extract

Extract structured data from websites and produce an executable Playwright script plus extracted data. Use when the user wants to scrape, extract, pull, collect, or harvest data from any website — product listings, tables, search results, feeds, profiles, or any repeating content.

Quality

88%

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

Quality

Content

77%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 body is highly actionable with executable code, a clear validated workflow, and strong error handling, but it is verbose due to repeated routing guidance and makes no use of progressive disclosure via bundle files despite its length.

Suggestions

Consolidate the selector-routing logic: pick one of the ASCII diagram, the priority table, or the Path A/B/C routing and reference it once instead of restating the same decision three times.

Move the per-mechanism Playwright patterns (hydration, virtualization, infinite scroll, pagination) into a references/ file (e.g. MECHANISMS.md) and link to it from SKILL.md to improve progressive disclosure and reduce token load.

Tighten the Decision Strategy and Execution Chain Step 2 sections, which overlap heavily on the search→get→fallback decision.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (no primers on what a website or Playwright is), but the selector-routing logic is restated three times — ASCII diagram, priority table, and Path A/B/C routing plus a restated 'Non-negotiable rule' — which could be consolidated.	3 / 5
Actionability	Provides copy-paste-ready Playwright snippets for hydration, virtualized lists, infinite scroll, and pagination, plus concrete actionbook commands with flags, a full script template, and a validation table with explicit pass conditions.	5 / 5
Workflow Clarity	A clear six-step sequence (Understand → Obtain selectors → Probe → Generate → Execute/validate → Deliver) with an explicit validation table and a feedback loop ('If validation fails... adjust selectors or wait strategy, and re-run').	5 / 5
Progressive Disclosure	Content is well-organized with clear section headers, but no bundle files exist and everything is inlined in a ~360-line SKILL.md; the mechanism code patterns and reference tables could plausibly live in separate reference files.	3 / 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 exemplary: it states concrete capabilities, supplies a rich set of natural trigger terms with synonyms, and explicitly covers both what the skill does and when to invoke it. It is concise yet comprehensive with a clearly distinct niche.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete actions — 'Extract structured data', 'produce an executable Playwright script', 'plus extracted data' — giving comprehensive coverage of capabilities, matching the anchor-5 example pattern.	5 / 5
Completeness	Explicitly answers both 'what' (extract data + produce Playwright script + data artifacts) and 'when' (an explicit 'Use when the user wants to scrape, extract, pull, collect, or harvest data...' clause with concrete trigger phrases).	5 / 5
Trigger Term Quality	Comprehensive synonym coverage users would naturally say — 'scrape, extract, pull, collect, or harvest' — plus concrete content types (product listings, tables, search results, feeds, profiles), with no common terms missing.	5 / 5
Distinctiveness Conflict Risk	Carves a clear niche — web data extraction delivered as a re-runnable Playwright script — with distinct harvesting triggers, leaving only minimal overlap risk with generic browser-automation skills.	5 / 5
	Total	20 / 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: actionbook/actionbook
Path: skills/extract/SKILL.md
Commit: 5a3eb05

Reviewed: 13 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.