web-fetch

Fetches web content with intelligent content extraction, converting HTML to clean markdown. Use for documentation, articles, and reference pages http/https URLs.

24.66x

Quality

76%

Does it follow best practices?

Impact

74%

24.66x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./data/skills-md/0xbigboss/claude-code/web-fetch/SKILL.md

Quality

Content

82%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 body is highly actionable with executable commands and well-structured sections, assuming Claude's intelligence throughout; its main weaknesses are mild redundancy between the usage examples and the patterns table, and an external script reference that is not bundled.

Suggestions

Remove the redundancy between the Quick Usage code block and the Site Patterns table — keep one as the canonical reference and link the other to it.

Bundle `fetch.ts` under `scripts/` (or move it to a `references/` doc) so the universal-fallback path resolves to a real file in the skill bundle.

Add a one-line verification step after fetching (e.g. pipe through `wc -l` or check for empty output) to give the workflow an explicit validation checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, but the Quick Usage code block duplicates the same selectors already given in the Site Patterns table, a minor redundancy that could be trimmed; not a 5 because of that repeated information.	4 / 5
Actionability	Commands are fully executable and copy-paste ready (e.g. `curl -s "<url>" \| html2markdown --include-selector "article"`), with concrete examples covering the common cases across known and unknown sites.	5 / 5
Workflow Clarity	There is a clear sequence (known-site selectors -> universal fallback -> finding a selector -> troubleshooting) and the selector-discovery section gives an ordered mini-workflow, but no explicit validation checkpoint; minor gap keeps it below 5.	4 / 5
Progressive Disclosure	Content is well-organized into clearly signaled sections with no nested references, but the referenced `~/.claude/skills/web-fetch/fetch.ts` script is not present in a `scripts/` bundle, a minor organization gap rather than a fully self-contained or cleanly offloaded structure.	4 / 5
	Total	17 / 20 Passed

Description

70%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 is third-person, answers both what and when, and carries solid trigger terms, but leans on the buzzword "intelligent content extraction" and lacks the concrete user-mention triggers that would push it to the top level.

Suggestions

Replace "intelligent content extraction" with concrete actions, e.g. "Fetches web pages and converts HTML to clean markdown, stripping navigation and boilerplate."

Expand the when-clause with user-mention triggers, e.g. "Use when the user asks to fetch a web page, convert a URL to markdown, or extract article/documentation content."

Add natural synonyms users say ("web page", "URL", "scrape") to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and a couple of concrete actions ("Fetches web content", "converting HTML to clean markdown") but "intelligent content extraction" is vague fluff rather than a distinct action, so it stops at 1-2 concrete actions rather than a comprehensive list.	3 / 5
Completeness	Clearly states what it does (fetch + convert HTML to markdown) and gives an explicit "Use for ..." when-clause listing document types; it is not a 5 because the when-clause lists categories rather than concrete user-mention trigger phrases.	4 / 5
Trigger Term Quality	Includes natural terms a user would say ("documentation, articles, and reference pages", "http/https URLs"), but misses common synonyms like "web page", "URL", or "scrape", leaving a few natural terms uncovered.	4 / 5
Distinctiveness Conflict Risk	The fetch-to-markdown niche with reference-page triggers is mostly distinct from other skills, with only minor overlap risk against general web/scraping tools; not a 5 because "web content" is still fairly broad.	4 / 5
	Total	15 / 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: NeverSight/skills_feed
Path: data/skills-md/0xbigboss/claude-code/web-fetch/SKILL.md
Commit: 2f57aec

Reviewed: about 23 hours 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.