CtrlK
BlogDocsLog inGet started
Tessl Logo

cold-start-interview

Professor's one-time clinic setup — practice areas, jurisdiction, supervision style (formal review queue / configurable flags / lighter-touch), and handbook/rules upload. Writes CLAUDE.md so every other skill and every student who runs /ramp reads from the same clinic context. Use on fresh install, when CLAUDE.md has placeholders, when re-doing setup with --redo, or when re-checking integrations with --check-integrations.

66

Quality

81%

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 highly actionable, well-sequenced interview script with strong validation checkpoints, weakened mainly by verbosity and a monolithic single-file structure that lacks in-bundle progressive disclosure.

Suggestions

Trim the repeated 'Why this matters' rationales and the capacity-constrained preamble; assume Claude can infer clinic context and keep only decision-relevant rationale.

Split the Part 0–5 interview questions and verbatim user-facing prompt blocks into reference files (e.g. references/interview-parts.md) signaled from SKILL.md to improve progressive disclosure.

Condense the 'After writing' capabilities list and closing notes, which repeat information already conveyed in the setup steps.

DimensionReasoningScore

Conciseness

Mostly actionable but padded with repeated 'Why this matters' rationales and contextual preamble ('Clinics are structurally capacity-constrained...') that Claude could infer; the ~360-line body could be tightened.

2 / 3

Actionability

Provides exact file paths, verbatim user-facing phrasings, concrete flags, and a precise ✓/⚪/✗ integration-probing procedure — copy-paste ready guidance throughout.

3 / 3

Workflow Clarity

Clear Part 0→5 sequence with explicit validation checkpoints: fact verification as answers arise, a 'Before writing — re-read' contradiction check, and 'never report ✓ based on configuration alone'.

3 / 3

Progressive Disclosure

Well-sectioned with headers but monolithic at ~360 lines; the interview parts and verbatim prompt blocks could be split into reference files rather than kept inline.

2 / 3

Total

10

/

12

Passed

Description

85%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.

A specific, complete, and distinctive description with an explicit 'Use when' clause; its main weakness is trigger phrasing that leans on flags and technical conditions rather than natural user language.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'practice areas, jurisdiction, supervision style ... and handbook/rules upload' and 'Writes CLAUDE.md' — rather than vague language.

3 / 3

Completeness

Explicitly states what it does and when to use it via 'Use on fresh install, when CLAUDE.md has placeholders, when re-doing setup with --redo, or when re-checking integrations'.

3 / 3

Trigger Term Quality

Triggers are mostly technical conditions and flags ('CLAUDE.md has placeholders', '--redo', '--check-integrations') rather than natural phrases a user would say, missing common variations.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (one-time law-school clinic setup feeding /ramp) with distinct triggers unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 2 missing

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

13

/

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.