vpe-advisor

VP of Engineering advisory for startups: delivery throughput (DORA 4 metrics + bottleneck identification), engineering hiring funnel (sourcing → screen → onsite → offer conversion + time-to-fill + pipeline gap), engineering team structure (squad/tribe/chapter design + tech-lead manager-trigger thresholds), and production discipline (on-call, deployment cadence, postmortem culture). Use when sprint velocity is dropping, eng hiring is broken, team structure is unclear, or deciding when to add a tech-lead manager. NOT a CTO skill (which owns architecture) — VPE owns delivery operations and how the team ships.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

71%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.

A well-structured, highly actionable skill body with real tooling and a clean progressive-disclosure split into verified reference files. The main drag is conciseness: a large keyword-stuffing section, duplicated boundary framing, and some re-explanation of well-known frameworks.

Suggestions

Remove or drastically trim the 'Keywords' section — it is keyword stuffing that adds tokens without guiding Claude's actions; the 'Use when' triggers in the description already cover discovery.

Delete the duplicate 'NOT a CTO skill' and 'NOT a cs-engineering-lead replacement' paragraphs from the body since the distinction is already stated in the description and the Adjacent Skills section.

Convert the workflow bash blocks from commented descriptive steps to actual runnable commands (or explicit validation calls) so the workflows are as copy-paste ready as the Quick Start.

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational content, but the ~25-term 'Keywords' section is pure keyword stuffing, the 'NOT a CTO skill' / 'NOT a cs-engineering-lead replacement' framing is duplicated from the description, and the DORA/Spotify-model explanations restate concepts Claude already knows.	3 / 5
Actionability	Three real executable scripts with embedded sample data and copy-paste Quick Start commands, plus concrete numeric thresholds (manager-trigger at 5-7 ICs, per-stage funnel conversions); held at 4 because the workflow bash blocks are mostly commented descriptive steps rather than runnable commands.	4 / 5
Workflow Clarity	Four workflows each carry a stated goal, numbered sequence, cross-check checkpoints, and a defined output via the Output Standards block; minor validation gaps keep it below 5, and the destructive/batch cap does not apply since these are diagnostic workflows.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview that signals one-level-deep references (all four references/.md and three scripts/.py files verified to exist) with a dedicated References section, and detail is appropriately split out rather than inlined.	5 / 5
	Total	16 / 20 Passed

Description

92%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.

A strong, specific description that clearly states what the skill does, when to invoke it via natural triggers, and how it differs from adjacent CTO/engineering-lead roles. Minor room only on trigger-synonym breadth; verbosity is present but each clause carries concrete content rather than padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across four domains — 'DORA 4 metrics + bottleneck identification', 'sourcing → screen → onsite → offer conversion + time-to-fill + pipeline gap', 'squad/tribe/chapter design + tech-lead manager-trigger thresholds', 'on-call, deployment cadence, postmortem culture' — with comprehensive coverage and no vague fluff.	5 / 5
Completeness	Explicitly answers both what (four advisory domains with concrete sub-actions) and when ('Use when…' with four concrete trigger scenarios), matching the anchor for clearly and explicitly answering both.	5 / 5
Trigger Term Quality	The 'Use when sprint velocity is dropping, eng hiring is broken, team structure is unclear, or deciding when to add a tech-lead manager' clause gives natural phrases a user would actually say; just shy of 5 because synonym/extension breadth is limited rather than comprehensive.	4 / 5
Distinctiveness Conflict Risk	The explicit boundary 'NOT a CTO skill (which owns architecture) — VPE owns delivery operations and how the team ships' carves a clear niche with distinct triggers and minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: alirezarezvani/claude-skills
Path: c-level-advisor/skills/vpe-advisor/SKILL.md
Commit: 19392f7

Reviewed: ~13 hours 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.