onboarding

Personalize COG for your workflow - creates profile, interests, and watchlist files with guided setup (run this first!)

Quality

72%

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 ./.claude/skills/onboarding/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is highly actionable with complete templates and a clear, validated workflow, but it is verbose and monolithic. Moving the large file templates into reference files and trimming repeated guidance and philosophy would improve both conciseness and progressive disclosure.

Suggestions

Extract the large file templates (welcome guide, profile, interests, watchlist, project overview) into separate files under references/ and link to them one level deep, reducing the main SKILL.md to an overview.

Remove repetition of the 'natural conversation, not a form' principle and condense the Philosophy and Privacy & Data sections to essential notes.

Keep the validated workflow and concrete templates intact, as these are the skill's strongest dimensions.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable but padded with repetition (the 'natural conversation, not a form' principle restated several times) and non-essential Philosophy/Privacy sections that restate benefits; it could be tightened significantly.	2 / 3
Actionability	Provides copy-paste-ready markdown templates for every generated file with full frontmatter, an explicit extraction rules table, exact directory structure, and concrete role-pack matching logic.	3 / 3
Workflow Clarity	A clear nine-step sequence with sub-steps, an explicit 'wait for confirmation' checkpoint before file generation, a success-criteria checklist, and error-handling/recovery feedback loops for profile-exists, directory failure, and mid-exit resume.	3 / 3
Progressive Disclosure	No bundle files exist and all large templates (welcome guide, profile, interests, watchlist, project overview) are inline in a ~550-line monolithic SKILL.md; section headings organize it, but content that should be separate reference files is inline.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 specific and distinct, naming concrete deliverables, but lacks explicit trigger guidance and broader natural-language keywords. Adding a 'Use when...' clause with terms like 'onboarding' and 'get started' would raise completeness and trigger quality.

Suggestions

Add an explicit 'Use when...' clause with trigger phrases users would actually say, e.g. 'Use when onboarding to COG, setting it up for the first time, or re-running setup.'

Broaden trigger terms to include natural variations like 'onboarding', 'get started', and 'configure COG'.

Keep the concise concrete-artifact list but pair it with the explicit when-trigger to satisfy completeness at level 3.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and artifacts ('creates profile, interests, and watchlist files with guided setup'), naming several specific deliverables rather than a vague domain.	3 / 3
Completeness	Clearly states what it does (creates profile/interests/watchlist files), but 'when' is only implied via '(run this first!)' with no explicit 'Use when...' trigger clause, capping completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Includes relevant natural terms ('Personalize COG', 'guided setup') but misses common variations a user would say like 'onboarding', 'get started', or 'configure COG'.	2 / 3
Distinctiveness Conflict Risk	The COG-specific niche and named artifacts (profile, interests, watchlist files) make it clearly distinguishable and unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (560 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: huytieu/COG-second-brain
Path: .claude/skills/onboarding/SKILL.md
Commit: dfbf9e9

Reviewed: 2 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.