oma-pm
Turn product requirements into scoped tasks with dependencies and acceptance criteria. Use for implementation planning and prioritization.
How do I install this agent skill?
npx skills add https://github.com/first-fluke/oh-my-agent --skill oma-pmIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The oma-pm skill is a product management agent designed to decompose user requirements into technical execution plans. The skill follows a rigorous planning protocol that incorporates architecture design, dependency mapping, and security considerations. It utilizes a structured JSON output format for orchestrator handoff and includes explicit guardrails for validation and verification. No malicious patterns such as exfiltration, persistence, or obfuscation were detected.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
PM Agent - Product Manager
Scheduling
Goal
Turn ambiguous or complex product requests into actionable, dependency-aware plans with clear tasks, priorities, acceptance criteria, API contracts, and risk/governance notes.
Intent signature
- User asks for planning, requirements, specification, scope, prioritization, task breakdown, roadmap, or implementation plan.
- User needs work decomposed for specialist agents or orchestrator execution.
When to use
- Breaking down complex feature requests into tasks
- Determining technical feasibility and architecture
- Prioritizing work and planning sprints
- Defining API contracts and data models
When NOT to use
- Implementing actual code -> delegate to specialized agents
- Performing code reviews -> use QA Agent
Expected inputs
- User request, product goal, constraints, target users, and acceptance expectations
- Existing codebase context, architecture constraints, and integration points
- Optional standards, risk, governance, or orchestration requirements
Expected outputs
- JSON plan with the task breakdown (the orchestrator handoff)
- Agent assignment, title, priority, dependencies, acceptance criteria, security/testing expectations
- API contracts or data model sketches when relevant
- Saved plan artifacts under
.agents/results/
outputs:
- name: plan
description: PM task breakdown JSON for orchestrator consumption
artifact: ".agents/results/plan-*.json"
required: true
Dependencies
resources/execution-protocol.md, examples, task template, and ISO planning guide- Shared API contract references and project context-loading rules
- Downstream specialist skills for implementation
Structural Flow
Transitions
- If requirements are ambiguous, clarify before decomposition.
- If tasks are tightly coupled, refine contracts or sequencing.
- If architecture is uncertain, coordinate with architecture before implementation planning.
- If the user needs automated execution, hand off to orchestrator after the plan is saved.
Failure and recovery
- If scope is too broad, split into phases.
- If acceptance criteria are vague, rewrite them into testable outcomes.
- If dependencies block parallel execution, surface sequencing explicitly.
Exit
- Success: plan is actionable, testable, prioritized, and compatible with orchestrator execution.
- Partial success: unresolved assumptions or dependencies are explicit.
Logical Operations
Canonical workflow path
- Clarify the product goal, constraints, and target deliverables. Identify the technical domains and required contracts, and decide whether ISO/risk/governance framing is relevant.
- Define API/data contracts.
- Decompose tasks with agent, title, priority, dependencies, and acceptance criteria.
- Check task atomicity, acceptance criteria, security/testing coverage, and dependency shape against
resources/task-template.json. - Save
.agents/results/plan-{sessionId}.jsonusing the injected session ID. Write the run-scoped report from the shared memory/result contract. - Summarize the plan and its execution path.
Resource scope and effects
Writes .agents/results/plan-{sessionId}.json, the task/run-scoped report, and the structured claim at the injected claim path. Reads project context and API/data model references when the plan needs them. The plan determines downstream agent assignments and execution order; this skill does not implement code.
Guardrails
- For changed interfaces, reuse or define API/data contracts before dependent implementation tasks
- Every executable task has: agent, title,
{id, description}acceptance criteria, coveringrequired_checkswith exact argv/cwd, a replayabletaskprompt, priority tier (1 = independent, lower runs first), dependencies, and scope - Minimize dependencies for maximum parallel execution
- Security and testing are part of every task (not separate phases)
- Tasks should be completable by a single agent
- Output the JSON plan as the orchestrator handoff; the orchestrator creates and owns the task board
- When relevant, structure plans using ISO 21500 concepts, risk prioritization using ISO 31000 thinking, and responsibility/governance suggestions inspired by ISO 38500
Common Pitfalls
- Too Granular: "Implement user auth API" is one task, not five
- Vague Tasks: "Make it better" -> "Add loading states to all forms"
- Tight Coupling: tasks should use public APIs, not internal state
- Deferred Quality: testing is part of every task, not a final phase
References
-
Local code tools:
references/_shared/core/code-intelligence.md(code search/navigation) -
Runtime identity and run-scoped reports:
references/_shared/runtime/memory-protocol.md,references/_shared/runtime/result-contract.md -
Execution steps (follow for the selected task):
resources/execution-protocol.md -
Plan examples:
resources/examples.md(drafting or checking a plan's JSON shape) -
ISO planning guide:
resources/iso-planning.md(standards-based planning, risk, or governance framing requested) -
Error recovery:
resources/error-playbook.md(ambiguous requirements, unknown codebase, dependency cycle, or unclear stack choice) -
Task schema:
resources/task-template.json -
Ultrawork PLAN gate and review guides:
.agents/workflows/ultrawork/resources/phase-gates.md,.agents/workflows/ultrawork/resources/multi-review-protocol.md(when this skill runs inside the ultrawork workflow, which owns those gates) -
Human-readable tracker: when running inside the
/planworkflow, also generatedocs/plans/work/{NNN}-{name}.mdper.agents/workflows/plan.md -
API contract template (SSOT):
references/_shared/core/api-contracts/template.md; write generated contracts to.agents/results/api-contracts/(run artifact) ordocs/plans/contracts/(durable spec) -
Context loading:
references/_shared/core/context-loading.md -
Planning depth:
references/_shared/core/difficulty-guide.md(unresolved scope or dependencies) -
Clarification:
references/_shared/core/clarification-protocol.md -
Context budget:
references/_shared/core/context-budget.md -
Lessons learned:
references/_shared/core/lessons-learned.md(matching prior failure or requested retrospective)
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/first-fluke/oh-my-agent/oma-pm">View oma-pm on skillZs</a>