Name: read
Rating: 72 (1 reviews)
Author: tw93

read

Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local text files already in the repo.

Quality

89%

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

The canonical home for this skill is read in tw93/Waza

Quality

Content

78%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.

A well-architected skill body: lean policy overview up front, executable commands correctly externalized one level deep, and real bundle files backing every reference. Main improvements are reducing minor ceremony and consolidating the workflow into a single explicit checkpointed sequence.

Suggestions

Collapse the abstract 'Outcome Contract' fields into the concrete bullets that follow them, and state the untrusted-data rule once to remove the line 12/81 redundancy.

Add one short numbered sequence (route → fetch → handle tier/failure → save or display → stop) near the top so the distributed validation checkpoints read as a single workflow.

Inline one or two of the most common fetch commands (e.g. the built-in fetcher invocation) directly in the Routing section so the body is copy-paste ready for the common case without requiring the reference.

Dimension	Reasoning	Score
Conciseness	The body is dense and skill-specific with no general-knowledge padding, but the abstract 'Outcome Contract' fields and a repeated untrusted-data rule (lines 12 and 81) are minor ceremony that could be trimmed.	4 / 5
Actionability	Concrete routing table, named script paths, a structured stderr format, and output templates make the body highly actionable; the copy-paste per-method command blocks live one level deep in references/read-methods.md, leaving a minor gap in the body itself.	4 / 5
Workflow Clarity	A clear route→fetch→extract→save/report flow exists with error-recovery feedback (Gotchas table) and save-validation (auto-increment, never overwrite), but it is distributed across sections rather than presented as one explicit validate→fix→retry numbered sequence.	4 / 5
Progressive Disclosure	Clean three-tier split — overview/policy body, one-level-deep references/read-methods.md (verified to exist and contain executable bash), and scripts/ implementations — with well-signaled navigation and no nested references.	5 / 5
	Total	17 / 20 Passed

Description

100%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.

A model description: concrete actions, comprehensive multilingual trigger terms, explicit what/when guidance, and a clear boundary that prevents misfires. No meaningful gaps to penalize.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'fetching source content', 'concise summaries', 'clean Markdown when asked to convert, save, quote, cite, or feed downstream work' — with comprehensive coverage and no vague filler.	5 / 5
Completeness	Explicitly answers both what ('Reads URLs and PDFs by fetching source content...') and when ('Use when users ask in any language to read, fetch...') with concrete trigger phrases, so the missing-'Use when' cap does not apply.	5 / 5
Trigger Term Quality	Enumerates eight natural user verbs (read, fetch, check, summarize, quote, cite, convert, save) and explicitly covers multiple languages, giving comprehensive synonym coverage beyond the 5 anchor.	5 / 5
Distinctiveness Conflict Risk	Clear URL/PDF-fetching niche with an explicit negative boundary ('Not for local text files already in the repo'), giving minimal conflict risk with other skills.	5 / 5
	Total	20 / 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: tw93/Waza
Path: plugins/waza/skills/read/SKILL.md
Commit: 97ddbc3

Reviewed: 6 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.