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

88%

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

81%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 a well-engineered orchestrator: clearly sequenced steps with gates, concrete commands, validation, and error-recovery guidance. It is slightly verbose from restatement and leans on external sibling-skill references for deep detail, but it is highly actionable and the workflow is unambiguous.

Suggestions

Consolidate the repeated 'faceless = no capture / no asset inventory' guidance into one canonical statement (e.g., the Quick Reference deltas) and reference it rather than restating it in Steps 0, 1, and the gates.

Move the dense voice-selection logic in Step 3.1 and the caption false-positive workaround in Step 6 into their respective reference files, keeping the step body to the command and a one-line pointer.

Resolve or constrain placeholders (<voice-id>, <frame-midpoints>) with a concrete lookup step or example so the commands are copy-paste-ready without external resolution.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's intelligence (no concept explanations), but several points are restated across steps — 'faceless means no capture' and the public/<basename> exception each appear multiple times — so it is efficient with minor trim opportunities rather than fully lean.	4 / 5
Actionability	Concrete, executable commands and exact file paths appear per step (init, build-frame, audio.mjs, lint/check/snapshot), but placeholders like <voice-id> and <frame-midpoints> and reliance on external sibling-skill docs for deep detail keep it just short of fully copy-paste-ready.	4 / 5
Workflow Clarity	A clear 7-step sequence with an explicit gate after each step, validation commands, an error-recovery loop ('surface stderr and stop ... fix it yourself ... rerun the failed check'), and a known-false-positive note together match the anchor for explicit checkpoints and feedback loops.	5 / 5
Progressive Disclosure	A well-signaled Quick Reference table ('Read \| When') plus inline per-step pointers to real local references and scripts give good one-level-deep structure, but reference sprawl into sibling skills outside the bundle and some inline detail that could live in references (the voice-selection and false-positive paragraphs) keep it at good rather than exemplary.	4 / 5
	Total	17 / 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.

The description is strong: it states a concrete capability, gives natural trigger terms, answers both what and when, and explicitly distinguishes itself from sibling skills with routing guidance. The only minor gap is specificity, where one core action is elaborated rather than a broad multi-action list.

Dimension	Reasoning	Score
Specificity	Names the domain and enumerates several concrete visual treatments ('typography, abstract graphics, diagrams, data-viz'), but the core is a single transformation rather than a comprehensive multi-action list, so it sits just below the 5 anchor.	4 / 5
Completeness	Explicitly answers both what ('Turn arbitrary text ... into a faceless explainer video') and when ('Use for topic explainers, concept breakdowns, how-tos, listicles') with concrete trigger phrases, matching the anchor-5 pattern.	5 / 5
Trigger Term Quality	Natural trigger phrases a user would actually say ('topic explainers, concept breakdowns, how-tos, listicles') plus input phrasings ('an article, notes, a topic, a brief') give comprehensive coverage with synonyms.	5 / 5
Distinctiveness Conflict Risk	A clear niche ('faceless', 'no site or footage to capture') is carved out with an explicit boundary against /product-launch-video and routing for unclear cases to /hyperframes, minimizing 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: 0f8eb89

Reviewed: 6 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.