oma-pm

Product manager that decomposes requirements into actionable tasks with priorities and dependencies. Use for planning, requirements, specification, scope, prioritization, task breakdown, and ISO 21500, ISO 31000, or ISO 38500-aligned planning recommendations.

Quality

88%

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

Quality

Content

77%

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

A well-structured, actionable planning skill with clear sequenced workflow and validation checkpoints. Its main weaknesses are a redundant references listing and references to external resources that are not present within the skill bundle.

Suggestions

Dedupe the References section — list each referenced file once in the bullet list and drop the repeated prose restatements.

Bundle the referenced resources/ and ../_shared/core/ files inside the skill (e.g., under references/) or remove references to files that are not part of the skill, so progressive disclosure points to real bundled content.

Trim ceremonial scaffolding (the SSL primitive table and Scenes labels) where it restates process structure Claude already applies, keeping only net-new planning guidance.

Dimension	Reasoning	Score
Conciseness	Sections are terse and well-structured, but there is redundancy — the References block lists the same files three ways (prose lines then a bullet list) — and some ceremonial scaffolding (SSL primitives, Scenes labels) adds structure Claude largely already knows. Not 1 because it is not padded with concept-explanations, but it is not fully lean either.	2 / 3
Actionability	Concrete, specific guidance throughout: the Guardrails specify exact task fields, Common Pitfalls give before/after rewrites ('Make it better' -> 'Add loading states to all forms'), and the canonical workflow names exact output paths. For an instruction-only skill this is fully actionable.	3 / 3
Workflow Clarity	A clear sequence (Entry -> PREPARE/REASON/ACT/VERIFY/FINALIZE -> Exit) with an explicit VERIFY checkpoint and a failure-and-recovery section providing feedback loops (vague criteria -> rewrite testable; broad scope -> split into phases). Validation is present for these planning operations.	3 / 3
Progressive Disclosure	References are clearly signaled and one level deep, but no bundle directories (references/, scripts/, assets/) exist and the referenced files (resources/, ../_shared/core/) live outside the skill and are not actually bundled here. Structure is an overview pointing to detail files, which is right in spirit, but the missing/out-of-tree bundle keeps it from the top anchor.	2 / 3
	Total	10 / 12 Passed

Description

100%

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, third-person description that clearly states both capability and explicit use-triggers with natural keywords. It is concrete and well-scoped to the PM planning niche with standards-based distinctiveness.

Dimension	Reasoning	Score
Specificity	Names concrete actions — 'decomposes requirements into actionable tasks with priorities and dependencies' — going beyond vague language to specify what the skill produces. It is slightly narrow (one core function) but the actions are specific and concrete, matching the top anchor.	3 / 3
Completeness	It explicitly answers both what ('decomposes requirements into actionable tasks with priorities and dependencies') and when ('Use for planning, requirements, specification, scope, prioritization, task breakdown'), with an explicit trigger clause present. Not 2 because the when is explicit, not merely implied.	3 / 3
Trigger Term Quality	The 'Use for planning, requirements, specification, scope, prioritization, task breakdown' clause gives good coverage of natural terms a user would actually say. The ISO standard names are technical, but the natural planning terms carry the score to the top anchor.	3 / 3
Distinctiveness Conflict Risk	The PM task-decomposition niche plus ISO 21500/31000/38500 framing gives it a distinct trigger profile unlikely to fire for the wrong skill. There is minor overlap with generic planning, but the task-breakdown and ISO alignment narrow it sufficiently.	3 / 3
	Total	12 / 12 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: first-fluke/oh-my-agent
Path: .agents/skills/oma-pm/SKILL.md
Commit: 3021301

Reviewed: about 24 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.