faceless-explainer

Turn arbitrary text — an article, notes, a topic, a brief — into a faceless explainer video: there is no site or footage to capture, so the visuals are invented per scene (typography, abstract graphics, diagrams, data-viz). Use for topic explainers, concept breakdowns, how-tos, listicles. Not a video built from a website (/product-launch-video — promo or tour). Unclear → /hyperframes.

Quality

91%

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

88%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 well-engineered orchestrator skill: concrete executable commands, explicit per-step gates, and real error-recovery feedback loops. Conciseness is good but has some verbose passages, and progressive disclosure is strong locally though many cross-skill reference paths are not present in the bundle.

Suggestions

Tighten the long compound sentences in Step 0's opening rule and Step 3.1's voice-selection paragraph into shorter declaratives or a small list to lift conciseness toward 5.

For progressive disclosure, either inline a one-line summary of what each missing cross-skill reference (../hyperframes-core, ../hyperframes-creative, ../hyperframes-animation, ../media-use, sub-agents/frame-worker.md) provides, or confirm those sibling skills ship alongside this one so the cited paths resolve.

Consider moving the dense Step 3.1 voice-resolution logic into references/tts-voice-selection.md and leaving a concise decision rule inline, reducing body length while preserving actionability.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational, not padded with concepts Claude already knows (no "what is a video" filler), and every step earns its place via concrete gates; held below 5 by several long compound sentences and verbose parentheticals (e.g., Step 0's opening rule, Step 3.1's voice-selection paragraph) that could be tightened.	4 / 5
Actionability	Provides copy-paste-ready commands with exact paths and flags (e.g., `npx hyperframes init "videos/<project>" --non-interactive --example=blank --skill=faceless-explainer`, `node <SKILL_DIR>/scripts/build-frame.mjs --preset <name> --hyperframes .`) and explicit per-step file artifacts, covering the common cases fully.	5 / 5
Workflow Clarity	Steps 0–6 are clearly sequenced, each with an explicit Gate: checkpoint, and Step 6 includes a validate→fix→rerun feedback loop ("If a command fails, surface stderr and stop... Fix it yourself... then rerun the failed check") plus lint/check/snapshot validation, satisfying the destructive/batch feedback-loop requirement.	5 / 5
Progressive Disclosure	The Quick Reference read→when table and one-level-deep local references (story-design.md, visual-design.md, motion-language.md, cut-catalog.md — all verified present) give good navigation; held below 5 because the bulk of cited paths (../hyperframes-core/, ../hyperframes-creative/, ../hyperframes-animation/, ../media-use/, sub-agents/frame-worker.md) do not resolve in this bundle and the orchestrator body is fairly dense for an overview.	4 / 5
	Total	18 / 20 Passed

Description

95%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 high-quality description that clearly states what it does, when to use it, and how it differs from adjacent video skills. The only mild gap is that the action list is a single primary verb enriched with enumerated visual/input types rather than several distinct operations.

Dimension	Reasoning	Score
Specificity	Names the concrete action ("Turn arbitrary text ... into a faceless explainer video") and enumerates specific invented-visual types (typography, abstract graphics, diagrams, data-viz) and input types (article, notes, topic, brief); falls short of 5 because the action set is essentially one primary verb with detailed sub-elements rather than multiple distinct actions like the 5-anchor example.	4 / 5
Completeness	Explicitly answers both "what" (turn text into a faceless explainer video with invented visuals) and "when" ("Use for topic explainers, concept breakdowns, how-tos, listicles") with concrete trigger phrases, matching the 5-anchor example structure.	5 / 5
Trigger Term Quality	Comprehensively lists the natural phrases users say ("topic explainers, concept breakdowns, how-tos, listicles") plus input forms (article, notes, topic, brief); no file extension applies to a video skill, and the explicit disambiguation routing ("Unclear → /hyperframes") adds trigger clarity.	5 / 5
Distinctiveness Conflict Risk	Carves a clear niche (faceless, no capture) and explicitly disambiguates from a sibling skill ("Not a video built from a website (/product-launch-video — promo or tour)") with an uncertainty escape hatch ("Unclear → /hyperframes"), giving minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing, 12 suspicious	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: heygen-com/hyperframes
Path: skills/faceless-explainer/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.