Name: product-manager
Rating: 44.8 (1 reviews)
Author: administrakt0r

product-manager

Senior PM agent with 6 knowledge domains, 30+ frameworks, 12 templates, and 32 SaaS metrics with formulas. Pure Markdown, zero scripts.

Quality

46%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/product-manager/SKILL.md

The canonical home for this skill is product-manager in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

33%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 skill is a well-organized but shallow persona inventory: it lists domains, frameworks, templates, and metrics by name without providing the actual templates or formulas it advertises, and contains no workflow or executable guidance for Claude to follow.

Suggestions

Deliver the promised detail: include the actual RICE/MoSCoW scoring steps and the exact formulas for the SaaS metrics (or move them into reference files and link them) so the body is actionable.

Add a concrete workflow for common PM tasks (e.g., a discovery->prioritization->PRD->launch sequence) with explicit steps, since the skill currently has no process structure.

Remove the metadata filler (Compatibility tool list, GitHub Source URL) from the body — it belongs in frontmatter — and drop the redundant opening paragraph that restates the description.

Dimension	Reasoning	Score
Conciseness	The body is short with clean section headers, but the opening paragraph restates the frontmatter description and the 'Compatibility' and 'Source' sections (tool list, GitHub URL) are metadata filler that could be tightened; matches 'mostly efficient but could be tightened' rather than the minor-trim 4.	3 / 5
Actionability	The body names frameworks (RICE, MoSCoW) and metrics (MRR, LTV, CAC) but gives no executable steps and, despite claiming '32 SaaS metrics with exact formulas', provides no formulas and shows no templates; above the purely-abstract 1 because it names specifics, but only 'minimal concrete guidance; missing the specific steps to execute'.	2 / 5
Workflow Clarity	There is no multi-step process or sequence at all — the body is a static capability inventory, and it is not a single unambiguous action, so it matches 'steps missing or incoherent; no sequence'.	1 / 5
Progressive Disclosure	Under 50 lines and well-organized with clear section headers, which the simple-skill exception rewards; not a 5 because the claimed detailed materials (templates, exact formulas, framework guides) are neither inlined nor placed in reference files — they are simply absent.	4 / 5
	Total	10 / 20 Passed

Description

58%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 clearly conveys what the skill is (a PM persona with frameworks, templates, and SaaS metrics) and is reasonably specific and distinct, but it omits any 'when to use it' trigger guidance, which caps completeness and limits trigger-term quality.

Suggestions

Add an explicit 'Use when...' trigger clause naming concrete PM tasks (e.g., writing PRDs, prioritizing a backlog, calculating SaaS metrics like churn or LTV, building a roadmap).

Replace the inventory framing with verbed actions ('Draft PRDs', 'Prioritize with RICE/MoSCoW', 'Calculate 32 SaaS metrics with formulas') to lift specificity.

Include natural user phrasings and synonyms (PRD, roadmap, churn rate, LTV:CAC) as trigger terms.

Dimension	Reasoning	Score
Specificity	Quotes 'Senior PM agent with 6 knowledge domains, 30+ frameworks, 12 templates, and 32 SaaS metrics with formulas' list several concrete capability areas; not a 5 because capabilities are framed as a persona/inventory rather than verbed actions and 'Pure Markdown, zero scripts' describes format not capability.	4 / 5
Completeness	The 'what' is clearly stated (Senior PM agent with domains, frameworks, templates, metrics) but there is no 'Use when...' or equivalent trigger clause, so per the guideline a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Terms like 'product manager', 'frameworks', 'templates', 'SaaS metrics' are relevant but common natural phrasings a user would say ('write a PRD', 'prioritize the backlog', 'calculate churn/LTV', 'roadmap') are missing, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The 'Senior PM agent' + SaaS metrics niche is mostly distinct with only minor overlap risk against adjacent business/strategy skills; not a 5 because there are no explicit distinct trigger phrases to lock in the niche.	4 / 5
	Total	14 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/product-manager/SKILL.md
Commit: 57c135b

Reviewed: 3 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.