hyperframes

Render MP4/WebM videos from HTML compositions.

Quality

69%

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

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/creative/hyperframes/SKILL.md

Quality

Content

88%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 a high-quality operational guide: an explicit hard-gated workflow, fully executable commands, embedded pitfalls that encode real failure modes, and a rigorous verification section. The main weaknesses are minor redundancy (repeated preview warning, transition rules split across two sections) and some detail that could live entirely in the referenced files.

Suggestions

Consolidate the preview-worker CPU warning into the Cleanup section only, and have Quick Reference and Pitfalls link to it rather than restating it.

Merge the transition rules in §5 and the transitions bullet in §6 into one place, pointing to references/features.md#transitions for mood/energy tables.

Trim the inline audio-reactive and caption-style specifics that references/features.md already documents, keeping only the hard rules (kill-tween requirement, no .en whisper models on non-English audio).

Dimension	Reasoning	Score
Conciseness	The body is dense with skill-specific, non-generic knowledge (finite repeat requirement, timeline registration contract, DESIGN.md gate, beginFrame fallback) and assumes Claude's competence throughout. However, the preview-worker CPU warning is repeated in three places (Quick Reference, Cleanup, Pitfalls) and scene-transition rules appear in both §5 and §6 — more than trivially trimmable, so anchor 4 rather than 5.	4 / 5
Actionability	Guidance is fully executable throughout: copy-paste commands (`npx hyperframes init/lint/validate/inspect/render`, `ffprobe` duration/audio checks, `ffmpeg` frame extraction, `pkill` cleanup), exact thresholds (4.5:1 contrast, paced-fast <0.2s, Node >= 22, hyperframes@>=0.4.2), and concrete GSAP patterns (`tl.set(el, {opacity: 0, visibility: "hidden"}, group.end)`). This matches the anchor-5 'fully executable; copy-paste ready' example.	5 / 5
Workflow Clarity	The 8-step procedure is clearly sequenced (plan → scaffold → layout → animate → transitions → audio/captions → lint/preview/render → website-to-video) with explicit validation gates (lint --strict && validate && inspect), a 6-point verification checklist, and an error-recovery loop (run doctor, attach output on render failure). This matches the anchor-5 'clear sequence with explicit validation steps; feedback loops for error recovery'.	5 / 5
Progressive Disclosure	The body is an overview that links one level deep to references/cli.md, composition.md, gsap.md, features.md, website-to-video.md, and troubleshooting.md — all verified to exist — plus scripts/setup.sh, with a clear References index. Scored against the actual bundle structure this is strong, but some detail duplicated inline (transition mood tables referenced in §6 while rules are restated, caption/audio-reactive specifics that features.md covers) keeps it at anchor 4 rather than 5.	4 / 5
	Total	18 / 20 Passed

Description

50%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 concise and names a concrete, distinctive capability, but it is a single clause with no trigger guidance, no coverage of the skill's full feature set, and no differentiation from the sibling manim-video skill. It answers "what" well and "when" not at all.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks for a rendered video from text, a script, or a website, or wants animated titles, captions, or social overlays."

Broaden capability coverage with 1-2 more concrete actions (e.g. synced captions/TTS, scene transitions, audio-reactive visuals) so the description reflects the skill's actual scope.

Add a disambiguator against sibling skills, e.g. "Use manim-video for math/equation animation; use this for motion graphics and media-driven video."

Dimension	Reasoning	Score
Specificity	"Render MP4/WebM videos from HTML compositions" names the domain and a single concrete action, but does not cover the skill's other capabilities (animation timelines, captions, TTS, transitions). This matches anchor 3 ('names domain and 1-2 concrete actions, but not comprehensive') and not anchor 4, which requires several specific actions listed.	3 / 5
Completeness	The "what" is clear (render MP4/WebM videos from HTML compositions) but there is no "when" clause or equivalent trigger guidance anywhere in the description, which caps completeness at 3 per the judging guidelines. Not score 2, because the "what" is concrete rather than vague.	3 / 5
Trigger Term Quality	Relevant keywords are present ("MP4", "WebM", "videos", "HTML") but common natural variations users would say — "make a video", "animation", "motion graphics", "captions" — are absent. This fits anchor 3 ('some relevant keywords but missing common variations or synonyms') better than anchor 4's 'good keyword coverage'.	3 / 5
Distinctiveness Conflict Risk	The HTML-to-video niche is fairly distinct, but a sibling video skill (manim-video) exists and the description offers no trigger phrasing to disambiguate which video requests should route here. This matches anchor 3 ('somewhat specific but could still overlap with similar skills') rather than anchor 4's 'mostly distinct; minor overlap risk'.	3 / 5
	Total	12 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/creative/hyperframes/SKILL.md
Commit: 68fa7e9

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.