onboarding

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

Quality

31%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/onboarding/SKILL.md

Quality

Content

27%

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

This skill is extremely comprehensive but suffers from severe verbosity - it reads more like a product specification document than a concise skill instruction. The inline templates (especially the ~80-line welcome guide) bloat the file enormously, and sections like 'Philosophy' and 'Privacy & Data' add no actionable value for Claude. The workflow is reasonably clear but lacks validation checkpoints after file/directory creation, and the entire content should be split across multiple files with the SKILL.md serving as a concise overview.

Suggestions

Cut the 'Philosophy' and 'Privacy & Data' sections entirely - Claude doesn't need to be told why markdown is human-readable or version-controllable.

Move the large file templates (WELCOME-TO-COG.md, MY-PROFILE.md, MY-INTERESTS.md, etc.) into separate template files and reference them from SKILL.md (e.g., 'Use template from 06-templates/onboarding/')

Add explicit validation steps after file/directory creation: verify files exist, check frontmatter is valid, confirm directory structure matches expected layout before proceeding to wrap-up.

Remove or drastically shorten the 'Benefits of markdown storage' list and the 'Tips for Success' section in the welcome guide - these explain concepts Claude already understands and are user-facing content that doesn't need to be in the skill instructions.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~400+ lines. Contains extensive philosophical sections ('Philosophy', 'Privacy & Data') explaining why markdown is good, which Claude already knows. The welcome guide template alone is massive and includes tips like 'Don't overthink it' that are user-facing fluff. The 'Benefits of markdown storage' list is entirely unnecessary. Much of this could be cut by 60-70% without losing actionable content.	1 / 3
Actionability	Provides concrete file templates with frontmatter and directory structures, which is good. However, there are no actual executable commands for creating directories or files - it's all descriptive ('Create the following markdown files'). The extraction logic in Step 3 is a table of heuristics rather than concrete implementation. The role pack matching in Step 5.5 describes logic but doesn't show actual code for scanning files or matching aliases.	2 / 3
Workflow Clarity	The process flow is clearly numbered (Steps 1-9) with a logical sequence, and error handling covers partial completion and existing profiles. However, there are no explicit validation checkpoints - after creating multiple files and directories, there's no step to verify they were created correctly. The workflow also has potential confusion with Step 5.5 and 5.6 being inserted between Steps 5 and 6, suggesting the sequence evolved organically rather than being cleanly designed.	2 / 3
Progressive Disclosure	Everything is in one monolithic file with no references to external files for detailed content. The massive welcome guide template, all file templates, directory structures, and philosophy sections are all inline. The role pack matching references `.claude/roles/*.md` files but no bundle files are provided. Content like the full WELCOME-TO-COG.md template and the Philosophy section should be in separate referenced files.	1 / 3
	Total	6 / 12 Passed

Description

35%

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 basic sense of purpose—initial setup/personalization creating specific files—but relies on product-specific jargon ('COG') without explanation and lacks an explicit 'Use when...' clause. It would benefit from clearer trigger terms and a more explicit statement of when Claude should select this skill.

Suggestions

Replace or explain the acronym 'COG' so users and Claude can understand the domain without prior knowledge, and add natural trigger terms like 'initialize', 'first-time setup', 'configure preferences', or 'onboarding'.

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to set up or initialize their profile, configure interests, or create a watchlist for the first time.'

Expand on what the guided setup entails with 1-2 more concrete actions to improve specificity, e.g., 'Asks preference questions and generates a user profile, topic interest list, and content watchlist.'

Dimension	Reasoning	Score
Specificity	Names some concrete outputs ('profile, interests, and watchlist files') and mentions 'guided setup', but doesn't detail what specific actions occur during setup or what these files contain.	2 / 3
Completeness	The 'what' is partially addressed (creates profile, interests, watchlist files with guided setup), but the 'when' is only implied by the parenthetical '(run this first!)' rather than an explicit 'Use when...' clause with clear trigger conditions.	2 / 3
Trigger Term Quality	Uses the term 'COG' which is jargon/product-specific and not something a user would naturally say. 'Personalize', 'profile', 'workflow' are somewhat generic. Missing natural trigger terms like 'configure', 'initialize', 'onboarding', or 'first time setup'.	1 / 3
Distinctiveness Conflict Risk	The mention of 'COG' and specific file types (profile, interests, watchlist) provides some distinctiveness, but 'personalize' and 'workflow' are generic enough to potentially overlap with other configuration or setup skills.	2 / 3
	Total	7 / 12 Passed

Validation

81%

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 — 9 / 11 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	9 / 11 Passed

Repository: huytieu/COG-second-brain
Commit: 034af4c

Reviewed: about 1 month 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.