native-web-search

Trigger native web search. Use when you need quick internet research with concise summaries and full source URLs.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/native-web-search/SKILL.md

Quality

Content

88%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 lean, executable, and clear for a single-command skill, scoring well on conciseness, actionability, and workflow clarity. Its main weakness is progressive disclosure: it advertises a `search.mjs` script that is not present in the bundle.

Suggestions

Ship the referenced `search.mjs` under a `scripts/` directory (or remove the script reference) so the bundle matches the documented invocation.

If the script grows, move detailed flag/env documentation into a short reference file and link to it one level deep to keep SKILL.md as an overview.

Add a one-line validation note (e.g. expected exit behavior or how to confirm URLs appeared) so users can verify a successful run.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient: a short overview, the script name, a copy-paste command, two examples, a flag list, and brief output/notes. It assumes Claude's competence and avoids explaining what web search or Node are.	5 / 5
Actionability	It gives a fully executable invocation `node search.mjs "..." --purpose "..."`, two concrete examples, and a complete optional-flags list (provider, model, timeout, json) — copy-paste ready and covering common cases.	5 / 5
Workflow Clarity	This is a single-command skill where the action is unambiguous: run the script with a query and purpose. Per the simple-skill exception, an unambiguous single action can score 5, and the "Output expectations" and "Notes" sections clearly frame results and failure handling.	5 / 5
Progressive Disclosure	The body references `search.mjs` but no `scripts/` directory or `search.mjs` file exists in the bundle, so the one referenced path is broken; structure is otherwise minimal sections with no deeper reference material to navigate to.	2 / 5
	Total	17 / 20 Passed

Description

62%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 cleanly states both what it does and when to use it with a third-person voice and no fluff. It is solid but could list more concrete capabilities and natural synonyms to sharpen specificity and trigger coverage.

Suggestions

Add 1-2 more concrete capabilities (e.g. optional provider/model selection, JSON output mode) to lift specificity toward 4-5.

Include natural user synonyms like "look up", "search the web", or "find online" to improve trigger term coverage.

Make the "when" clause more explicit about what distinguishes this from Claude's built-in search, e.g. "Use when you need a fast dedicated search with full source URLs rather than Claude's built-in lookup."

Dimension	Reasoning	Score
Specificity	"Trigger native web search" and "concise summaries and full source URLs" name the domain and 1-2 concrete actions, but the actions are minimal (trigger a search, get a summary) without enumerating specific capabilities like provider/model selection.	3 / 5
Completeness	It clearly answers what ("Trigger native web search... concise summaries and full source URLs") and when ("Use when you need quick internet research"), but the "when" could be more specific about distinguishing this from ordinary built-in search.	4 / 5
Trigger Term Quality	Phrases like "web search", "internet research", and "source URLs" are relevant natural terms, but common synonyms a user might say (e.g. "look up", "search the web", "find online") and variations are missing.	3 / 5
Distinctiveness Conflict Risk	"Native web search" carves a reasonably distinct niche (a dedicated fast-model search with URLs) with only minor overlap risk against general research or browsing skills.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mitsuhiko/agent-stuff
Path: skills/native-web-search/SKILL.md
Commit: 13bc8f8

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.