anysearch

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

Quality

66%

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 ./SKILL.md

Quality

Content

65%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 concrete commands and clear sectioning, but it is verbose (repeated tables, inline reference-grade material) and lacks validation checkpoints for its batch operations.

Suggestions

Move the API-key management and full platform-detection procedure into a reference file (e.g. references/setup.md) and link to it, keeping SKILL.md to the fast-path cheat sheet and a one-line fallback pointer.

Deduplicate the command tables — keep one invocation reference instead of repeating the per-runtime doc and invocation tables.

Add an explicit validation checkpoint for batch_search results (e.g. verify each item's status/error field before reporting success) to satisfy the feedback-loop requirement for batch operations.

Dimension	Reasoning	Score
Conciseness	Mostly operational and free of generic concept explanations, but ~186 lines repeat the command tables (cheat sheet plus platform-detection invocation table) and spell out the full detection procedure inline that runtime.conf is meant to bypass.	2 / 3
Actionability	Provides exact, copy-paste command shapes with realistic examples (AAPL/MSFT, JSON batch queries) and explicitly flags invalid forms ('do not use extract --format markdown'), matching fully executable guidance.	3 / 3
Workflow Clarity	Detection and key-persistence flows are sequenced with fallbacks, but batch_search is a batch operation with no agent-side validation/verification checkpoint — the rubric caps workflow_clarity at 2 when batch ops lack validation.	2 / 3
Progressive Disclosure	References real bundle scripts (anysearch_cli.{py,js,ps1,sh} exist) and uses clear headers, but API-key management and the full platform-detection procedure are inline rather than split out, and doc_spec.md is only reachable via the doc command rather than a signaled link.	2 / 3
	Total	9 / 12 Passed

Description

67%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 distinctive about capabilities but omits any explicit trigger/usage guidance, leaving the 'when to use this skill' question unanswered.

Suggestions

Append a 'Use when...' clause naming natural triggers, e.g. 'Use when looking up current facts, fact-checking claims, extracting URL content, or running structured/vertical-domain searches.'

Replace jargon like 'vertical domain search' and 'parallel batch search' with user-facing phrasing ('structured searches by domain', 'searching multiple queries at once') so the description surfaces terms users actually say.

Add common query verbs ('look up', 'find', 'browse') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists four concrete capabilities ('web search, vertical domain search, parallel batch search, and URL content extraction'), matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	Clearly answers 'what' but provides no 'Use when...' trigger clause or equivalent 'when' guidance, which the rubric caps at 2 for missing triggers.	2 / 3
Trigger Term Quality	Contains some natural terms ('search', 'web search', 'URL content extraction') but 'vertical domain search' and 'parallel batch search' are jargon, and common variations users would say ('look up', 'find', 'fact-check', 'browse') are absent.	2 / 3
Distinctiveness Conflict Risk	The combination of real-time vertical-domain, parallel batch, and URL-extraction capabilities defines a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 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: anysearch-ai/anysearch-skill
Path: SKILL.md
Commit: caed9ea

Reviewed: 7 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.