web-search-and-fetch
Run Google searches and fetch JS-rendered web pages as Markdown via `google-search-cli`, a Patchright-based CLI invoked through `uvx` from its GitHub repo (no local install needed). Use when the agent needs (1) fresh Google search results from a query, (2) the Markdown of a URL that plain HTTP fetch (curl/WebFetch) cannot render because it requires JavaScript or evades bots, or (3) inspection of the raw HTML of a Google results page. Trigger phrases include "google for ...", "search the web for ...", "fetch this page as markdown", "this page needs JS to render". Do not use for static doc URLs that WebFetch handles cleanly, or when Chromium cannot be installed on the machine.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Critical
Do not install without reviewing
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that covers all dimensions thoroughly. It provides specific capabilities, clear trigger phrases, explicit 'Use when' and 'Do not use' guidance, and carefully distinguishes itself from overlapping tools like WebFetch/curl. The description is detailed yet well-organized, making it easy for Claude to select appropriately from a large skill set.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: running Google searches, fetching JS-rendered web pages as Markdown, inspecting raw HTML of Google results pages. Also names the specific tool (`google-search-cli`), technology (Patchright-based CLI), and invocation method (`uvx`). | 3 / 3 |
Completeness | Clearly answers both 'what' (run Google searches, fetch JS-rendered pages as Markdown, inspect raw HTML) and 'when' (explicit 'Use when' clause with three numbered scenarios, plus trigger phrases and explicit 'Do not use' guidance for negative cases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases: 'google for ...', 'search the web for ...', 'fetch this page as markdown', 'this page needs JS to render'. Also includes technical terms like 'JavaScript', 'Google search results', 'Markdown', and 'URL' that users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive: explicitly differentiates itself from plain HTTP fetch tools (curl/WebFetch) by specifying its niche is JS-rendered pages and Google searches. The 'Do not use' clause further reduces conflict risk by clarifying boundaries with other fetching skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill with excellent actionability and workflow clarity. The exact command templates, output contracts, error handling branches, and retry policies give Claude precise guidance for every scenario. The main weakness is moderate verbosity — some sections explain design rationale (asymmetric headless defaults, why the install command uses the same --from URL) that Claude doesn't need to understand, only follow.
Suggestions
Trim the 'Critical default quirks' section to just state the defaults and when to override, removing the rationale ('mimics human browsing for anti-bot evasion', 'some pages render incorrectly headless').
Condense the Prerequisites section — the explanation of why the install routes through the same --from URL is unnecessary; just provide the command and the trigger condition.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary explanations (e.g., explaining what patchright is, the asymmetric headless defaults rationale, and the browser-state cache details could be tighter). The 'Critical default quirks' section explains design intent Claude doesn't need. However, most content is operationally relevant. | 2 / 3 |
Actionability | Provides exact, copy-paste-ready bash command templates for all three operations, specific CLI flags with explanations, concrete output format descriptions, and clear examples mapping user requests to commands. The explicit prohibition against modifying command templates is highly actionable. | 3 / 3 |
Workflow Clarity | The workflow section provides a clear numbered sequence with explicit validation/recovery steps: checking for truncation, handling anomalous output with retry (with a 'do not loop' cap), and error handling with specific branching (Chromium missing vs other errors). The failure policy adds additional guardrails including rate-limit detection. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers, but it's a moderately long monolithic file (~100 lines of substantive content) with no bundle files. Some sections like 'Critical default quirks' and 'Browser-state cache' could potentially be separated. However, for a single-tool skill without bundle files, the organization is reasonable. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- ceshine/ceshine-agent-skills
- Commit
348c2c1
- Reviewed
Table of Contents
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.