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

87%

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%

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

A well-structured, actionable router skill that sequences routing decisions with explicit checkpoints and delegates detail to loaded-on-demand sibling skills. The main drag is conciseness — the 'Keeping skills current' section and some disambiguation prose carry explanatory padding.

Suggestions

Tighten the 'Keeping skills current' paragraph to the commands and their one-line effect; drop the network-hiccup and no-op rationale that explains behavior Claude can infer.

Consider moving the '--skip-skills neutered' aside and CI escape-hatch into a footnote or removing it, since it is operational minutiae that competes with routing context.

De-duplicate the disambiguation bullets that restate cheat-sheet rows (e.g. the product-vs-site and footage cases) to keep the routing section lean.

Dimension	Reasoning	Score
Conciseness	The body is dense and avoids explaining known concepts, but contains padded passages (the 'Keeping skills current' paragraph — 'so a freshly init'd project always has the complete, latest set... so init never hard-fails on a network hiccup' and the '--skip-skills flag is currently neutered' aside) and some redundant disambiguation prose that could be tightened.	2 / 3
Actionability	Provides concrete executable commands ('npx skills add heygen-com/hyperframes --skill <workflow-name>', 'npx hyperframes skills check --json', 'npx hyperframes skills update') plus per-workflow concrete Input/Output/Triggers, giving copy-paste-ready routing guidance.	3 / 3
Workflow Clarity	The routing process is clearly sequenced with explicit checkpoints: confirm input before routing ('ask before entering any workflow'), disambiguate when unclear ('ask one question'), and verify the workflow is installed ('check it's actually available to you' → install → re-read).	3 / 3
Progressive Disclosure	Acts as a lean overview/router that points one level deep to on-demand domain skills ('/hyperframes-core', '/hyperframes-animation', etc.) and workflows, each clearly signaled; no bundle files exist, and the inline workflow details are summaries rather than full workflows.	3 / 3
	Total	11 / 12 Passed

Description

90%

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, highly targeted router description that answers what and when with explicit triggers and clear deferral rules. Its only real weakness is voice: the second-person imperative phrasing triggers the rubric's specificity penalty.

Suggestions

Rewrite in third person to avoid the specificity penalty — e.g. 'Routes any request to make, create, edit, animate, or render a video...' instead of 'READ THIS FIRST... read it before any other video or animation skill'.

Trim the internal rationale ('so read it before any other video or animation skill instead of guessing a workflow') which restates the trigger and adds length without new trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('make, create, edit, animate, or render a video, animation, or motion graphic — a promo, explainer, captioned clip, title card, overlay', 'routes the request to the right specialized workflow', 'renders video from HTML'), which would anchor at 3, but the description is written in second-person imperative voice ('READ THIS FIRST', 'read it before any other video or animation skill instead of guessing a workflow'), which the rubric penalizes by one point.	2 / 3
Completeness	Clearly answers both what ('HyperFrames renders video from HTML... routes the request to the right specialized workflow and points to the HyperFrames domain skills') and when with explicit triggers ('READ THIS FIRST for any request to make...', 'Most important when no project CLAUDE.md or AGENTS.md describes the video workflow').	3 / 3
Trigger Term Quality	Covers natural terms users would actually say — 'make/create/edit/animate/render a video', 'promo', 'explainer', 'captioned clip', 'title card', 'overlay' — matching the anchor for good coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	Carves a clear niche (HyperFrames video authoring/rendering) with explicit deferral guidance ('defer only when the user asks to drive a browser to capture or record a session, or names another framework'), making conflicts with sibling skills unlikely.	3 / 3
	Total	11 / 12 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: 0af32ce

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.