CtrlK
BlogDocsLog inGet started
Tessl Logo

web-reader

Read web pages, articles, and document links by converting URLs into Markdown text. Use the `read_url` tool directly, without bash. Sends the full URL to the third-party Jina Reader (r.jina.ai).

60

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./agent/src/skills/web-reader/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 examples and clear single-step guidance, and it adds genuine non-obvious value in the Privacy & freshness section. The main weakness is redundancy between the Usage and Common Usage sections that slightly hurts conciseness and organization.

Suggestions

Drop the repeated tushare example from 'Common Usage' or merge the two usage sections to remove redundancy.

Consider trimming the 'Suitable for' list since the same cases appear as concrete examples in 'Common Usage'.

DimensionReasoningScore

Conciseness

The body is mostly lean, but the 'Common Usage' section repeats the same tushare example already shown in 'Usage', and the 'Suitable for' list overlaps with 'Common Usage'; not a 4 because of this concrete redundancy that could be trimmed.

3 / 5

Actionability

Provides fully executable, copy-paste-ready 'read_url(url=...)' calls plus the JSON return shape, with examples covering API docs, articles, and GitHub; not below 5 because the common cases are concretely covered.

5 / 5

Workflow Clarity

This is a simple single-action skill and the single action ('Call the read_url tool directly ... do not use bash') is unambiguous, qualifying for the simple-skill exception; no destructive/batch operation is present to require validation checkpoints.

5 / 5

Progressive Disclosure

Content is well-organized into clearly headed sections (Purpose, Usage, Notes, Privacy & freshness, Common Usage) with no bundle files needed; not a 5 because the Usage/Common Usage redundancy is a minor organization gap.

4 / 5

Total

17

/

20

Passed

Description

61%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 clearly states what the skill does and anchors it to a specific tool, but it lacks an explicit 'Use when...' trigger clause, which caps completeness and limits distinctiveness. Trigger term coverage is good but not exhaustive.

Suggestions

Add an explicit trigger clause such as 'Use when the user asks to read, fetch, or scrape a web page, article, blog post, or documentation link as Markdown.'

Include a few more natural synonyms (e.g. 'blog posts', 'websites', 'documentation') to broaden trigger coverage.

Clarify what differentiates this from a generic web-fetch skill (e.g. ad/navigation stripping, Markdown output) to reduce overlap risk.

DimensionReasoningScore

Specificity

Quotes 'Read web pages, articles, and document links by converting URLs into Markdown text' name the domain plus one concrete action (URL→Markdown); not a 4 because only a single action is described rather than several.

3 / 5

Completeness

The 'what' is clear ('convert URLs into Markdown text') but there is no 'Use when...' or equivalent explicit trigger clause, so per the guideline completeness is capped at 3; not a 4 because 'when' is only weakly implied.

3 / 5

Trigger Term Quality

Natural user-facing phrases 'web pages, articles, and document links' plus 'URLs' give good keyword coverage; not a 5 because synonyms like 'blog posts', 'websites', or 'documentation' are missing.

4 / 5

Distinctiveness Conflict Risk

Tying the skill to the specific 'read_url' tool and 'Jina Reader (r.jina.ai)' gives it a distinct niche with minor overlap risk against general web-fetch skills; not a 5 because 'web pages, articles' is still somewhat broad.

4 / 5

Total

14

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
HKUDS/Vibe-Trading
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.