CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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 highly actionable, gate-driven orchestration workflow with exact commands, explicit validation and error-recovery loops, and well-signaled progressive disclosure into reference files. The weaknesses are modest: some redundant restatement in the opening sections and one or two bundle/reference inconsistencies (missing sub-agents file, incomplete background-scripts list).

Suggestions

Deduplicate the opening: 'You are the orchestrator' and the routing rules are stated twice before Step 0 — fold them into one statement and let Step 0's opening rule carry the routing detail.

Add `sub-agents/frame-worker.md` to the bundle (or fix the path), since Step 5 and the packet builder treat it as the frame-worker role delta.

Include `frame-packets.mjs` in the Quick Reference's 'Background scripts' list so the shipped-scripts inventory matches what Step 5 actually invokes.

DimensionReasoningScore

Conciseness

The body is dense, imperative, and free of concepts Claude already knows, but carries minor redundancy that could be trimmed: "You are the orchestrator" is stated twice in the opening paragraphs, and the front-door/routing rules are restated across the intro and Step 0's opening rule. This matches the 'efficient; minor instances of over-explanation' anchor rather than the fully lean one.

4 / 5

Actionability

Every step carries exact, copy-paste-ready commands with concrete paths and flags (e.g. `npx hyperframes init "videos/<project>" --non-interactive --example=blank --skill=faceless-explainer`, `node <SKILL_DIR>/scripts/audio.mjs sync-durations --audio-meta ./audio_meta.json --storyboard ./STORYBOARD.md`), plus explicit expected artifacts and branch conditions covering the common cases.

5 / 5

Workflow Clarity

Steps 0–6 are strictly sequenced, user-gated steps are named up front, every step ends in an explicit **Gate**, and validation with a feedback loop is present (lint/check/snapshot, "If a command fails, surface stderr and stop — fix it yourself… then rerun the failed check", plus the documented `check` false-positive and the review loop's approve/revise cycle).

5 / 5

Progressive Disclosure

Structure is good: method detail is pushed to clearly signaled one-level-deep references with a Read/When table in the Quick Reference, and the four local `references/` files all exist. Minor gaps keep it below a 5: the locally-referenced `sub-agents/frame-worker.md` is absent from the bundle, and the Quick Reference's "Background scripts" list omits `frame-packets.mjs`, which Step 5 actually invokes.

4 / 5

Total

18

/

20

Passed

Description

87%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 strong description: concrete capability statement, explicit "Use for…" triggers with natural vocabulary, and crisp boundary/routing guidance against sibling skills. Its only softness is that the action list is one well-elaborated capability rather than a breadth of distinct operations.

DimensionReasoningScore

Specificity

The description names a concrete capability ("Turn arbitrary text — an article, notes, a topic, a brief — into a faceless explainer video") with concrete input types and visual modes ("typography, abstract graphics, diagrams, data-viz"), but the action coverage is really one capability elaborated in detail rather than multiple distinct actions, so it sits just below the comprehensive anchor.

4 / 5

Completeness

Both halves are explicit: the "what" is turning text into a faceless explainer video with invented visuals, and the "when" is a concrete "Use for topic explainers, concept breakdowns, how-tos, listicles" trigger clause, plus negative and uncertain-routing guidance ("Not a video built from a website… Unclear → /hyperframes").

5 / 5

Trigger Term Quality

Natural user phrasing is well covered — "topic explainers, concept breakdowns, how-tos, listicles", "explainer video", "article, notes, a topic, a brief" — matching the good anchor's keyword density, though a few common variants (e.g. "tutorial video", "voiceover video") are absent.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche — text-driven faceless explainers with invented visuals — and explicitly disambiguates from the nearest sibling ("Not a video built from a website (/product-launch-video — promo or tour)") with a fallback route for ambiguity, minimizing wrong-skill triggering.

5 / 5

Total

18

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing, 13 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

Reviewed

Table of Contents

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.