CtrlK
BlogDocsLog inGet started
Tessl Logo

oma-pm

Turn product requirements into scoped tasks with dependencies and acceptance criteria. Use for implementation planning and prioritization.

56

Quality

63%

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

56%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 body is well-structured with a clear scene-based workflow, explicit verification and failure-recovery sections, and genuinely concrete guardrails and pitfalls. It is held back by repeated output-path and ISO statements, an abstract canonical workflow whose core artifact (the plan JSON) is never exemplified, and a References section whose targets are absent from the bundle and whose list formatting is broken.

Suggestions

Include a minimal example task object (agent, title, priority tier, dependencies, acceptance criteria, scope) or an inline excerpt of the task schema so the plan artifact is concrete without needing resources/task-template.json.

State the save paths and ISO-structuring guidance once (e.g., in Expected outputs) and remove the repetitions in the canonical workflow, guardrail 6, and the stray line inside the References section.

Fix the References section formatting so it is an uninterrupted, consistently styled list, and ensure the referenced resources/ files actually ship in the skill bundle or drop the dead paths.

DimensionReasoningScore

Conciseness

The body is dense and does not explain known concepts, but the save-path instruction ("Save plan to `.agents/results/plan-{sessionId}.json`...") is repeated across the Expected outputs, YAML outputs block, canonical workflow, guardrail 6, and References, ISO framing appears twice, and "Control-flow features" is meta-description that could be cut.

3 / 5

Actionability

Concrete guidance exists (guardrail 2's explicit task fields, pitfalls with real examples like "'Implement user auth API' is one task, not five"), but the canonical workflow is abstract ("Define API/data contracts. Decompose tasks...") and the actual plan JSON shape or example task is never shown — it is deferred to resources/task-template.json, which is not present in the bundle, leaving key details missing.

3 / 5

Workflow Clarity

A clear sequenced flow (Entry, PREPARE/REASON/ACT/VERIFY/FINALIZE, Exit) with an explicit VERIFY checkpoint ("Check task atomicity, acceptance criteria, security/testing coverage, and dependency shape") and a failure-and-recovery feedback section; verification is stated at a high level but not operationalized as a concrete checklist, matching the 'most checkpoints present' anchor.

4 / 5

Progressive Disclosure

References are one level deep and each is labeled with its purpose, but none of the referenced files (resources/execution-protocol.md, resources/task-template.json, ../_shared/core/*) exist in the bundle, and the References section is structurally broken by a stray prose line ("Save plan to `.agents/results/...`") interrupting the bullet list mid-section, so organization is imperfect rather than merely having minor gaps.

3 / 5

Total

13

/

20

Passed

Description

70%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 solid description that explicitly states both what the skill does and when to use it in third person with concrete deliverable attributes. Its main gaps are the single-action specificity and a 'when' clause that lacks richer natural trigger phrases like 'task breakdown', 'roadmap', or 'spec'.

DimensionReasoningScore

Specificity

"Turn product requirements into scoped tasks with dependencies and acceptance criteria" names the domain with one concrete action and its attributes, but does not list several distinct actions, matching the 1-2-concrete-actions anchor rather than the several-actions anchor above.

3 / 5

Completeness

Both parts are explicitly present: what ("Turn product requirements into scoped tasks with dependencies and acceptance criteria") and when ("Use for implementation planning and prioritization"), but the when-clause is generic rather than listing concrete trigger phrases, matching the anchor where 'when' could be more explicit.

4 / 5

Trigger Term Quality

"implementation planning", "prioritization", "product requirements", and "dependencies" are natural user phrases with good coverage, but common variations like "task breakdown", "roadmap", "spec", or "sprint" are missing, so it falls just short of the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

The product-planning framing ("scoped tasks", "acceptance criteria", "prioritization") carves a mostly distinct PM niche with only minor overlap risk against generic planning or orchestration skills, fitting the 'mostly distinct' anchor rather than the clear-niche anchor.

4 / 5

Total

15

/

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.

Validation — 16 / 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.