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.

Quality

85%

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

78%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 is well-structured as an overview that routes to real reference files, with concrete executable commands and an explicit bounded polling checkpoint. Tightening the repeated academic-source guidance and surfacing a few more per-capability flag details inline would lift conciseness and actionability toward 5.

Suggestions

Consolidate the academic-source priority so it appears once; the 'Academic source priority' subsection partly restates the lead sentence's guidance, adding redundant tokens.

Add one inline example per capability for its most common flags (e.g., a sample `parallel-cli search` and `parallel-cli enrich` invocation) so the common cases are copy-paste ready without opening a reference.

Spell out the failure/recovery loop for research and enrichment tasks (e.g., on a failed status, what to inspect or retry) to match the explicit checkpoint quality of the polling section.

Dimension	Reasoning	Score
Conciseness	Dense instructional body with little concept padding, but the academic-source priority is restated across two sections and the citation block is lengthy, leaving minor tokens that could be trimmed short of the lean 5 anchor.	4 / 5
Actionability	Provides concrete executable commands (install, status, poll with --timeout 540) and a routing table to specific references, but some per-capability flag specifics live in the reference files rather than inline, leaving minor gaps versus fully copy-paste-ready 5.	4 / 5
Workflow Clarity	Routing table gives a clear action sequence and the polling section has an explicit bounded checkpoint (poll at most three times, then stop and report), satisfying the batch-cap; recovery loops for failed research/enrichment runs are not fully spelled out, capping it below 5.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview with a routing table pointing to six one-level-deep, verified reference files, each clearly signaled by capability, with setup/status kept inline — matching the well-signaled-easy-navigation 5 anchor.	5 / 5
	Total	17 / 20 Passed

Description

92%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 and specific, naming six concrete capabilities alongside explicit 'best for' trigger guidance that clearly answers both what and when. Minor room to add common synonyms (e.g., 'scrape', 'fetch URL') to push trigger coverage from 4 to 5.

Dimension	Reasoning	Score
Specificity	Names six concrete capabilities ('web search, URL extraction, deep research, structured data enrichment, entity discovery, and recurring web monitoring'), matching the comprehensive-coverage anchor rather than the minor-gaps anchor at 4.	5 / 5
Completeness	'Use Parallel CLI for…' states what it does and 'Best for requests that explicitly need…' states when to use it with concrete triggers, explicitly answering both; not the 4 anchor since neither half is merely implied.	5 / 5
Trigger Term Quality	Includes natural trigger phrases ('current web evidence', 'academic-source discovery', 'repeated entity lookups', 'exhaustive reports', 'ongoing change tracking') but omits common synonyms like 'scrape' or 'fetch a URL', so it falls just below the exhaustive-synonym 5 anchor.	4 / 5
Distinctiveness Conflict Risk	Scoped to Parallel CLI with six distinct web-intelligence capabilities and specific triggers, giving it a clear niche with minimal overlap risk against generic skills.	5 / 5
	Total	19 / 20 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
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
Path: skills/parallel-web/SKILL.md
Commit: 1e5eeff

Reviewed: 3 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.