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

66%

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.

The body is highly actionable and well-sequenced with real HeyGen API specifics and approval checkpoints, but it is verbose in the discovery/script-coaching sections and monolithic with no progressive disclosure to separate reference files. Strong on execution guidance, weaker on token efficiency and file structure.

Suggestions

Move stable reference content (style presets, cost reference, supported output types, avatar/voice catalog commands) into separate files under references/ and link to them one level deep to improve progressive disclosure.

Trim the discovery section: replace the full quoted dialog scripts for each mode with compact templates, and drop the 'Why it matters' rationale columns that re-explain concepts Claude already knows.

Add an explicit failure-handling feedback loop in the polling step (what to do on 'failed' status or HTTP 429) and a single end-to-end runnable example to close the workflow-clarity and actionability gaps.

Dimension	Reasoning	Score
Conciseness	Mostly efficient domain-specific content, but padded with full discovery dialog scripts for three modes, 'Why it matters' rationale columns, and spoken-word writing coaching ('Short sentences', 'Rhetorical questions work well') that Claude largely already knows.	3 / 5
Actionability	Provides concrete curl commands, scene-composition JSON, an AVATAR-CONFIG.md template, and exact endpoints, with minor gaps: the voice config shows only the 'text' type, payloads use placeholders, and there is no single end-to-end runnable example.	4 / 5
Workflow Clarity	Steps 1-10 are clearly sequenced with an approval gate before the expensive generation step (Full Producer) and avatar preview confirmation; minor gaps include no explicit failure-handling feedback loop in polling and Quick Shot skipping approval.	4 / 5
Progressive Disclosure	The skill is a monolithic 671-line SKILL.md with no bundle files and zero external references; reference-style content (style presets, cost tables, API catalog, supported output types) is inlined. Headers are well-organized but the file far exceeds the under-50-line exception.	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.

The description clearly conveys what the skill does with concrete, domain-specific actions and distinct triggers, but it lacks an explicit 'Use when...' trigger clause, capping completeness. Overall a strong, specific description with one notable gap.

Suggestions

Add an explicit 'Use when...' trigger clause naming natural user phrases, e.g. 'Use when the user wants a talking head / narrated video from a changelog, docs page, blog post, or notes.'

Surface voice selection and asset upload as capabilities so the action coverage reads as comprehensive rather than having minor gaps.

Include common synonyms users might say ('narrated video', 'avatar video', 'explainer video') alongside 'talking head video' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Creates talking head videos', 'Produces multi-scene videos with avatar narration over screenshots/images', 'using HeyGen v2 API', 'Supports Quick Shot and Full Producer modes') with only minor gaps (voice selection and asset upload not surfaced).	4 / 5
Completeness	The 'what' is clearly answered but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Natural terms users would say are present ('talking head videos', 'docs, changelogs, blog posts, notes, transcripts') plus mode names; a few synonyms like 'narrated video' or 'explainer' are missing.	4 / 5
Distinctiveness Conflict Risk	'Talking head videos' produced via the 'HeyGen v2 API' is a clear niche with distinct triggers and minimal conflict risk with other 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: 2523432

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.