stitched-full-page-capture

Capture or repair reliable full-page screenshots for lazy-loaded, scroll-animated, Framer, WebGL/canvas, or reveal-heavy web pages. Use when full-page screenshots are blank, gray, white, sparse, show a tiny content strip, disagree with a working scroll video, or when article evidence/section crops must be derived from a trustworthy full-page image.

Quality

90%

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

96%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 content is tight, actionable, and well-structured, with a concrete script invocation, real validation checkpoints, and a genuine feedback/reject loop for a batch operation. The only minor gap is slight overlap between the inline script-behavior bullets and the bundled script itself.

Dimension	Reasoning	Score
Conciseness	Lean body with no padding or re-explanation of concepts Claude already knows; every section (Overview, Core Workflow, Script, Validation, Notes) earns its tokens.	5 / 5
Actionability	Fully executable guidance: a copy-paste node command with real path and manifest argument, documented options with defaults, and concrete validation commands (sips, git diff, ffprobe).	5 / 5
Workflow Clarity	Clear 9-step Core Workflow sequence plus an explicit Validation section with checkpoints and a reject-candidate feedback signal ("Reject a full-page candidate when...") appropriate for this batch operation.	5 / 5
Progressive Disclosure	Well-organized into clear sections with the heavy logic correctly deferred to the bundled scripts/stitch_full_page_capture.mjs (a real, one-level-deep reference); minor inline duplication of the script's behavior slightly tempers the score.	4 / 5
	Total	19 / 20 Passed

Description

83%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 well-constructed: third-person voice, explicit what-and-when structure, and vivid failure-mode triggers that a user would naturally voice. Minor room to broaden the action vocabulary and add a few more trigger synonyms.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "Capture or repair reliable full-page screenshots" and deriving "article evidence/section crops" — with named page-type domains, though the action set is essentially capture/repair rather than a broad inventory.	4 / 5
Completeness	Explicitly answers both what ("Capture or repair reliable full-page screenshots...") and when ("Use when full-page screenshots are blank, gray, white, sparse...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural trigger language users would say ("blank, gray, white, sparse, show a tiny content strip, disagree with a working scroll video") with good synonym coverage, though a few common phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (stitched full-page capture for lazy/scroll-animated pages) with distinct failure-mode triggers; minor overlap risk with general screenshot skills.	4 / 5
	Total	17 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: MengTo/Skills
Path: agent-skills/codex/stitched-full-page-capture/SKILL.md
Commit: 4c716b5

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.