CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

hyperframes-cli

HyperFrames CLI - scaffold, check frames, edit timelines, preview, render, share and project history; read JSON and recover from failures.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 body is an exemplary CLI skill: lean command tables, copy-paste-ready invocations, and a tightly sequenced workflow with validation and recovery at every step. Bundle structure matches the reference table exactly, making navigation trivial. No material weaknesses found.

DimensionReasoningScore

Conciseness

The body is lean and telegraphic — dense command tables ("Commands by job", "Render where", "When a command fails") with zero explanation of concepts Claude already knows; every line carries operational information. Not 4 because there is no over-explanation to trim; even behavioral notes (usage beacon, updateNotice) are actionable instructions, not padding.

5 / 5

Actionability

Fully executable, copy-paste-ready commands with exact flags throughout: `render --quality looks -o out.mp4`, `timeline apply plan.json --json` with a concrete JSON edit-file example, the `until grep -qE 'Render (complete|failed)' render.log; do sleep 5; done` wait loop, and a symptom→fix failure table. Not 4 because the commands cover the common cases with specific flags and outputs, leaving no significant gaps.

5 / 5

Workflow Clarity

"The loop" gives a clear 5-step sequence with explicit validation checkpoints (lint after first pass, `check --json` fix every error, read snapshot PNGs, preview URL must answer 200, confirm non-empty render with ffprobe duration matching data-duration), plus feedback loops for recovery (failure table, `--plan` previews before edits, `clean --dry-run` before `clean`, `history undo`). Not 4 because validation is explicit at every step, including for the destructive `clean` and edit operations.

5 / 5

Progressive Disclosure

A ~100-line overview keeps SKILL.md as a map: a References table ("Read the row before running its command") routes each command group to one-level-deep reference files, and all 12 local references (init-and-scaffold, lint-validate-inspect, preview-render, cloud, lambda, etc.) exist in the bundle. Not 4 because the split is appropriate and navigation is explicit; the few ../hyperframes cross-skill links are clearly signaled plugin-level references.

5 / 5

Total

20

/

20

Passed

Description

70%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 specific and clearly anchored to a distinct named tool, but it lacks any 'Use when...' trigger guidance, capping its completeness, and it omits the media/audio and cloud-rendering halves of the skill's coverage. Adding an explicit usage clause and the video/animation nouns users would actually say would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when working with HyperFrames projects, or when the user mentions rendering a video, editing a timeline, or previewing an animation."

Include the media/audio jobs (transcribe, captions, tts, beats) and cloud rendering in the action list so the 'what' matches the body's actual coverage.

Add natural nouns and synonyms users would say — "video", "animation", "slideshow", "captions", "audio" — to improve trigger term coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions ("scaffold, check frames, edit timelines, preview, render, share and project history; read JSON and recover from failures"), matching the several-specific-actions anchor. Not 5 because coverage has gaps — the body's media/audio jobs (tts, transcribe, beats, remove-background) and cloud rendering are absent; not 3 because it goes well beyond 1-2 actions.

4 / 5

Completeness

The 'what' is clear (scaffold, check, edit timelines, preview, render, share, history, JSON, failure recovery) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4 because 'when' is not even weakly implied by a usage context.

3 / 5

Trigger Term Quality

Good keyword coverage with natural verbs users would say ("scaffold", "edit timelines", "preview", "render", "share", "project history"), fitting the good-coverage anchor. Not 5 because it misses core nouns and synonyms a user would naturally say — "video", "animation", "captions", "audio" — and no file extensions; not 3 since the term list is broader than 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

"HyperFrames CLI" names a specific tool with a clear niche and distinct actions (timelines, frames, renders, project history), giving minimal conflict risk with other skills. Not 4 because no overlapping skill domain is plausibly triggered by these terms.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

heygen-com/hyperframes

Path

skills/hyperframes-cli/SKILL.md

Reviewed

Table of Contents

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.