url-dump

Quick capture URLs with automatic content extraction, insights, and categorization into knowledge booklets

Quality

66%

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 ./.claude/skills/url-dump/SKILL.md

Quality

Content

62%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 skill specifies a well-validated, clearly sequenced workflow with excellent output templates, but it is monolithic and verbose, inlining material that would benefit from separate reference files. Tightening and splitting would improve token efficiency and navigation.

Suggestions

Move the full bookmark template, tool template, and category index template into a references/ file (e.g. TEMPLATES.md) and link to them from the body to cut inline tokens.

Replace the abstract fetch/extract step ('Fetch the web page content') with the concrete web-fetch invocation or reader-mode/archive fallback commands named in the Loop Engineering section.

Trim or remove the 'Learning and Adaptation' and 'Success Metrics' sections, which state generic aspirations Claude can infer rather than executable guidance.

Dimension	Reasoning	Score
Conciseness	The ~450-line body is noticeably verbose: two full inline markdown templates, a booklet directory tree, a category index template, plus padded sections like 'Learning and Adaptation' and 'Success Metrics' that add tokens without aiding execution.	2 / 5
Actionability	Output structure is copy-paste ready — exact YAML frontmatter fields, file paths like '05-knowledge/booklets/[category-slug]/[title-slug]-YYYY-MM-DD.md', and full markdown templates — but the core fetch/extract step is described ('Fetch the web page content') rather than given as an executable command.	4 / 5
Workflow Clarity	The 8-step process is clearly sequenced with explicit validation: a deterministic quality gate, confidence thresholds, a ~3-retry cap, paywall hard-stop, and human escalation, plus Verification Protocols acting as a checklist for this batch operation.	5 / 5
Progressive Disclosure	Section structure is clear and the one external reference (loop-engineering SKILL.md) is well signaled, but no bundle files exist and large inlined content — two full templates, the booklet tree, and the category index template — that belongs in separate reference files keeps this at the midpoint.	3 / 5
	Total	14 / 20 Passed

Description

71%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 states concrete capabilities clearly but omits explicit trigger guidance, relying on the body for 'when to use' phrasing. Adding a 'Use when...' clause with natural terms like 'bookmark this' or 'save for later' would raise completeness and trigger quality.

Suggestions

Add an explicit 'Use when the user says "save this link", "bookmark this", "url dump", or "save for later"' clause to the description so trigger guidance is not isolated in the body.

Surface natural trigger synonyms (bookmark, save for later, save this link) directly in the description field rather than only in the When to Invoke section.

Tighten 'automatic content extraction, insights, and categorization' so the distinct URL-capture niche reads even more clearly apart from general knowledge skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Quick capture URLs', 'automatic content extraction', 'insights', and 'categorization into knowledge booklets' — covering the workflow comprehensively with no real gaps.	5 / 5
Completeness	The 'what' is clear and concrete, but the description lacks any 'Use when...' clause or explicit trigger guidance — the natural triggers live in the body's 'When to Invoke' section, capping completeness at 3.	3 / 5
Trigger Term Quality	'Quick capture URLs' is a natural phrase and 'knowledge booklets' is domain-distinct, but the common trigger variations a user would say ('bookmark this', 'save for later', 'save this link') appear only in the body, not the description field.	4 / 5
Distinctiveness Conflict Risk	The URL-capture-into-knowledge-booklets niche is mostly distinct, though there is minor overlap risk with the related 'braindump' and 'knowledge-consolidation' skills referenced in the body.	4 / 5
	Total	16 / 20 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: huytieu/COG-second-brain
Path: .claude/skills/url-dump/SKILL.md
Commit: cb4644d

Reviewed: 2 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.