talking-head-recut

Package an existing talking-head / interview / podcast video with timed, designed GRAPHIC OVERLAY cards — kinetic titles, lower-thirds, data callouts, quotes, side panels, picture-in-picture — synced to the transcript, on a 16:9 / 9:16 / 4:5 canvas of your choice; the clip plays untouched underneath. Trigger on "graphic overlays", "on-screen graphics", "package / dress up my video". Not plain subtitles (/embedded-captions). Unclear → /hyperframes.

Quality

85%

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

78%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 highly actionable with a well-sequenced workflow and exemplary progressive disclosure into verified reference files. Its main weakness is conciseness: repeated bounds tables and verbose user-question copy add tokens without adding clarity.

Suggestions

Consolidate the zone/bounds table into one canonical location (Step 6) and have Steps 7 and 9 reference it instead of re-listing the same bounds.

Compress the Channel A AskUserQuestion option labels/descriptions to one-line summaries; the full rationales can live in DESIGN_INDEX.md.

Add an explicit validate→fix→retry loop after the Step 10 snapshot (e.g. "if the snapshot shows a frozen frame or overlap, fix card bounds/GSAP targets and re-snapshot before the full render") to lift workflow clarity to 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient concrete commands and templates, but the zone/bounds table recurs across Steps 6, 7, and 9 and the AskUserQuestion option descriptions are verbose, so it could be tightened (3 anchor).	3 / 5
Actionability	It provides copy-paste-ready ffprobe/ffmpeg/hyperframes commands, a full composition HTML template, a GSAP statement cheat sheet, and a concrete storyboard schema example, matching the fully-executable 5 anchor.	5 / 5
Workflow Clarity	An 11-step numbered workflow with checkpoints (hyperframes doctor, snapshot sanity render, QA rules checklist) fits the 4 anchor; it stops short of 5 because there is no explicit validate→fix→retry error-recovery loop.	4 / 5
Progressive Disclosure	The SKILL.md is a clear overview pointing to one-level-deep, well-signaled references (DESIGN_INDEX.md plus styles/layouts/frames directories), all of which exist, matching the 5 anchor.	5 / 5
	Total	17 / 20 Passed

Description

92%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 concrete, trigger-rich, and explicitly answers both what and when while actively disambiguating from sibling skills. The only minor gap is the absence of file-extension triggers like .mp4, which keeps trigger term quality at 4.

Dimension	Reasoning	Score
Specificity	"Package an existing talking-head / interview / podcast video with timed, designed GRAPHIC OVERLAY cards — kinetic titles, lower-thirds, data callouts, quotes, side panels, picture-in-picture" lists multiple concrete overlay types with comprehensive coverage, matching the 5 anchor.	5 / 5
Completeness	It states both what (package a clip with designed graphic cards on a chosen canvas) and when ("Trigger on 'graphic overlays', 'on-screen graphics', 'package / dress up my video'") with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	Natural triggers are present ("graphic overlays", "on-screen graphics", "package / dress up my video", talking-head/interview/podcast) but file extensions like .mp4 are absent, so it falls just below the comprehensive-synonyms 5 anchor.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche and explicitly disambiguates ("Not plain subtitles (/embedded-captions). Unclear → /hyperframes"), minimizing conflict risk per the 5 anchor.	5 / 5
	Total	19 / 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
skill_md_line_count	SKILL.md is long (1212 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: heygen-com/hyperframes
Path: skills/talking-head-recut/SKILL.md
Commit: a562946

Reviewed: about 10 hours 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.