talking-head-video

Creates talking head videos from any source material (docs, changelogs, blog posts, notes, transcripts). Produces multi-scene videos with avatar narration over screenshots/images using HeyGen v2 API. Supports Quick Shot and Full Producer modes.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/design/packs/video-production/talking-head-video/SKILL.md

Quality

Content

63%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 production workflow with concrete API details throughout. Its weaknesses are length and monolithic structure: large self-contained sections (avatar setup, style presets, cost tables) belong in reference files, which would also tighten the core SKILL.md.

Suggestions

Move the avatar/voice first-run setup flow, the visual style preset table, the cost reference, and the avatar/voice catalog commands into reference files (e.g. references/avatar-setup.md, references/style-presets.md) linked from the body.

Trim the scripted discovery dialogue blocks and the "Why it matters" column of the discovery table to their essential decision content.

Add validation checkpoints: verify the asset upload response before composing scenes, and handle a non-completed video_status (e.g. failed) during polling.

Dimension	Reasoning	Score
Conciseness	The ~660-line body is mostly skill-specific operational detail (endpoints, presets, costs) rather than explanations of known concepts, but it is padded in places — full scripted dialogue blocks, "Why it matters" table columns, a 10-row style preset table — and could be meaningfully tightened.	3 / 5
Actionability	Copy-paste curl commands, exact endpoints, JSON payload structures, polling intervals, and known-good default avatar/voice IDs make the main generation path fully executable; minor gaps remain in the first-run flows (avatar-creation request bodies and the consent-verification flow are underspecified).	4 / 5
Workflow Clarity	Ten clearly sequenced steps with mode detection up front, an explicit user approval gate before the expensive render, and a poll-to-completion loop with a post-delivery adjust/regenerate offer; minor validation gaps (no check that asset upload succeeded, no handling of a failed video_status) keep it below a 5.	4 / 5
Progressive Disclosure	No bundle files exist and everything — avatar setup flow, style presets, cost reference, avatar/voice catalog commands — is inlined in one monolithic SKILL.md; section headers give it structure, but content that clearly belongs in separate reference files is inline with no references at all.	3 / 5
	Total	14 / 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.

A specific, distinctive description that clearly conveys what the skill produces and on what inputs. Its main weakness is the absent "when to use" trigger clause, which both limits completeness and leaves invocation guidance only implied.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to turn docs, changelogs, blog posts, or notes into a narrated video, or mentions HeyGen, talking head videos, or explainer videos."

Include a few natural synonym trigger terms users would actually say ("make a video", "avatar video", "video walkthrough") alongside the current source-material list.

Dimension	Reasoning	Score
Specificity	"Creates talking head videos from any source material (docs, changelogs, blog posts, notes, transcripts). Produces multi-scene videos with avatar narration over screenshots/images using HeyGen v2 API" lists several concrete actions with named inputs and a named API, but omits capabilities like avatar/voice setup and output formats, leaving minor gaps in coverage.	4 / 5
Completeness	The "what" is explicit and concrete (multi-scene avatar-narrated videos via HeyGen v2), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Natural terms like "talking head videos", "changelog", "blog post", and "HeyGen" give good keyword coverage, but common variations users would say — "make a video", "explainer video", "avatar video" — are missing.	4 / 5
Distinctiveness Conflict Risk	"Talking head videos ... using HeyGen v2 API" carves out a clear niche with distinct triggers (talking head, HeyGen, changelog video) and minimal conflict risk with generic media or documentation skills.	5 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (672 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: gooseworks-ai/goose-skills
Path: skills/design/packs/video-production/talking-head-video/SKILL.md
Commit: cc3e518

Reviewed: 7 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.