations.

DimensionReasoningScore

Conciseness

Mostly lean routing table and command blocks that assume Claude's competence; the 'Academic source priority' section repeats generic guidance Claude already knows and could be trimmed.

4 / 5

Actionability

Provides copy-paste-ready commands for install, login, status, and polling with concrete flags and version pins, plus a routing table mapping intents to capability files.

5 / 5

Workflow Clarity

Setup, status, and polling steps are sequenced with a hard three-poll limit and explicit stop-and-report checkpoint; the routing decision flow is clear, though destructive monitor state changes lack an explicit validate-before-act loop.

4 / 5

Progressive Disclosure

Clear overview routing table signals one-level-deep references to six real capability files (all present in references/), with setup/status/polling kept inline; navigation is explicit and shallow.

5 / 5

Total

18

/

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.

A strong, specific description that names six concrete capabilities and ties each to explicit trigger conditions, with third-person voice throughout. Trigger-term coverage is good but could add a few more everyday synonyms.

DimensionReasoningScore

Specificity

Lists six concrete capabilities (web search, URL extraction, deep research, structured data enrichment, entity discovery, recurring web monitoring) covering the toolkit comprehensively.

5 / 5

Completeness

Explicitly answers 'what' (the six capabilities) and 'when' via the 'Best for requests that explicitly need...' clause naming concrete trigger conditions.

5 / 5

Trigger Term Quality

Includes strong natural terms like 'current web evidence', 'academic-source discovery', 'repeated entity lookups', and 'ongoing change tracking', but misses common synonyms like 'fact-check', 'scrape', or specific phrasings users might say.

4 / 5

Distinctiveness Conflict Risk

The Parallel CLI niche and web-intelligence framing are distinct, but the broad 'web search' capability overlaps with general web-search skills; minor overlap risk.

4 / 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.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

relative_links

Relative link issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
K-Dense-AI/scientific-agent-skills
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.