product-manager-toolkit

Comprehensive toolkit for product managers including RICE prioritization, customer interview analysis, PRD templates, discovery frameworks, and go-to-market strategies. Use for feature prioritization, user research synthesis, requirement documentation, and product strategy development.

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/product-manager-toolkit/product-manager-toolkit/SKILL.md

Quality

Content

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is over-long and padded with standard PM frameworks Claude already knows plus a large tangential agent-integration section, dragging down token efficiency and progressive disclosure. It does provide genuinely executable script commands and well-sequenced workflows, but those workflows lack validation checkpoints and several referenced external files do not exist in the bundle.

Suggestions

Remove or move to a reference file the explanations of well-known frameworks (RICE formula, MoSCoW, North Star, funnel, Opportunity Solution Tree) and the entire agent-collaboration section, keeping SKILL.md a lean overview.

Add explicit validation checkpoints to the batch workflows (e.g. verify the CSV parses and required columns exist before scoring; confirm PRD acceptance criteria are testable before sign-off).

Delete the broken external references (agent-team/*, multi-agent-meeting/*) or gate them behind a clear prerequisite note, since those files are not present in this bundle.

Dimension	Reasoning	Score
Conciseness	The ~600-line body is verbose and re-explains concepts Claude already knows (the RICE formula, MoSCoW, North Star, funnel analysis, Opportunity Solution Tree), and the 250-line appended agent-collaboration section is largely tangential padding — matching the 'verbose; explains concepts Claude knows; padded' anchor.	1 / 3
Actionability	Executable, copy-paste-ready bash commands for the real bundle scripts (e.g. 'python scripts/rice_prioritizer.py features.csv --capacity 15') are present, but roughly half the document is descriptive framework lists and best-practice bullets rather than concrete instruction, fitting 'some concrete guidance but incomplete'.	2 / 3
Workflow Clarity	The Feature Prioritization, Customer Discovery, and PRD processes are clearly sequenced as numbered steps, but none include explicit validation/verification checkpoints for these batch CSV and document operations, which per the rubric caps workflow clarity at 2.	2 / 3
Progressive Disclosure	A real reference file (references/prd_templates.md) and two real scripts are correctly signaled, but the body is a monolithic wall of framework/metrics content that should be split into reference files, and it references non-existent external paths (agent-team/references/agent-registry.md, multi-agent-meeting/assets/...) — matching the 'some structure but content that should be separate is inline' anchor.	2 / 3
	Total	7 / 12 Passed

Description

85%

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 strong: it enumerates concrete capabilities, supplies an explicit 'Use for' trigger clause, and carves a distinct PM niche. Its main weakness is trigger-term naturalness, which leans on category labels rather than the phrasings a user would actually say.

Suggestions

Replace category labels with natural user phrasings, e.g. 'Use when prioritizing features with RICE, writing a PRD, or synthesizing customer interview notes'.

Lead with the single most common trigger (e.g. prioritizing features / writing PRDs) before listing the full capability set to sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete capabilities — "RICE prioritization, customer interview analysis, PRD templates, discovery frameworks, and go-to-market strategies" — matching the anchor for enumerating several specific actions rather than vague language.	3 / 3
Completeness	Explicitly answers both what (the toolkit's capabilities) and when via the "Use for feature prioritization, user research synthesis, requirement documentation, and product strategy development" clause, satisfying the explicit-trigger anchor.	3 / 3
Trigger Term Quality	Contains relevant PM terms ("feature prioritization," "user research synthesis," "requirement documentation") but misses the most natural trigger phrasings users would say (e.g., "write a PRD," "RICE score," "analyze an interview"), fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	Distinctive triggers like RICE, PRD templates, and customer interview analysis carve a clear product-management niche unlikely to fire for unrelated skills, despite the somewhat broad 'comprehensive toolkit' framing.	3 / 3
	Total	11 / 12 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
skill_md_line_count	SKILL.md is long (604 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: anbeime/skill
Path: skills/product-manager-toolkit/product-manager-toolkit/SKILL.md
Commit: f595e96

Reviewed: about 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.