self-assessment

Interactive skill assessment with personalized learning path generation

Quality

46%

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 ./.agents/skills/self-assessment/SKILL.md

Quality

Content

50%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 well-structured and offers concrete invocation commands and example outputs, but it is notably verbose due to repeated sections and lacks validation checkpoints in its batch-scoring workflow. With no bundle files present, referenced guide paths cannot be verified for progressive disclosure.

Suggestions

Collapse the repeated 'How It Works', 'Getting Started', 'What You Learn', and 'After Your Assessment' sections into a single concise overview to remove redundancy and respect the context window.

Add an explicit validation checkpoint for the assessment workflow (e.g., how answers are scored, how partial/skipped questions are handled, when the profile is finalized).

Provide or verify the referenced bundle files (guide/ultimate-guide.md, examples/*) so the one-level-deep references are real and navigable, or mark external guide sections as out-of-bundle explicitly.

Dimension	Reasoning	Score
Conciseness	The 200+ line body reiterates the same workflow four times (How It Works, Getting Started, What You Learn, After Your Assessment) and restates the frontmatter profiles/modes, adding substantial padding beyond what Claude needs.	2 / 5
Actionability	Concrete triggers (/self-assessment quick/comprehensive with --verbose and --save flags) and example outputs are provided, though the actual question/answer mechanics and scoring algorithm are described in prose rather than as executable logic.	4 / 5
Workflow Clarity	A clear 4-step sequence (choose mode, answer, get profile, get path) is presented, but the assessment involves batch scoring across 10-20 topics with no validation/checkpoint step confirming answers or handling edge cases, capping workflow clarity at 3.	3 / 5
Progressive Disclosure	Sections are well-organized with headers and an overview, but no bundle files (references/scripts/assets) exist; referenced paths like guide/ultimate-guide.md and examples/* are external and not verifiable, so structure is inline-only with references that cannot be confirmed.	3 / 5
	Total	12 / 20 Passed

Description

42%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 states a clear 'what' (interactive assessment generating a learning path) but omits any 'when to use it' trigger guidance, capping completeness and trigger quality. It is specific enough to be distinct but lacks the natural trigger phrases users would say.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when the user wants to gauge their Codex proficiency, quiz themselves, or get a personalized learning path.'

Include common user phrasings such as 'quiz', 'test my skills', 'find my gaps', or 'what should I learn next' to improve trigger-term coverage.

Briefly enumerate concrete outputs (skill profile, per-topic scores, prioritized learning path, practice projects) to broaden capability coverage.

Dimension	Reasoning	Score
Specificity	Phrases 'skill assessment' and 'learning path generation' name the domain and 1-2 concrete actions (assess, generate path), but do not enumerate what the assessment produces beyond a learning path, leaving coverage only partial.	3 / 5
Completeness	The 'what' is stated (interactive skill assessment with learning path generation) but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	The only natural trigger keyword is 'assessment'; common user phrasings like 'quiz', 'test my skills', 'find my gaps', or 'learning path' are absent, so it relies on a single generic term.	2 / 5
Distinctiveness Conflict Risk	'Interactive skill assessment' is fairly specific and unlikely to conflict with unrelated skills, but it could overlap with general quiz/learning skills and lacks triggers that sharply bound its niche.	3 / 5
	Total	11 / 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: .agents/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.