CtrlK
BlogDocsLog inGet started
Tessl Logo

onboarding

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

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/onboarding/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 a well-sequenced, highly actionable onboarding workflow with strong validation checkpoints and appropriately split reference templates. Its main weakness is conciseness, driven by a few padded sections and repeated reminders.

Suggestions

Trim or remove the 'Benefits of markdown storage' and 'Philosophy' sections, which restate concepts Claude already knows about markdown.

Consolidate the repeated 'Don't present a numbered menu' guidance into one stated rule instead of restating it at steps 2, 5, 9, and the wrap-up.

Consider moving the verbatim welcome messages and MY-INTEGRATIONS.md template into a reference file to shorten the body toward a true overview.

DimensionReasoningScore

Conciseness

Most of the body is efficient, skill-specific process guidance, but the 'Benefits of markdown storage' and 'Philosophy' sections plus the ~4x repeated 'Don't present a numbered menu' reminders are unnecessary explanation that could be tightened, matching 'mostly efficient but includes some unnecessary explanation'.

3 / 5

Actionability

Verbatim copy-paste welcome messages, a concrete extraction table with specific patterns ('I'm Alex', 'I'm a PM'), an inline MY-INTEGRATIONS.md markdown template, and a literal directory tree provide fully executable guidance covering common cases.

5 / 5

Workflow Clarity

A clearly numbered 9-step sequence has explicit validation checkpoints ('Wait for confirmation', confirm captured info), feedback loops (Error Handling with resume), and a Success Criteria checklist; the batch file-creation op includes validation so the destructive/batch cap does not apply.

5 / 5

Progressive Disclosure

Two real, clearly-signaled, one-level-deep references (profile-templates.md, welcome-guide.md) appropriately split the bulky templates out, but the body itself is long with substantial inline content (integration template, role-pack matching), keeping it just below a clean 'clear overview' 5.

4 / 5

Total

17

/

20

Passed

Description

58%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 'what' with several concrete actions and COG-specific outputs, but its trigger guidance is only weakly implied and keyword coverage is thin. Adding an explicit 'Use when…' clause with natural synonyms would lift completeness and trigger quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when a new user runs /onboarding, says they want to set up or get started with COG, or wants to personalize their profile.'

Broaden trigger keywords to include natural synonyms like 'getting started', 'new user setup', and 'initialize COG'.

Consider naming the concrete actions more comprehensively (e.g. 'creates profile, interests, integrations, and watchlist files') to push specificity toward 5.

DimensionReasoningScore

Specificity

"creates profile, interests, and watchlist files with guided setup" names several concrete actions (three file types plus guided setup), but coverage is not fully comprehensive, matching the 'lists several specific actions; minor gaps' anchor rather than the 5.

4 / 5

Completeness

It states a clear 'what' (creates profile/interests/watchlist files), but the 'when' is only weakly implied by '(run this first!)' with no explicit 'Use when…' clause, so per the cap it stays at 3.

3 / 5

Trigger Term Quality

"guided setup" and "run this first" are natural phrases, but the description misses common synonyms users might say (getting started, new user, initialize), fitting the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

The COG-specific outputs (profile, interests, watchlist files) give it a clear niche with minor overlap risk against other COG config skills, matching 'mostly distinct; minor overlap risk' rather than the broad 3.

4 / 5

Total

14

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
huytieu/COG-second-brain
Reviewed

Table of Contents

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.