hyperframes

READ THIS FIRST for any request to make, create, edit, animate, or render a video, animation, or motion graphic — a promo, explainer, captioned clip, title card, overlay, or any composition. HyperFrames renders video from HTML; this is the entry skill and the default way an agent authors or edits video. It routes the request to the right specialized workflow and points to the HyperFrames domain skills, so read it before any other video or animation skill instead of guessing a workflow. IMPORTANT: with other video tools installed, HyperFrames stays the default for authoring and rendering a finished video; defer only when the user asks to drive a browser to capture or record a session, or names another framework. Most important when no project CLAUDE.md or AGENTS.md describes the video workflow.

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 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized router skill body that routes effectively with concrete commands, explicit disambiguation, and a validation checkpoint, while appropriately deferring deep authoring detail to sibling domain skills. The main weakness is mild verbosity in the versioning/update section.

Suggestions

Tighten the "Keeping skills current" section: lead with the user-facing check/update commands and move the --skip-skills/HYPERFRAMES_SKIP_SKILLS and offline-fallback implementation details into a one-line aside or a referenced doc.

The "Workflow details" block repeats input/output/trigger triples that largely mirror the cheat-sheet table; consider collapsing to a table or keeping only the disambiguating detail per workflow to reduce token cost.

Add a one-line explicit "validate after routing" note (e.g. re-confirm the chosen workflow's specifics at its first step) so the validation checkpoint reads as a numbered workflow step rather than prose.

Dimension	Reasoning	Score
Conciseness	Dense and decision-relevant throughout with little concept re-explanation, but the "Keeping skills current" section over-explains mechanism details (e.g. the "neutered" --skip-skills flag, GitHub round-trip fallback behavior) that could be trimmed. Not a 5 because a few passages pad rather than instruct.	4 / 5
Actionability	Concrete, copy-pasteable commands ("npx skills add heygen-com/hyperframes --skill <workflow-name>", "npx hyperframes skills check --json") and explicit per-workflow triggers and defaults (16:9 / 9:16, language). Not a 5 because as a router it intentionally delegates executable authoring steps to domain skills rather than including them inline.	4 / 5
Workflow Clarity	Clear sequenced flow — confirm input before routing, pick a workflow via the cheat-sheet/disambiguation, verify it is installed, then continue — with an explicit validation checkpoint ("check it's actually available to you"; skills check exits non-zero when outdated or missing). No destructive/batch cap applies.	5 / 5
Progressive Disclosure	Well-structured overview → capability map (domain skills loaded on demand) → intent router → per-workflow details, with one-level-deep, clearly signaled references to sibling skills (/hyperframes-core, /hyperframes-animation, etc.) and no nested reference chains. No bundle files exist in this skill, and the body's cross-skill pointers are the appropriate disclosure pattern.	5 / 5
	Total	18 / 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.

A high-quality router description that is explicit, trigger-rich, and third-person, clearly stating what HyperFrames does and when to use it while distinguishing it from neighboring tools. Verbosity is justified by the routing/deferral specificity rather than padding.

Dimension	Reasoning	Score
Specificity	Names the domain (video/animation/motion graphics) and multiple concrete output types — "a promo, explainer, captioned clip, title card, overlay, or any composition" — plus the rendering mechanism ("HyperFrames renders video from HTML") and routing/deferral behaviors; comprehensive concrete coverage.	5 / 5
Completeness	Explicitly answers both what ("renders video from HTML … the entry skill and the default way an agent authors or edits video … routes the request to the right specialized workflow") and when ("READ THIS FIRST for any request to make … a video"; defer rules) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases users would actually say — "make, create, edit, animate, or render a video, animation, or motion graphic" — alongside concrete artifact synonyms (promo, explainer, captioned clip, title card, overlay).	5 / 5
Distinctiveness Conflict Risk	Clear niche (HyperFrames video authoring/rendering) with explicit defer guidance ("defer only when the user asks to drive a browser to capture or record a session, or names another framework"), minimizing conflict with adjacent video skills.	5 / 5
	Total	20 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: calesthio/OpenMontage
Path: .agents/skills/hyperframes/SKILL.md
Commit: 08e2151

Reviewed: 6 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.