cold-start-interview

Cold-start interview — connects to your launch tracker, reads past reviews, learns your risk calibration. Use on fresh install, when onboarding product counsel, or when the plugin config has placeholders. Run with --redo to re-interview, or --check-integrations to re-probe connectors only.

Quality

80%

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 ./product-legal/skills/cold-start-interview/SKILL.md

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 thorough, highly actionable interview skill with strong sequencing and validation checkpoints, but it is long and motivational prose pads the body, and much of the template/script content that could live in reference files is inlined in SKILL.md.

Suggestions

Move the full practice-profile template and the verbatim interview scripts into a references/ file (e.g. references/practice-profile-template.md), keeping SKILL.md a lean overview with one-level-deep pointers.

Trim repeated motivational justification ('Why this matters', the multi-paragraph orientation monologue) to prose that assumes the model's competence and states only the non-obvious rationale.

Consolidate the connector-probing guidance, which appears in three near-duplicate spots (top of file, --check-integrations section, and Part 0), into one canonical reference.

Dimension	Reasoning	Score
Conciseness	The guidance is mostly purposeful and actionable, but the body runs ~480 lines with repeated motivational framing ('Why this matters', orientation monologues, and preamble prose) that restates context a skilled model already grasps.	2 / 3
Actionability	Highly concrete: exact config paths, a copy-forward migration rule, a literal calibration-table schema, an inline practice-profile template, and verbatim phrasings to use — copy-paste ready instruction rather than abstract direction.	3 / 3
Workflow Clarity	A clearly numbered 6-step top-level sequence plus explicit validation checkpoints (probe connectors before reporting ✓, list skipped placeholders before writing, verify user-stated legal facts before saving) with pause/resume and redo loops.	3 / 3
Progressive Disclosure	Sections are well-labeled and there is a one-level reference to references/company-profile-template.md, but the bulk of the material (the full practice-profile template and all interview scripts) is inlined in SKILL.md rather than split into reference files, making it monolithic.	2 / 3
	Total	10 / 12 Passed

Description

82%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, third-person description that clearly scopes when to use the skill (fresh install, onboarding, placeholder config) and what it does. Its main weakness is trigger-term naturalness: 'cold-start interview' is product-internal phrasing a user is unlikely to say unprompted.

Suggestions

Add common natural phrasings a user would actually say ('set up', 'onboard', 'configure the plugin') alongside the jargon so the description triggers when users ask in their own words.

Consider mentioning the underlying domain ('product counsel / launch review setup') so the description is discoverable to someone who doesn't yet know the plugin's name.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in third person — 'connects to your launch tracker, reads past reviews, learns your risk calibration' — naming specific capabilities rather than vague abstractions.	3 / 3
Completeness	Explicitly answers both what (connects/reads/learns risk calibration) and when ('Use on fresh install, when onboarding product counsel, or when the plugin config has placeholders'). Both halves are present with explicit triggers.	3 / 3
Trigger Term Quality	Has relevant natural terms ('launch tracker', 'past reviews', 'risk calibration', 'product counsel') but leans on skill-specific jargon; a user needing this is more likely to say 'onboarding' or 'set up' than 'cold-start interview'.	2 / 3
Distinctiveness Conflict Risk	Narrows to a clear niche — the cold-start/onboarding moment for the product-legal plugin with --redo and --check-integrations flags — making it unlikely to trigger for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
Path: product-legal/skills/cold-start-interview/SKILL.md
Commit: 4a6c651

Reviewed: 6 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.