CtrlK
BlogDocsLog inGet started
Tessl Logo

ramp

Student semester onboarding — clinic procedures, tool walkthrough, practice exercises before real cases. Reads the handbook the professor uploaded at setup and teaches it interactively. Use when a new clinic student says "onboard me", "I'm new to the clinic", "getting started", or at the start of each semester; pass --card for the one-page reference.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-3

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

A well-structured, actionable onboarding walkthrough with a clear timed sequence and good comprehension checkpoints. Its weaknesses are token efficiency (verbatim scripted speeches) and a monolithic layout with no external references for content that could be split out.

Suggestions

Trim the verbatim Opening and Closing speeches to a brief outline of the points to cover; let Claude phrase the greeting naturally rather than scripting it word-for-word.

Move the full walkthrough dialogue and practice-exercise hypos into a reference file (e.g. references/walkthrough.md), keeping SKILL.md as a concise overview that links to it — this improves both conciseness and progressive disclosure.

Extract the --card content spec into its own reference file so the main body stays a tight overview of the onboarding flow.

DimensionReasoningScore

Conciseness

The body is mostly efficient, but the fully scripted Opening/Closing speeches ('I'm going to walk you through how this clinic works...') are dialogue Claude could generate itself, which is unnecessary scaffolding that could be tightened.

2 / 3

Actionability

Concrete and specific throughout: a command table with when/what columns, named practice exercises with worked example hypos (Maria's eviction), and explicit debrief questions — actionable guidance despite being instruction-only with no code.

3 / 3

Workflow Clarity

A clearly sequenced multi-step walkthrough (Opening → Parts 1–4 with minute budgets → Closing) with a load-context validation gate and comprehension/debrief checkpoints after each exercise; no destructive ops so heavy validation is not required.

3 / 3

Progressive Disclosure

Well-organized into sections but monolithic at ~120 lines with no bundle references — the full walkthrough script and the --card spec are inline content that could be split into separate reference files, matching the 'content that should be separate is inline' anchor.

2 / 3

Total

10

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 concise, third-person, and explicitly covers capabilities plus natural trigger terms tied to a distinct niche. It cleanly matches the top anchor on all four dimensions.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'clinic procedures, tool walkthrough, practice exercises', 'Reads the handbook... and teaches it interactively', and 'pass --card for the one-page reference' — matching the 'multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers what (onboarding, procedures, walkthrough, practice exercises, reads/teaches handbook) and when (the 'Use when...' clause with explicit triggers), satisfying both halves.

3 / 3

Trigger Term Quality

'Use when a new clinic student says "onboard me", "I'm new to the clinic", "getting started", or at the start of each semester' gives natural phrasings a user would actually say, with good coverage.

3 / 3

Distinctiveness Conflict Risk

The legal-clinic student onboarding niche with distinct triggers ('onboard me', 'I'm new to the clinic') is clearly bounded and unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
anthropics/claude-for-legal
Reviewed

Table of Contents

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.