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

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is highly actionable with concrete API guidance and a clear step sequence, but it is a lengthy monolithic document with redundancy and lacks validation/error-recovery feedback loops for its expensive async generation workflow.

Suggestions

Move the detailed avatar setup flow, style preset table, and cost reference into separate reference files (e.g., references/avatar-setup.md, references/style-presets.md) and keep SKILL.md as an overview with one-level-deep links.

Add a validation checkpoint before submitting the generation request and an error-recovery loop for failed poll status / HTTP 429, since video generation is costly and asynchronous.

Tighten the Discovery section by consolidating the questions table, per-mode scripts, and answer-to-decision mapping to remove triplicated content.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient operational detail, but it is ~660 lines with notable redundancy — discovery is covered three times (questions table, per-mode scripts, and answer-to-decision mapping) and the avatar setup flow is heavily padded with full dialogue quotes.	2 / 3
Actionability	Provides copy-paste-ready guidance: exact curl commands, complete JSON payloads with real field names, precise endpoints (including the separate upload.heygen.com host), known-good avatar/voice IDs, and concrete script templates.	3 / 3
Workflow Clarity	A clear 10-step sequence with a Full Producer approval gate exists, but there is no payload validation checkpoint before submission and no error-recovery feedback loop for the costly asynchronous generation step (e.g., handling a failed status or HTTP 429).	2 / 3
Progressive Disclosure	Content is well-organized into sections but is a single monolithic file with no bundle references; large API reference detail, the 10-preset style table, the avatar setup flow, and cost reference are all inline when they could be split into separate reference files.	2 / 3
	Total	9 / 12 Passed

Description

67%

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, concrete, and clearly distinct, but it omits any explicit 'when to use' trigger guidance, which limits its completeness and trigger-term coverage.

Suggestions

Add an explicit 'Use when...' clause listing natural trigger scenarios (e.g., 'Use when the user wants a narrated/explainer video from docs, a changelog, blog post, or notes').

Broaden trigger terms to include common user phrasings like 'narrated video', 'explainer video', or 'video walkthrough' alongside 'talking head video'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in third person — 'Creates talking head videos', 'Produces multi-scene videos with avatar narration over screenshots/images', 'Supports Quick Shot and Full Producer modes' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Clearly answers 'what' the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Contains relevant keywords ('talking head videos', 'docs, changelogs, blog posts, notes, transcripts') but misses common natural variations a user might say ('narrated video', 'explainer video', 'video walkthrough') and lacks explicit trigger phrasing.	2 / 3
Distinctiveness Conflict Risk	The niche is narrow and specific — HeyGen v2 API talking-head videos with avatar narration — making it unlikely to conflict with or wrongly trigger for other skills.	3 / 3
	Total	10 / 12 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: 8866b2a

Reviewed: 1 day 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.