self-assessment

Comprehensive Claude Code self-assessment and learning path advisor. Runs a multi-category quiz covering 10 feature areas, produces a detailed skill profile with per-topic scores, identifies specific gaps, and generates a personalized learning path with prioritized next steps. Use when asked to "assess my level", "take the quiz", "find my level", "where should I start", "what should I learn next", "check my skills", "skill check", or "level up".

Quality

85%

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

Quality

Content

71%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 highly actionable with concrete questions, scoring, and templates and a clearly sequenced, error-handled workflow. Its main weakness is token efficiency and progressive disclosure: roughly 280 lines of content that already exist in the bundled reference files are inlined verbatim rather than linked.

Suggestions

Move the duplicated question rounds, output templates, and topic-specific recommendations out of SKILL.md into the existing reference files and link to them from the relevant steps instead of inlining the content verbatim.

Add explicit, clearly signaled references to deep-assessment-rounds.md, output-templates.md, and topic-recommendations.md at the points where that content is currently inlined, so the overview points one level deep to the details.

Trim the generic placeholder-laden path-output template and rely on the concrete topic-specific recommendations to reduce the token load while preserving actionability.

Dimension	Reasoning	Score
Conciseness	The ~432-line body inlines the full question rounds, result templates, and all topic-specific recommendations that are duplicated verbatim in the three reference files; it is operational rather than padded with known concepts, but the heavy duplication makes it noticeably longer than necessary. Not 2 because it does not explain concepts Claude already knows; not 4 because substantial inlined tokens could be offloaded.	3 / 5
Actionability	Provides exact AskUserQuestion option text, explicit scoring rules (e.g. "0-2 total = Level 1: Beginner"), concrete output templates, and tutorial paths with exercises and success criteria, making it fully executable for an instruction skill.	5 / 5
Workflow Clarity	The Step 1 through Step 5 sequence is clearly laid out with Quick/Deep branching and an Error Handling section covering edge cases, and deterministic scoring acts as validation. Not 5 because there are no explicit validate-fix-retry feedback loops or checklists, and the simple-skill exception does not apply to this complex skill.	4 / 5
Progressive Disclosure	Section structure is good and navigable, but the body never links the three existing reference files (deep-assessment-rounds.md, output-templates.md, topic-recommendations.md) and instead inlines their content; references are present but not signaled. Not 2 because structure is real; not 4 because content that belongs in separate files is fully inlined.	3 / 5
	Total	15 / 20 Passed

Description

100%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 strong: it states concrete capabilities in third person, lists a comprehensive set of natural trigger phrases, and explicitly covers both what the skill does and when to use it. It occupies a clear, low-conflict niche.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Runs a multi-category quiz covering 10 feature areas, produces a detailed skill profile with per-topic scores, identifies specific gaps, and generates a personalized learning path") with comprehensive coverage, matching the score-5 anchor rather than the minor-gaps anchor at 4.	5 / 5
Completeness	Explicitly answers both what (quiz, profile, gap identification, learning path) and when ("Use when asked to ...") with concrete trigger phrases, matching the score-5 anchor rather than the weaker-when anchor at 4.	5 / 5
Trigger Term Quality	Provides comprehensive natural trigger phrases and synonyms users would actually say ("assess my level", "take the quiz", "find my level", "check my skills", "skill check", "level up", "what should I learn next"), matching the score-5 anchor.	5 / 5
Distinctiveness Conflict Risk	The Claude Code self-assessment/quiz framing with distinct triggers carves a clear niche with minimal conflict risk; voice is third-person throughout ("Runs", "produces", "generates").	5 / 5
	Total	20 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 10 suspicious	Warning

	Total	14 / 16 Passed

Repository: luongnv89/claude-howto
Path: .claude/skills/self-assessment/SKILL.md
Commit: 1c04dbf

Reviewed: 4 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.