self-assessment

Interactive skill assessment with personalized learning path generation

Quality

44%

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/self-assessment/SKILL.md

Quality

Content

35%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 reads as user-facing marketing/documentation rather than an executable instruction set for Claude: it shows what the assessment produces but not how Claude should run it. It is verbose and lacks the concrete question bank, scoring rules, and path-generation logic that would make it actionable.

Suggestions

Replace the ASCII-art examples and marketing prose with the concrete mechanics Claude needs: a question-bank structure, scoring formula mapping answers to the 0-20 profiles, and explicit rules for ordering the dependency-aware learning path.

Move the question bank and detailed scoring rubric into reference files (e.g. references/questions.md, references/scoring.md) and keep SKILL.md a lean overview with one-level-deep links.

Trim or remove the redundant 'What You Learn', 'Tips for Better Results', and 'Need Help?' sections to recover token budget, or relocate them to a reference doc.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: large ASCII-art output boxes, marketing prose ('Master your Claude Code skills', 'Ready to master Claude Code?'), and redundant sections ('What You Learn', 'Tips for Better Results', 'Need Help?') pad the skill without adding executable guidance for Claude.	2 / 5
Actionability	It gives high-level hints (mode definitions, example output templates) but is missing the specific steps Claude must execute — there is no question bank, no scoring logic, and no algorithm for generating the dependency-aware learning path, so it describes rather than instructs.	2 / 5
Workflow Clarity	A clear Step 1-4 sequence is present (choose mode, answer questions, get profile, get learning path), but validation/feedback checkpoints are only implicit and the per-step mechanics (how answers map to scores, how the path is ordered) are underspecified.	3 / 5
Progressive Disclosure	Section headers give reasonable in-file structure, but no reference/bundle files exist and content that would belong in separate files (question banks, scoring rubric, path-generation rules) is simply absent rather than split out one level deep.	3 / 5
	Total	10 / 20 Passed

Description

53%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 specific and distinctive but lacks an explicit 'when to use' trigger clause, capping completeness at 3. It is a single tight sentence with no explicit invocation guidance.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases (e.g. 'Use when the user wants to gauge their Claude Code proficiency, find skill gaps, or get a personalized study plan').

Include natural keyword variations users might say ('quiz myself', 'test my Claude Code knowledge', 'learning plan') to lift trigger-term coverage.

Expand the action list slightly (e.g. 'scores per-topic, identifies gaps, generates a dependency-aware learning path') to push specificity toward 4-5.

Dimension	Reasoning	Score
Specificity	Names the domain ('skill assessment') and 1-2 concrete actions ('Interactive skill assessment', 'personalized learning path generation'), but the action set is not comprehensive — closer to the score-3 anchor than score 4, which requires several specific actions.	3 / 5
Completeness	The description gives a clear 'what' but no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 3.	3 / 5
Trigger Term Quality	Contains a couple of relevant natural keywords ('skill assessment', 'learning path') but misses common variations and synonyms a user might actually say ('quiz', 'test my knowledge', 'evaluate my skills'), matching the score-3 anchor.	3 / 5
Distinctiveness Conflict Risk	'Interactive skill assessment with personalized learning path generation' carves a mostly distinct niche with only minor overlap risk against closely related quiz/skills (e.g. /lesson-quiz referenced in the body), fitting score 4 rather than the fully-distinct score 5 which expects explicit distinct trigger phrases.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: FlorianBruniaux/claude-code-ultimate-guide
Path: .claude/skills/self-assessment/SKILL.md
Commit: e828d7f

Reviewed: 3 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.