cpo-review

/cs:cpo-review <plan> — JTBD-driven interrogation of product roadmap, PMF signal, and portfolio focus. Use when committing a quarter's roadmap, deciding whether to kill a feature, or claiming PMF without a retention curve.

Quality

87%

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

87%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 lean, actionable skill body with concrete commands and a complete output template. The main gap is workflow clarity: a verdict-rendering skill needs explicit decision rules and validation/feedback steps rather than an undefined 'Apply the verdict'.

Suggestions

Add an explicit decision rule mapping the six answers to the verdict (e.g., ship if RICE ranks top-3 AND retention is smiling/flat AND a kill criterion is defined; sharpen if one signal is weak; kill if retention is decaying or no North Star link).

Insert a validation checkpoint after 'Run the analyses' (e.g., confirm each script exited 0 and produced output before proceeding) and a retry path on failure.

Define the SHIP/SHARPEN/KILL thresholds in writing so the verdict is reproducible rather than left to judgment.

Dimension	Reasoning	Score
Conciseness	Lean body with short headers, one-liner definitions, and no explanation of JTBD/PMF/RICE concepts Claude already knows; the few aphorisms ('Job ≠ feature', 'The cut list is the focus list') are mnemonic rather than padding.	5 / 5
Actionability	Provides concrete runnable commands (rice_prioritizer.py, pmf_scorer.py, portfolio_analyzer.py) and a fully specified copy-paste output template with placeholders covering all six questions plus a verdict rubric.	5 / 5
Workflow Clarity	A clear three-step sequence exists ('Run the analyses', 'Answer the six questions', 'Apply the verdict'), but there are no validation checkpoints, no feedback loop if a script fails, and no rule mapping the six answers to the SHIP/SHARPEN/KILL verdict — a gap that caps this consequential decision workflow at 3.	3 / 5
Progressive Disclosure	Well-organized into clear sections (When to Run, Six Questions, Workflow, Output Format, Routing, Related) with no nested references; cross-skill pointers are one-level-deep and clearly signaled, and no bundle files are needed.	5 / 5
	Total	18 / 20 Passed

Description

87%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 description: third-person, concrete, with explicit what/when clauses and a distinct CPO-level niche. Minor room to broaden trigger-term synonyms and enumerate actions more comprehensively.

Dimension	Reasoning	Score
Specificity	Names the product/PMF/portfolio domain and several concrete forcing actions ('interrogation of product roadmap, PMF signal, and portfolio focus', 'kill a feature', 'claiming PMF without a retention curve'); not a 5 because actions are framed as question categories rather than an enumerated comprehensive action list.	4 / 5
Completeness	Explicitly states both what ('JTBD-driven interrogation of product roadmap, PMF signal, and portfolio focus') and when ('Use when committing a quarter's roadmap, deciding whether to kill a feature, or claiming PMF without a retention curve') with three concrete triggers.	5 / 5
Trigger Term Quality	Includes natural CPO/PM trigger phrases ('committing a quarter's roadmap', 'deciding whether to kill a feature', 'claiming PMF without a retention curve') with good coverage; not a 5 because common synonyms like 'roadmap review' or 'prioritization' are absent.	4 / 5
Distinctiveness Conflict Risk	The named command '/cs:cpo-review' plus the narrow CPO/JTBD/PMF niche gives it a clear, distinct trigger with minimal overlap risk against other skills.	5 / 5
	Total	18 / 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/cpo-review/SKILL.md
Commit: 19392f7

Reviewed: ~11 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.