weread-year-in-review-video-template

WeRead-inspired HyperFrames video template for vertical annual reading reports, personal reading dashboards, book-note recaps, and shareable year-in-review stories. Use when users want a 9:16 HTML-to-MP4 reading report with warm paper texture, editorial Chinese typography, book-page metaphors, data highlights, and deterministic motion.

Quality

85%

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

82%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 tight, executable template skill body: lean token usage, a concrete copy-and-edit workflow, and appropriate one-level-deep references with an explicit validation step. The main weaknesses are the missing example.html listed in the Resource Map, the absence of any inline REPORT-object example, and no fix-and-revalidate feedback loop.

Suggestions

Remove or actually add the missing 'example.html' from the Resource Map (and the frontmatter 'od.preview.entry') so the documented bundle matches the real file tree.

Inline a minimal REPORT object snippet (3-4 keys) so the executor knows the data shape without opening assets/template.html first.

Add a fix-and-revalidate feedback loop after the checklist step (e.g., 'If any P0 item fails, fix the scene and re-validate before emitting').

Dimension	Reasoning	Score
Conciseness	The body is lean and directive throughout: copy path, the exact REPORT fields to replace, visual-language constraints, determinism rules, and an output contract. It assumes Claude's competence (no explanation of HyperFrames, video rendering, or HTML) and every section earns its place. Fits the top anchor; no padded or redundant explanation to trim.	5 / 5
Actionability	Concrete, executable steps ('Copy `assets/template.html` to `index.html`', a specific field list for the REPORT object, direct 'data-start', 'data-duration', 'data-track-index' attributes, and a copy-paste artifact XML snippet). Not 5 because it never shows the shape of the REPORT object or a minimal scene snippet inline, so the executor must open the template file to know exactly what to edit.	4 / 5
Workflow Clarity	A clear 7-step sequence with an explicit validation checkpoint ('Validate against `references/checklist.md` before emitting') and a referenced checklist. Not 5 because there is no feedback loop (what to do when validation fails: fix and re-validate), which the top anchor expects; not 3 because validation is explicit, not missing.	4 / 5
Progressive Disclosure	Good structure against the actual bundle: a Resource Map, a one-level-deep clearly signaled reference ('references/checklist.md'), and the heavy template appropriately split into 'assets/template.html'. Not 5 because the Resource Map lists 'example.html' at the skill root, which does not exist in the bundle (only SKILL.md, assets/template.html, and references/checklist.md are present), so the file listing is partly stale/inaccurate.	4 / 5
	Total	17 / 20 Passed

Description

87%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 strong description: it states what the skill produces and when to use it with concrete, distinctive trigger conditions and natural user phrasing. The only gap is that capabilities are framed as template characteristics rather than explicit action verbs, which slightly limits specificity.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete deliverable characteristics ('9:16 HTML-to-MP4 reading report', 'warm paper texture, editorial Chinese typography, book-page metaphors, data highlights, and deterministic motion'), but the actions themselves (create/generate/assemble) are implied by 'template for' rather than enumerated as specific verbs. Not 5 because no explicit list of concrete actions; not 3 because coverage goes well beyond 1-2 actions.	4 / 5
Completeness	Clearly answers both: what ('WeRead-inspired HyperFrames video template for vertical annual reading reports, personal reading dashboards, book-note recaps, and shareable year-in-review stories') and when ('Use when users want a 9:16 HTML-to-MP4 reading report with...') with concrete trigger conditions. Explicit 'Use when' clause with concrete format and content conditions matches the top anchor.	5 / 5
Trigger Term Quality	Good natural phrases users would say: 'WeRead', 'annual reading reports', 'reading dashboards', 'book-note recaps', 'year-in-review stories'. A few natural terms are missing (e.g., Goodreads, 'reading wrap-up', 'reading log'), keeping it below the comprehensive synonym/extension coverage of a 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche: WeRead-inspired vertical annual reading report videos with a specific format (9:16, HyperFrames, HTML-to-MP4). Triggers are distinctive and unlikely to fire for the wrong skill; minimal overlap with generic video or dashboard skills.	5 / 5
	Total	18 / 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: nexu-io/open-design
Path: skills/weread-year-in-review-video-template/SKILL.md
Commit: 1b47e60

Reviewed: 3 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.