CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

video-podcast-maker-nano

Smallest personal narrated-explainer-video pipeline (spoken narration over visuals, not an audio podcast), fully tool-agnostic and autonomous by default — topic → research ∥ asset collection → script → TTS → video → 4K render ∥ publish info + cover. The skill defines the pipeline logic and self-verified checkpoints; any TTS backend and any video tool (Remotion, HyperFrames, CapCut, ...) work, and how much human oversight to apply is set by the working project's AGENTS.md/CLAUDE.md, not here. Use when the user wants a quick personal narrated video with minimal steps, whether or not they name the tool stack. Do NOT trigger for audio-only podcasts, written episodic content, or heavy multi-format production.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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.

A well-engineered, tool-agnostic pipeline skill with excellent workflow sequencing and embedded validation checkpoints. Its main weakness is progressive disclosure: it references bundle files (AGENTS.template.md, canonical reference docs) that do not exist in the skill directory, leaving those pointers dangling.

Suggestions

Either include the referenced `AGENTS.template.md` in the bundle or remove/descope the reference so users are not pointed at a missing file.

Resolve the provenance pointer to `video-podcast-maker/references/natural-narration.md` and `script-polish.md`: ship local copies or rephrase so the Script style section stands alone without relying on an external skill.

Tighten the Oversight policy and Tool selection sections (e.g., collapse the three per-checkpoint bullet variants) to recover tokens without losing the decision logic.

DimensionReasoningScore

Conciseness

Dense and free of basic-concept padding, with every section earning its place; a few policy passages (oversight, tool-selection rules) could be tightened without losing clarity.

4 / 5

Actionability

Provides concrete commands (`ffprobe`, `ffmpeg -ss <mid-section-time> -i draft.mp4 -frames:v 1`, `silencedetect`/`volumedetect`), a ±0.5s threshold, and a marker syntax, but much guidance remains policy/logic rather than copy-paste code, appropriate for a tool-agnostic skill.

4 / 5

Workflow Clarity

A clearly sequenced 7-step pipeline with three explicit checkpoints, self-verification criteria, fix-and-re-verify feedback loops, and a dedicated Iterating section — exemplary sequencing and validation.

5 / 5

Progressive Disclosure

Well-organized into clearly headed sections and largely self-contained; minor gaps are references to non-bundled files (`AGENTS.template.md`, external `video-podcast-maker/references/...`) that are not present in the bundle.

4 / 5

Total

17

/

20

Passed

Description

92%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, specific description that names concrete pipeline stages, gives explicit trigger guidance, and draws clear boundaries against adjacent skills. It could add a couple more natural synonyms (voiceover, tutorial) but is otherwise comprehensive.

DimensionReasoningScore

Specificity

Lists multiple concrete pipeline actions — 'research ∥ asset collection → script → TTS → video → 4K render ∥ publish info + cover' — covering the full workflow comprehensively.

5 / 5

Completeness

Explicitly answers both what (the 7-stage pipeline) and when ('Use when the user wants a quick personal narrated video with minimal steps'), with concrete trigger phrasing.

5 / 5

Trigger Term Quality

Includes natural phrases like 'quick personal narrated video', 'explainer-video', and 'minimal steps' plus negative triggers, but misses common synonyms such as 'voiceover' or 'tutorial' video.

4 / 5

Distinctiveness Conflict Risk

Clear niche — personal narrated explainer video — reinforced by an explicit anti-trigger ('Do NOT trigger for audio-only podcasts, written episodic content, or heavy multi-format production'), minimizing conflict risk.

5 / 5

Total

19

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

14

/

16

Passed

Repository

Agents365-ai/video-podcast-maker

Path

skills/video-podcast-maker-nano/SKILL.md

Revision

33b8078

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill