vpe-review

/cs:vpe-review <plan> — Throughput-first VP of Engineering interrogation of any plan that touches delivery, eng hiring, team structure, or production discipline. Use when cycle time balloons, DORA metrics slide, or before committing to an eng hiring wave or a reorg.

Quality

89%

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

83%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.

The body is highly actionable and token-efficient with concrete thresholds and a complete output template. Its main weakness is workflow_clarity: the workflow lacks explicit validation/feedback loops despite covering batch-style hiring and production decisions.

Suggestions

Add explicit validation checkpoints to the Workflow section — e.g. after running delivery_throughput_analyzer.py, verify the metrics file parsed and the DORA levels populated before proceeding to the next question.

Include a fix-and-retry feedback loop for batch/commitment operations: when offer-to-accept < 70% or a manager/director trigger fires, state the corrective action and re-check rather than only emitting the verdict.

For multi-year hiring commitments (routed to /cs:freeze 30), add an explicit validation gate (e.g. confirm headcount envelope against CFO budget) before the workflow advances to the verdict step.

Dimension	Reasoning	Score
Conciseness	The body is lean and bullet-driven throughout, assumes Claude's competence (no DORA/PDF-style concept primers), and every line earns its place; even the bolded one-liners under each question are terse diagnostic cues.	5 / 5
Actionability	Provides copy-paste-ready commands with arguments (e.g. `python ../../../c-level-advisor/skills/vpe-advisor/scripts/delivery_throughput_analyzer.py sprint_metrics.json`), concrete thresholds (offer-to-accept < 70%, 5-9 ICs per squad, on-call rotation ≥ 6), and a fully specified output template covering the common cases.	5 / 5
Workflow Clarity	The Workflow section lists three numbered script invocations and the Six Questions are sequenced, but there are no explicit validation checkpoints or fix-and-retry feedback loops, and several operations (production-discipline assessment, multi-year hiring commitments) are batch/commitment-style where missing validation caps the score per the rubric.	3 / 5
Progressive Disclosure	Content is well-organized into clearly-signaled sections (When to Run, Six Questions, Workflow, Output Format, Routing, Related) with one-level-deep pointers to adjacent skills/agents; there are no in-skill bundle files, so the split is clean, though the external relative-path script references are not bundled references to verify.	4 / 5
	Total	17 / 20 Passed

Description

95%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.

The description is specific, trigger-rich, and cleanly answers both what and when for a well-scoped niche. It is a strong model of the form.

Dimension	Reasoning	Score
Specificity	Names the concrete capability ("Throughput-first VP of Engineering interrogation of any plan") and enumerates the four touched domains (delivery, eng hiring, team structure, production discipline); the only gap is that the actions are described at the interrogation-of-a-plan level rather than as multiple discrete operations.	4 / 5
Completeness	Explicitly answers both what ("Throughput-first VP of Engineering interrogation of any plan that touches delivery, eng hiring, team structure, or production discipline") and when ("Use when cycle time balloons, DORA metrics slide, or before committing to an eng hiring wave or a reorg") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would actually say when they need this skill — "cycle time balloons", "DORA metrics slide", "eng hiring wave", "reorg" — covering the full range of triggering situations with synonyms.	5 / 5
Distinctiveness Conflict Risk	Carves a clear VPE-throughput niche with distinct triggers (cycle time, DORA, hiring waves, reorg) that are unlikely to fire for unrelated skills, so conflict risk is minimal.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 suspicious	Warning

	Total	15 / 16 Passed

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

Reviewed: ~12 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.