page-prep

Prepare any webpage for clean interaction by detecting and removing disruptive overlays (cookie banners, GDPR consent, modals, popups, newsletter signups, paywalls, login walls). Uses a cached database of 300+ known CMPs (Consent-O-Matic + EasyList) combined with heuristic DOM scanning. Produces portable JS recipes for any browser tool (Playwright, CDP, cmux-browser). ALWAYS use this skill before taking screenshots, scraping content, or automating interaction on any webpage that might have overlays blocking the view or preventing interaction. Triggers on: page prep, clean page, remove overlays, dismiss cookie banner, page blocked, overlay cleanup, consent banner, prepare page, unblock page, clear popups, cookie popup.

Quality

92%

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

85%Weight 40%Scale 1-3

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 and well-sequenced with strong validation feedback loops and appropriate externalization of scripts and references. Its only weakness is minor verbosity from editorializing and overlapping inline format specs.

Suggestions

Remove the editorializing line 'This two-layer verification is the agent's value over the heuristic script alone...' — it justifies the skill rather than instructing action.

Consolidate the Detection Report Format and Recipe Manifest Format into one example or move the detailed manifest spec into references/known-patterns.md to reduce inline overlap.

Tighten the Mode table prose and Step 8 bullet commentary, which restates information already conveyed by the table and code.

Dimension	Reasoning	Score
Conciseness	The body is mostly procedural and assumes Claude's competence (no basic-concept filler), but includes editorializing ('This two-layer verification is the agent's value over the heuristic script alone') and two overlapping JSON specs (Detection Report Format and Recipe Manifest Format) that could be tightened, matching the 'mostly efficient but could be tightened' anchor rather than the fully lean one.	2 / 3
Actionability	Provides copy-paste-ready bash commands ('node "$PAGE_PREP_DIR/overlay-db.js" refresh/bundle/status/lookup'), executable DOM-residual and watch-mode JS, and concrete Agent Fallback selectors, fully satisfying the 'executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	Steps 1–10 are explicitly sequenced with validation checkpoints and feedback loops ('Repeat until only legitimate page elements remain'; Step 9b 'Maximum 2 retries... After retries exhausted: report... do not block'), matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	Clear overview with well-signaled one-level-deep references to a real references/known-patterns.md file and externalized scripts (overlay-db.js, overlay-detect.js, both present in scripts/), with easy section-based navigation.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 specific, complete, and distinctive, naming concrete actions, tools, and overlay types while providing explicit when-to-use guidance and natural trigger terms. It is a strong, low-conflict description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('detecting and removing disruptive overlays', 'Produces portable JS recipes') with named overlay types, CMPs, and browser tools (Playwright, CDP, cmux-browser), matching the 'multiple specific concrete actions' anchor; voice is third person.	3 / 3
Completeness	Clearly answers what (detect/remove overlays, produce JS recipes) and when ('ALWAYS use this skill before taking screenshots, scraping content, or automating interaction') with explicit triggers, satisfying the both-what-and-when anchor.	3 / 3
Trigger Term Quality	Both a natural-use clause ('ALWAYS use this skill before taking screenshots, scraping content, or automating interaction') and an explicit trigger list ('page prep, clean page, remove overlays, dismiss cookie banner...') give strong coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	A narrow overlay/cookie-banner removal niche with distinct, specific triggers makes it unlikely to fire for the wrong skill.	3 / 3
	Total	12 / 12 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: catalan-adobe/skills
Path: skills/page-prep/SKILL.md
Commit: 7576839

Reviewed: 1 month 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.