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

86%

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

73%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 a clear, validated multi-step workflow, but it is noticeably verbose and fails to use the provided reference files — inlining deep-assessment rounds, output templates, and topic recommendations that already exist as separate bundle files.

Suggestions

Replace the inlined Step 2B rounds with a pointer to references/deep-assessment-rounds.md, keeping only the round structure and scoring summary in SKILL.md.

Move the Step 3 output templates to references/output-templates.md and the Step 4 topic-specific recommendations to references/topic-recommendations.md, linking to them from the body.

Trim version-specific trivia (e.g. 'v2.1.251', 'v2.1.224') out of the inline focus lists or relocate it to the relevant reference file, since Claude already knows the feature surface.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but could be tightened: the inline Topic-Specific Recommendations section embeds long per-topic advanced-feature lists and version-specific notes ('v2.1.251', 'v2.1.224', 'v2.1.200') that restate facts Claude largely knows and would fit better in a reference file.	3 / 5
Actionability	Fully executable guidance: exact AskUserQuestion options with headers, explicit scoring thresholds ('0-2 total = Level 1'), fenced output templates, a dependency order, and phase-grouping rules — copy-paste ready across common cases.	5 / 5
Workflow Clarity	Clear 5-step sequence with explicit 2A/2B branches, scoring as a validation checkpoint, a dedicated Error Handling section covering empty selections and retakes, and feedback loops (retake returns to Step 1).	5 / 5
Progressive Disclosure	The bundle ships references/deep-assessment-rounds.md, output-templates.md, and topic-recommendations.md, yet the body inlines all of that content (Step 2B rounds, Step 3 templates, Step 4 recommendations) instead of linking to the reference files, leaving content that belongs in separate files buried inline.	2 / 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 exemplary: it states concrete capabilities in third person and provides an explicit 'Use when...' clause with comprehensive natural trigger phrases. It clearly distinguishes itself from neighboring skills.

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 prioritized next steps' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (quiz, profile, gap identification, learning path) and 'when' via a concrete 'Use when asked to...' clause with named trigger phrases.	5 / 5
Trigger Term Quality	Includes comprehensive natural trigger phrases a user would actually say — 'assess my level', 'take the quiz', 'find my level', 'where should I start', 'what should I learn next', 'check my skills', 'skill check', 'level up' — with good synonym coverage.	5 / 5
Distinctiveness Conflict Risk	The trigger terms ('assess my level', 'take the quiz', 'level up') carve a clear niche around self-assessment that is unlikely to overlap with code-review or skill-creation skills.	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: 97bfb06

Reviewed: 7 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.