tutorial

Interactive walkthrough for new users. Learn by doing — each step creates real content in your vault. Three tracks (researcher, manager, personal) with a universal learning arc. Triggers on "/tutorial", "walk me through", "how do I use this".

Quality

78%

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 ./skills/tutorial/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill body is highly actionable with a well-sequenced, validated workflow, but it is verbose and monolithic. Tightening the repeated track framings and offloading the detailed per-track prose into a reference file would improve both conciseness and progressive disclosure.

Suggestions

Condense the repeated three-track WHY/DO tables: state the shared structure once and keep only the track-specific deltas, cutting the philosophical prose that pads each step.

Move the per-step track-adaptation language tables (Steps 1-5) into a single reference file (e.g. references/track-framing.md) and signal it once, reducing the inline bulk.

The workflow sequencing and state-persistence rules are exemplary; preserve them as-is while trimming surrounding prose.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient domain guidance, but ~490 lines repeat the WHY/DO/SEE structure across five steps each with three lengthy philosophical track paragraphs that could be tightened; verbosity is present even though the content is accurate.	2 / 3
Actionability	Guidance is concrete and executable for an instruction-only skill: verbatim AskUserQuestion prompts per track, literal display templates, exact YAML state schemas, and specific file paths like 'ops/tutorial-state.yaml' and '{vocabulary.notes}/'.	3 / 3
Workflow Clarity	A clearly sequenced five-step flow (Capture, Discover, Process, Maintain, Reflect) with progress bars, mandatory state persistence after every step, resume detection, and an explicit validation/feedback loop in the Step 4 health check (detect warnings, auto-fix, report).	3 / 3
Progressive Disclosure	Internal section organization is clear and the runtime config files it cites are one level deep, but as a ~490-line single SKILL.md with no bundle reference files, the per-step track-adaptation tables and philosophy text are inline material that could be split out.	2 / 3
	Total	10 / 12 Passed

Description

80%

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 has strong triggers, completeness, and distinctiveness, but its capability list is vague and it slips into second-person voice ('your vault'). Rewording in third person and naming the concrete walkthrough actions would raise it.

Suggestions

Replace second-person phrasing ('your vault') with third person (e.g. 'Creates real notes in the user's vault') to satisfy the voice requirement.

Enumerate the concrete actions the walkthrough performs — e.g. 'captures notes, finds connections, extracts insights, runs vault health checks, and reflects on the graph' — instead of the generic 'creates real content'.

Keep the existing 'Triggers on...' clause; it is the strongest part of the description.

Dimension	Reasoning	Score
Specificity	The phrase 'each step creates real content in your vault' names a domain and one vague action but never lists the concrete actions (capture notes, discover connections, extract insights, health-check, reflect); it also uses second person ('your vault'), which reduces the specificity score by 1 per the voice guideline.	1 / 3
Completeness	It answers 'what' ('Interactive walkthrough for new users... each step creates real content... Three tracks') and 'when' with explicit trigger guidance ('Triggers on...'), satisfying both halves.	3 / 3
Trigger Term Quality	It explicitly states 'Triggers on "/tutorial", "walk me through", "how do I use this"', giving natural phrases a user would actually say plus the command form.	3 / 3
Distinctiveness Conflict Risk	The distinct '/tutorial' command and the three named tracks carve a clear onboarding niche, making overlap with other skills unlikely.	3 / 3
	Total	10 / 12 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: agenticnotetaking/arscontexta
Path: skills/tutorial/SKILL.md
Commit: 2acfd5c

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.