anysearch

Real-time search engine supporting web search, vertical domain search, parallel batch search, and URL content extraction.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/anysearch/SKILL.md

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 is well-structured and actionable with concrete commands and validation/confirmation checkpoints, but it is somewhat verbose and the platform-detection section repeats content that the <cmd> abstraction already encapsulates.

Suggestions

Collapse the overlapping platform-detection sections (Pre-detected Runtime, Detection Procedure, CLI Invocation) since the <cmd> cheat-sheet abstraction already covers routine use.

Surface the detailed reference as a clearly signaled file path (e.g., link scripts/shared/doc_spec.md) in the overview rather than only via the `doc` command.

Tighten the Trigger section, which restates domain lists and rules that partly duplicate the cheat sheet's inline guidance.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but the platform-detection tables (Pre-detected Runtime, Detection Procedure, CLI Invocation) overlap and restate what the <cmd> abstraction already covers, going beyond minor trimmings.	3 / 5
Actionability	The command cheat sheet provides copy-paste-ready exact invocations for search, get_sub_domains, batch_search, and extract plus invalid-example guidance; minor gaps remain around the platform-conditional <cmd> placeholder.	4 / 5
Workflow Clarity	Sequences are clear (vertical rule -> get_sub_domains -> required params -> search) with explicit checkpoints for key exhaustion (user confirmation before saving) and CLI fallback; some checkpoints stay implicit rather than strict validate->retry checklists.	4 / 5
Progressive Disclosure	Bundled scripts and shared references are real and the bulky reference is deferred behind an offline `doc` command, giving good one-level-deep structure; navigation to detail is via command rather than clearly signaled file links, keeping it at 4.	4 / 5
	Total	15 / 20 Passed

Description

58%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 specific and distinct, naming four concrete capabilities, but lacks an explicit trigger/"Use when" clause and natural user phrasings, limiting completeness and trigger-term quality.

Suggestions

Add a "Use when ..." clause naming natural user intents (e.g., looking up facts, fact-checking, reading a URL's content) to lift completeness and trigger-term quality.

Include common synonyms users say ("look up", "search the web", "fact-check") alongside the technical capability terms.

Optionally mention the vertical-domain identifiers (Stock:/CVE:/DOI:) to sharpen distinctiveness against generic search skills.

Dimension	Reasoning	Score
Specificity	"web search, vertical domain search, parallel batch search, and URL content extraction" lists four concrete capability areas with only minor coverage gaps; it does not reach 5 because no deeper capability specifics are given.	4 / 5
Completeness	The description gives a clear "what" but no explicit "Use when..." trigger clause, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Natural terms like "web search" and "URL content extraction" are present, but common user phrasings and synonyms (e.g., "look up", "fact-check") are missing, placing it at 3 rather than 4.	3 / 5
Distinctiveness Conflict Risk	"Real-time search engine" with vertical, batch, and extraction modes carves a clear niche with only minor overlap risk, though absent trigger phrases keep it below 5.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: jxxghp/MoviePilot
Path: skills/anysearch/SKILL.md
Commit: f28e8b1

Reviewed: 4 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.