CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

64

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/oma-pm/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 content is a well-structured, actionable planning skill with a clear scene-based workflow and explicit verification and recovery steps. Its weak points are token-efficiency (a duplicated reference section and an abstract SSL-primitive action table) rather than correctness or organization.

Suggestions

De-duplicate the References section: keep the bulleted path list and remove the repeated prose lines (lines 140-145) that restate the same resources/execution-protocol.md, examples.md, and iso-planning.md paths.

Replace or drop the "SSL primitive" (READ/SELECT/INFER/VALIDATE/WRITE/NOTIFY) Actions table, which reads as non-executable jargon; the evidence column already conveys the same meaning without the abstraction layer.

Make the VERIFY scene's validation concrete by naming the actual check (e.g., the task-template.json schema fields to validate against) instead of only describing the validation conceptually, which would lift workflow_clarity to 5.

DimensionReasoningScore

Conciseness

The body is largely tight and table-driven without explaining concepts Claude already knows, but the References section lists paths twice (prose then bullets, lines 140-159) and the SSL-primitive "Actions" table adds jargon that could be trimmed.

3 / 5

Actionability

Concrete guidance is present via the YAML output schema, canonical file paths (plan-{sessionId}.json, result-pm.md), and specific guardrail fields, but the READ/SELECT/INFER "SSL primitive" action layer is abstract non-executable jargon rather than real operations.

4 / 5

Workflow Clarity

A clear PREPARE→REASON→ACT→VERIFY→FINALIZE sequence with an explicit VERIFY checkpoint and failure/recovery feedback loops is present; the VERIFY step is described as checks rather than a concrete validation command, keeping it just short of a clean 5.

4 / 5

Progressive Disclosure

The body is an overview that points one level deep to clearly signaled reference files, with no inline bulk content that belongs elsewhere; minor gaps come from the duplicated reference list and cross-skill paths (../_shared/, ../oma-orchestration/) that cannot be verified against a bundle.

4 / 5

Total

15

/

20

Passed

Description

83%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 strong: it answers both what and when explicitly, uses natural trigger keywords, and stakes out a distinct PM/ISO-aligned niche. Its main limitation is specificity of actions, which leans on attribute phrasing rather than an enumerated action list.

DimensionReasoningScore

Specificity

Names the PM domain and concrete actions ("decomposes requirements into actionable tasks with priorities and dependencies"), with several specific attributes, though it does not enumerate many distinct actions like drafting API contracts or acceptance criteria.

4 / 5

Completeness

Explicitly states what the skill does ("decomposes requirements into actionable tasks with priorities and dependencies") and when to use it ("Use for planning, requirements, specification, scope, prioritization, task breakdown...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural trigger terms are well covered ("Use for planning, requirements, specification, scope, prioritization, task breakdown") plus ISO standards, but the synonym sweep is not fully comprehensive.

4 / 5

Distinctiveness Conflict Risk

The "Product manager" plus ISO 21500/31000/38500 framing carves a clear niche distinct from coding/QA skills, with only minor overlap risk against generic orchestration/planning skills.

4 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
first-fluke/oh-my-agent
Reviewed

Table of Contents

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.