anysearch

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

Quality

73%

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

81%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 content is well-structured, actionable, and includes strong sequenced workflows with explicit validation and error-recovery loops. It is concise with only minor redundancy, and it leverages real bundle files for progressive disclosure effectively.

Suggestions

De-duplicate the platform detection procedure, which currently appears as both narrative steps and tables; consolidate to trim conciseness from 4 toward 5.

Surface more complete option coverage for batch_search and get_sub_domains inline (or via a clearly linked reference) to close the minor actionability gaps.

Convert the 'doc' recovery reference into an explicit file/command link and consider moving the API-key persistence detail into a referenced file to lift progressive disclosure toward 5.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient with an executable cheat sheet and compact tables, but re-states the runtime detection procedure in both prose and tables and repeats the 'doc' guidance, matching 'efficient; minor instances of over-explanation that could be trimmed' rather than the fully lean 5 anchor.	4 / 5
Actionability	Provides concrete, copy-paste-ready command shapes with real arguments (e.g., 'search "AAPL" --domain finance --sub_domain finance.us_stock --sub_domain_params \'{"ticker":"AAPL"}\'') plus explicit invalid-example callouts, matching 'mostly executable; minor gaps'; not a 5 because some option sets are not exhaustively demonstrated.	4 / 5
Workflow Clarity	Multi-step processes are clearly sequenced with explicit validation and feedback loops — runtime detection falls through on failure, and the key-exhaustion flow (extract new key → ask user confirmation → save to .env → retry) provides error-recovery checkpoints, matching the top anchor.	5 / 5
Progressive Disclosure	The body is an overview that points to real bundled CLI scripts (anysearch_cli.py/.js/.ps1/.sh and shared/) with one-level-deep, clearly signaled references and organized sections; not a 5 because the 'doc' reference is a command rather than a navigable file link and some inline reference material could be pushed into separate files.	4 / 5
	Total	17 / 20 Passed

Description

66%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 clearly states what AnySearch does with four concrete capabilities, but omits any 'Use when...' trigger guidance, which caps its completeness. It is specific and reasonably distinct, yet could be elevated by adding explicit activation triggers and more natural synonyms.

Suggestions

Add a 'Use when...' clause naming concrete user intents (e.g., 'Use when looking up facts, news, or current data; verifying claims; extracting page content; or running structured vertical-domain queries').

Include more natural trigger synonyms and file-extension/identifier-style terms users actually say (e.g., 'look up', 'find', 'fact-check', Stock:/CVE:/DOI: identifiers) to lift trigger-term quality from 4 to 5.

Tighten the capabilities list into a single comprehensive enumeration (sub-features of each search type) to move specificity from 4 toward 5.

Dimension	Reasoning	Score
Specificity	Names the search domain and four concrete capabilities ('web search, vertical domain search, parallel batch search, and URL content extraction'), which matches the 'several specific actions; minor gaps' anchor; not a 5 because each action is terse without comprehensive coverage of sub-features.	4 / 5
Completeness	The description gives a clear 'what' but contains no 'Use when...' clause or equivalent explicit trigger guidance; per the rubric, a missing 'when' clause caps completeness at 3 even though the 'what' is well stated.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ('web search', 'search engine', 'URL content extraction', 'parallel batch search'), but misses common synonyms and phrasings like 'look up', 'find', 'facts', or 'news', so it sits at good-but-not-comprehensive coverage rather than 5.	4 / 5
Distinctiveness Conflict Risk	The niche (a real-time search service with vertical-domain and extraction features) is clearly distinct from most skills with only minor overlap risk against other web/search utilities; not a 5 because the high-level phrasing could still overlap with generic browsing/search tools.	4 / 5
	Total	15 / 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: 4f716c4

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.