member-skill-distiller

Distill team members from profile, files, and YouTube subtitles into session-activated member skills.

Quality

66%

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 ./desktop/builtin-skills/member-skill-distiller/SKILL.md

Quality

Content

80%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 content is admirably concise and well-structured for a short instruction-only skill, with concrete output requirements. Its main weakness is workflow clarity: it lists constraints rather than a sequenced compilation process with validation checkpoints.

Suggestions

Add a short numbered workflow (e.g., 1. gather profile/subtitles, 2. extract persona and knowledge boundaries, 3. emit the skill package) to make the process explicit.

Include a validation/check step, such as verifying the generated skill activates via session metadata and contains all required fields before finishing.

Provide one minimal example of a generated member skill so the expected output shape is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is lean with no padding and no explanation of concepts Claude already knows; every bullet earns its place and assumes Claude's competence.	5 / 5
Actionability	Concrete, specific guidance is given — an explicit field list (member id, source type, preferred language, persona, system prompt, evidence summary) and clear separation of concerns — but no concrete example of a generated skill and the actual compilation steps remain abstract, leaving minor gaps.	4 / 5
Workflow Clarity	The Contract and Output Requirements state constraints rather than a sequenced process, so the workflow is only implicit with no explicit steps or validation checkpoints.	3 / 5
Progressive Disclosure	The skill is under 50 lines, requires no external references (no references/scripts/assets bundle exists), and is organized into clear sections (Contract, Output Requirements), satisfying the simple-skill exception for a top score.	5 / 5
	Total	17 / 20 Passed

Description

53%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 conveys a clear, specific purpose with concrete input sources and output, but it omits any 'when to use' trigger guidance and leans on some technical jargon. It sits at a mid-range score, strongest on distinctiveness and weakest on completeness.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when the user wants to turn a teammate's profile or YouTube talks into a reusable skill').

Replace or gloss the jargon 'session-activated member skills' with plain-language terms a user would actually say.

List 1-2 more concrete actions (e.g., 'extracts speaking style and knowledge boundaries') to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain and concrete input sources ('profile, files, and YouTube subtitles') plus the output ('session-activated member skills'), but the only action verb is 'Distill', so coverage is not comprehensive.	3 / 5
Completeness	It clearly states what the skill does ('Distill team members ... into session-activated member skills') but provides no 'Use when...' clause, so the 'when' is missing — capping completeness at 3 per the guidelines.	3 / 5
Trigger Term Quality	Terms like 'team members', 'profile', and 'YouTube subtitles' are somewhat natural, but 'session-activated member skills' is jargon and common variations/synonyms are missing.	3 / 5
Distinctiveness Conflict Risk	The niche (compiling team members into activated skill packages from specific sources) is fairly distinct with limited overlap risk, though the lack of explicit trigger phrases keeps it just short of a 5.	4 / 5
	Total	13 / 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: Jamailar/Beav
Path: desktop/builtin-skills/member-skill-distiller/SKILL.md
Commit: 0c95e8e

Reviewed: 1 day 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.