podcast-generation

Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/public/podcast-generation/SKILL.md

Quality

Content

68%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 highly actionable with executable commands and a full example, and is reasonably well structured. It loses points for redundant sections (the JSON schema and several notes are repeated) and for lacking a validation checkpoint in a batch audio-generation workflow; it also references a template file that is missing from the bundle.

Suggestions

De-duplicate the script JSON schema: keep it in one place ('Script JSON Format') and reference it from Step 2 instead of repeating it.

Add a verification checkpoint after generation (e.g. confirm the MP3 and transcript files exist and are non-empty, with retry guidance if the script reports an error) to satisfy the batch-operation feedback-loop requirement.

Either ship templates/tech-explainer.md or remove the dangling link under 'Specific Templates' so every referenced file resolves.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but padded: the script JSON structure appears twice (Step 2 and the 'Script JSON Format' section), 'Hello Deer' and output/notes guidance are repeated across overlapping sections, and Notes restate earlier rules.	3 / 5
Actionability	Provides a fully executable python invocation with all required and optional flags, a concrete JSON schema, and a complete copy-paste-ready worked example covering the common case.	5 / 5
Workflow Clarity	The three steps are clearly sequenced, but this is a batch audio-generation operation with no validation/verification checkpoint (the skill even tells Claude not to split the workflow), and Output Handling lacks any error-recovery feedback loop, so the batch-operation cap applies.	3 / 5
Progressive Disclosure	Good sectioning with a one-level-deep conditional reference to templates/tech-explainer.md that is clearly signaled; however that referenced file is absent from the bundle, a minor organization gap that keeps it below 5.	4 / 5
	Total	15 / 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.

The description is strong: it names concrete actions, supplies natural trigger verbs, and explicitly covers both what the skill does and when to use it. Minor specificity gaps (generic 'text content', no audio/file-extension terms) keep a couple dimensions at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('generate, create, or produce podcasts', 'Converts written content into a two-host conversational podcast audio format') but leaves input scope generic as 'text content', a minor coverage gap versus score 5.	4 / 5
Completeness	Explicitly answers both 'what' ('Converts written content into a two-host conversational podcast audio format with natural dialogue') and 'when' ('Use this skill when the user requests to generate, create, or produce podcasts') with concrete trigger phrases, paralleling a good_overall example.	5 / 5
Trigger Term Quality	Covers natural user verbs with synonyms (generate/create/produce podcasts) and 'from text content', good coverage but missing a few natural terms like 'audio' or file extensions that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	'podcasts from text content' and 'two-host conversational podcast audio' carve a clear niche with distinct, low-conflict triggers unlikely to fire for unrelated skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: bytedance/deer-flow
Path: skills/public/podcast-generation/SKILL.md
Commit: 0d49253

Reviewed: 5 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.