- name
SKILL.md
Файл навыка остаётся в репозитории издателя.
Вставьте скопированную команду в терминал. Она установит этот SKILL.md в выбранного агента.
npx skills add first-fluke/oh-my-agent --skill oma-pm -a cursor -yВставьте скопированную команду в терминал. Она установит этот SKILL.md в выбранного агента.
npx skills add first-fluke/oh-my-agent --skill oma-pm -a claude-code -yВставьте скопированную команду в терминал. Она установит этот SKILL.md в выбранного агента.
npx skills add first-fluke/oh-my-agent --skill oma-pm -a codex -yВставьте скопированную команду в терминал. Она установит этот SKILL.md в выбранного агента.
npx skills add first-fluke/oh-my-agent --skill oma-pm -a grok -yОтправьте скопированное сообщение в чат Grok Bot. Бот загрузит этот SKILL.md с GitHub и добавит его к навыкам, общим для всех ваших ботов.
Install this skill: https://github.com/first-fluke/oh-my-agent/tree/HEAD/.agents/skills/oma-pmОт издателя
Turn ambiguous or complex product requests into actionable, dependency-aware plans with clear tasks, priorities, acceptance criteria, API contracts, and risk/governance notes.
.agents/results/outputs:
- name: plan
description: PM task breakdown JSON for orchestrator consumption
artifact: ".agents/results/plan-*.json"
required: true
resources/execution-protocol.md, examples, task template, and ISO planning guideresources/task-template.json..agents/results/plan-{sessionId}.json using the injected session ID. Write the run-scoped report from the shared memory/result contract.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.
{id, description} acceptance criteria, covering required_checks with exact argv/cwd, a replayable task prompt, priority tier (1 = independent, lower runs first), dependencies, and scopeLocal code tools: ../_shared/core/code-intelligence.md (code search/navigation)
Runtime identity and run-scoped reports: ../_shared/runtime/memory-protocol.md, ../_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 /plan workflow, also generate docs/plans/work/{NNN}-{name}.md per .agents/workflows/plan.md
API contract template (SSOT): ../_shared/core/api-contracts/template.md; write generated contracts to .agents/results/api-contracts/ (run artifact) or docs/plans/contracts/ (durable spec)
Context loading: ../_shared/core/context-loading.md
Planning depth: ../_shared/core/difficulty-guide.md (unresolved scope or dependencies)
Clarification: ../_shared/core/clarification-protocol.md
Context budget: ../_shared/core/context-budget.md
Lessons learned: ../_shared/core/lessons-learned.md (matching prior failure or requested retrospective)
Turn product requirements into scoped tasks with dependencies and acceptance criteria. Use for implementation planning and prioritization.
---name: oma-pmdescription: Turn product requirements into scoped tasks with dependencies and acceptance criteria. Use for implementation…---# .agents/skills/oma-pm/SKILL.mdFAQ
Скачайте .agents/skills/oma-pm/SKILL.md у издателя или скопируйте путь и откройте репозиторий. PlugMCP только показывает навык в каталоге и не хранит файл.
Издатель хранит его в https://github.com/first-fluke/oh-my-agent.
Claude, Cursor, Codex и Grok Build могут читать SKILL.md, который вы добавляете из репозитория издателя. Grok Bot устанавливает его, когда вы отправляете в чат ссылку на папку навыка на GitHub.