scientific-podcast-summary

Automatically summarize scientific podcasts like Huberman Lab and Nature.

Quality

58%

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

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Evidence Insight/scientific-podcast-summary/SKILL.md

Quality

Content

56%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 actionable and reasonably well-sequenced, but it is padded with generic governance boilerplate and duplicated sections that hurt token efficiency and keep progressive disclosure middling. Trimming the boilerplate and splitting reference-worthy material into bundled files would improve it.

Suggestions

Remove or relocate the generic governance boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template) into a separate reference file to improve conciseness and progressive disclosure.

Delete redundant cross-reference sections ('See ## Usage above', 'See ## Workflow above', duplicated py_compile commands) and consolidate Installation/Prerequisites.

Add a concrete technical validation checkpoint in the Workflow tied to the actual fetch/summarize/write operations (e.g. verify transcript extraction succeeded before calling the LLM) to move workflow_clarity toward 5.

Dimension	Reasoning	Score
Conciseness	The 268-line body carries substantial governance boilerplate (Risk Assessment, 12-item Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template) plus redundant cross-references ('See ## Usage above', 'See ## Workflow above') and duplicated compile commands, fitting 'noticeably verbose; several unnecessary explanations or padded sections'; it avoids a 1 because it does not lecture on basic concepts Claude already knows.	2 / 5
Actionability	It provides concrete executable commands in the Usage block, a complete Arguments table, Environment Variables, and a copy-paste Example Output, giving mostly executable guidance; it is not a 5 because some example paths are soft placeholders and the actionable core is diluted by boilerplate.	4 / 5
Workflow Clarity	The Workflow section is a clear five-step sequence with an explicit stop-early validation check and a documented fallback path, plus a Quick Check compile step, matching 'clear sequence with most checkpoints present'; it is not a 5 because the checkpoints are process-level rather than concrete technical validations tied to the fetch/summarize/write operations.	4 / 5
Progressive Disclosure	There is one clearly signaled one-level reference (references/audit-reference.md) and clear section headers, but large blocks that could live in separate files (Security Checklist, Example Output, Risk Assessment) are inlined, fitting 'some structure but content that should be separate is inline'; it is not a 4 because the inlined governance material is substantial.	3 / 5
	Total	13 / 20 Passed

Description

61%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 clear about what it does and names a specific niche, but it omits an explicit 'Use when...' trigger clause, capping completeness. Adding trigger phrases and one or two more concrete actions would lift it.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when the user asks to summarize or recap a Huberman Lab or Nature podcast episode.'

List one or two more concrete actions (e.g. 'extract key findings', 'generate Markdown or JSON briefings') to move specificity from 3 toward 4-5.

Include common synonyms users say ('recap', 'episode notes') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('scientific podcasts like Huberman Lab and Nature') and one concrete action ('summarize'), matching the 'names domain and 1-2 concrete actions but not comprehensive' anchor; it is not a 2 because it names specific shows rather than minimal/generic actions, and not a 4 because only the single action 'summarize' is given.	3 / 5
Completeness	It clearly answers 'what' ('Automatically summarize scientific podcasts...') but provides no 'when/Use when...' trigger clause, so per the boundary guidance a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	It includes natural terms users would say ('Huberman Lab', 'Nature', 'scientific podcasts', 'summarize'), giving good keyword coverage; it stops short of 5 because common synonyms like 'recap', 'episode notes', or 'transcribe' are missing.	4 / 5
Distinctiveness Conflict Risk	The named shows and 'scientific podcasts' niche make it mostly distinct with only minor overlap risk against a general podcast-summary skill; it is not a 5 because the trigger is generic enough that a broader podcast skill could still compete.	4 / 5
	Total	14 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/scientific-podcast-summary/SKILL.md
Commit: 63c61d3

Reviewed: 5 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.