hyperframes-cli

Use the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, cloudrun, feedback, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, auth, tts, and remove-background. Also use when diagnosing build or render failures. validate, inspect, and layout are deprecated aliases; use check. Covers local, HeyGen-hosted cloud, AWS Lambda, and Google Cloud Run rendering.

Quality

96%

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

92%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 highly actionable, well-sequenced skill body with explicit validation checkpoints and excellent progressive disclosure via a verified reference table. The only weakness is moderate verbosity in the catalog/agent-conventions prose, which could be tightened.

Suggestions

Tighten the agent-conventions catalog prose (lines 79-84): collapse the dropped/unindexed/tier explanation into a shorter rule plus the one remediation command, cutting redundant rationale.

The 'Mandatory creator-edit cross-references' list and the reference table overlap somewhat with the inline commands; consider consolidating cross-skill links into a single short pointer to reduce repetition.

Dimension	Reasoning	Score
Conciseness	Largely efficient, domain-specific operational guidance Claude would not already know, with copy-paste commands; the agent-conventions block (catalog tiers, dropped/unindexed semantics) is somewhat dense and could be trimmed without losing the action.	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands throughout (init, catalog --query, lint, check, preview --background, render --quality high, jq/ffprobe pipelines) covering the common authoring and render cases.	5 / 5
Workflow Clarity	The 9-step Development loop is clearly sequenced with explicit validation gates (lint after first pass, check as required final gate, render only after approval, verify output non-empty via test -s and ffprobe) and feedback loops; destructive/batch paths include validation, so no cap applies.	5 / 5
Progressive Disclosure	SKILL.md is a well-structured overview with a clear needs-to-reference table pointing one level deep to real bundle files (init-and-scaffold.md, lint-validate-inspect.md, cloud.md, lambda.md, etc., all present in references/), with easy navigation and no deep nesting.	5 / 5
	Total	19 / 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 dense, command-enumerated description that clearly states capabilities and explicit use-conditions with strong trigger-term coverage and distinctiveness. The long command list is information-dense capability enumeration rather than fluff, though it borders on verbose.

Dimension	Reasoning	Score
Specificity	Names the domain ("HyperFrames CLI development loop") and enumerates many concrete actions/commands (init, add, catalog, capture, lint, check, snapshot, compare, render, cloud, lambda, etc.), giving comprehensive coverage rather than vague abstraction.	5 / 5
Completeness	Explicitly answers both what ("Use the HyperFrames CLI development loop: ...") and when ("Also use when diagnosing build or render failures") with concrete trigger phrases and an explicit Use-when clause.	5 / 5
Trigger Term Quality	Covers natural command-name triggers users actually say (render, preview, lint, check, doctor), scenario phrasing ("diagnosing build or render failures"), and synonyms/deprecated aliases (validate/inspect/layout → check), including hosting variants.	5 / 5
Distinctiveness Conflict Risk	The HyperFrames-specific command vocabulary and scenario triggers carve a clear niche with minimal overlap risk against other 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
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: heygen-com/hyperframes
Path: skills/hyperframes-cli/SKILL.md
Commit: 0f8eb89

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.