anysearch

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

Quality

72%

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

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable command examples, clear sequenced workflows, and a genuine progressive-disclosure structure that pushes the full reference into the doc command and shared bundle. Its main weakness is length and redundancy — the per-runtime invocation tables and entry-point guidance are repeated.

Suggestions

Collapse the duplicate per-runtime invocation tables (the "doc" command table and the "CLI Invocation" table) into a single table; the second copy is pure token waste.

Consolidate the repeated "do not run doc on every activation" guidance so it appears once instead of being restated across the Overview, Recommended Entry Point, and cheat-sheet sections.

Trim the platform-detection procedure (e.g. the macOS python/python3 aside and verbatim version-probe blocks) to the essential priority order and probe commands.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and actionable, but the per-runtime invocation patterns are duplicated across the "doc" command table and the "CLI Invocation" table, and the recommended-entry-point guidance is restated — tightening opportunities that fit the 2 anchor rather than the every-token-earns-its-place level at 3.	2 / 3
Actionability	The Command Cheat Sheet gives fully executable, copy-paste-ready commands with concrete examples (e.g. `search "AAPL" --domain finance --sub_domain finance.us_stock --sub_domain_params '{"ticker":"AAPL"}'`) and platform-detection probes are real commands, matching the fully-executable anchor at 3.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced with checkpoints — the vertical workflow mandates "call get_sub_domains first" then include all required params (with the empty-string fallback guard), and the key-exhaustion recovery is an explicit 4-step feedback loop with retry, matching the clear-sequence-with-validation anchor at 3.	3 / 3
Progressive Disclosure	The body is an overview that defers the full CLI/parameter reference one level deep to the `doc` command backed by the real scripts/shared/doc_spec.md and constants.json bundle, with the deferral clearly signaled ("run doc only when the CLI interface is unknown..."), matching the well-signaled one-level-deep reference anchor at 3.	3 / 3
	Total	11 / 12 Passed

Description

60%Weight 40%Scale 1-3

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 concrete about capabilities but lacks any explicit "Use when" trigger guidance and leans on product jargon ("vertical domain search", "parallel batch search") over natural user phrasing. It is a solid what-only description capped by the missing when clause.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user needs to look up current facts, fact-check a claim, search a specific domain like finance or travel, or extract the full content of a URL."

Replace or augment jargon terms with natural phrasing users actually say — e.g. "search by domain/topic" for vertical search and "search several queries at once" for parallel batch search.

Include common keyword variations ("web search, search the web, look something up, read a webpage, extract page content") to improve trigger-term coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — "web search, vertical domain search, parallel batch search, and URL content extraction" — matching the anchor for listing several specific actions rather than the partial single-action anchor at 2.	3 / 3
Completeness	It clearly states what the skill does but has no "Use when..." clause or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 2 rather than reaching the explicit-both-what-and-when level at 3.	2 / 3
Trigger Term Quality	"web search" and "URL content extraction" are natural user terms, but "vertical domain search" and "parallel batch search" are product jargon users would not naturally say, and common variations are missing — closer to the 2 anchor than the broad natural-term coverage at 3.	2 / 3
Distinctiveness Conflict Risk	"Real-time search engine" carves a niche, but "web search" and "URL content extraction" overlap generic web-search/browse skills and the absence of explicit triggers keeps it at the 2 anchor (somewhat specific but could overlap) rather than the clearly-distinct level at 3.	2 / 3
	Total	9 / 12 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: 1b065cc

Reviewed: 9 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.