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

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

75%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 a well-organized, mostly lean overview that routes to real bundle files and supplies concrete output contracts, hard rules, and an error-recovery table. Its main limitation is that some executable detail and a consolidated validate-checkpoint workflow live across the reference rather than fully realized inline.

Suggestions

Add a short numbered end-to-end workflow with an explicit validate-checkpoint (fetch → read stderr tier line → warn on shell/empty → output) to push workflow_clarity toward 5.

Trim the duplicated trigger-term lists in the body (they already appear in when_to_use frontmatter) to tighten conciseness.

Move or consolidate the inline Privacy/fetch-tier command explanations into references/read-methods.md so SKILL.md stays a pure overview.

Dimension	Reasoning	Score
Conciseness	Lean, scannable sections that assume Claude's competence (routing table, output templates, hard rules) with only minor over-explanation (e.g. the Privacy tier rationale and repeated 'when_to_use' guidance); tighter than the score-3 anchor but not perfectly stripped like the score-5 example.	4 / 5
Actionability	Provides concrete routing rules, output-format templates, and defers executable commands to real bundle scripts (fetch.sh, fetch_feishu.py, fetch_weixin.py, read-methods.md), all of which exist in the bundle; minor gaps are that key command snippets live in the reference rather than inline in SKILL.md.	4 / 5
Workflow Clarity	Clear sequence — route → fetch → output → save — with explicit validation signals ('read the stderr if a fetch fails', 'stop and warn' on paywall shells) and a Gotchas error-recovery table; just short of the score-5 anchor because there is no single numbered end-to-end checklist with a validate-then-proceed loop.	4 / 5
Progressive Disclosure	SKILL.md acts as an overview pointing one level deep to references/read-methods.md and four scripts/ files, all verified present; well-signaled routing table directs to the right file, but a couple of inline command blocks could arguably live in the reference, leaving it just below the ideal score-5 split.	4 / 5
	Total	16 / 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.

The description is concrete, complete, and distinctive, covering both capabilities and triggers in multiple languages with a clear scope boundary. It is among the strongest reference examples and shows no vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'fetching source content', 'concise summaries', 'clean Markdown', 'convert, save, quote, cite, or feed downstream work' — with comprehensive coverage analogous to the score-5 PDF example.	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, check, summarize...') with concrete trigger phrases, plus a boundary clause ('Not for local text files already in the repo').	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms ('read, fetch, check, summarize, quote, cite, convert, save'), URL/PDF targets, and multilingual triggers, matching the score-5 anchor that expects synonyms and file extensions.	5 / 5
Distinctiveness Conflict Risk	Clear niche (URL/PDF fetching and conversion) with distinct triggers and an explicit exclusion ('Not for local text files already in the repo') that minimizes overlap with local-file skills, matching the score-5 'clear niche with distinct triggers' anchor.	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: f902996

Reviewed: 1 day 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.