ab-test-setup
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split…
Use when you need to delegate, track, or review work.
$ npx -y skills add marian2js/opengoat --skill og-board-manager --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/og-board-managerContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when you need to delegate, track, or review work.
name: og-board-manager description: Use when you need to delegate, track, or review work. metadata: version: "1.0.0"
Delegate and track work using OpenGoat tools.
Use tools directly. Do not run shell CLI commands like `sh ./opengoat ...`.
Important: replace `<me>` with your agent ID.
opengoat_agent_info({ "agentId": "<me>" })opengoat_task_list({ "assignee": "<me>" })
opengoat_task_get({ "taskId": "<task-id>" })
opengoat_task_create({
"actorId": "<me>",
"title": "...",
"description": "...",
"assignedTo": "<agent-id>"
})
opengoat_task_update_status({
"actorId": "<me>",
"taskId": "<task-id>",
"status": "todo|doing|blocked|pending|done",
"reason": "<optional-reason>"
})
opengoat_task_add_blocker({ "actorId": "<me>", "taskId": "<task-id>", "blocker": "..." })
opengoat_task_add_artifact({ "actorId": "<me>", "taskId": "<task-id>", "content": "..." })
opengoat_task_add_worklog({ "actorId": "<me>", "taskId": "<task-id>", "content": "..." })opengoat_agent_info({ "agentId": "<me>" })Use the output to ensure:
opengoat_task_list({ "assignee": "<me>" })
opengoat_task_get({ "taskId": "<task-id>" })Create one task per owner and outcome.
opengoat_task_create({
"actorId": "<me>",
"title": "<verb>: <deliverable>",
"description": "<context + deliverable + acceptance criteria>",
"assignedTo": "<agent-id>"
})If the task is small enough and you have the tools and context to complete it efficiently, do not delegate. Create a task for yourself so the work is still tracked.
Rules:
Example:
opengoat_task_create({
"actorId": "<me>",
"title": "Fix: <short description>",
"description": "Context:\n- ...\n\nDeliverable:\n- ...\n\nAcceptance criteria:\n- ...",
"assignedTo": "<me>"
})Do not blindly break tasks down small. Size tasks based on where you sit in the org and who you are assigning to.
Write outcome-focused tasks:
Expect your reportee to create smaller tasks for their own direct reportees if needed.
Write execution-ready tasks:
Use a verb + deliverable:
Context: - Why this matters (1–3 bullets) Deliverable: - What to produce (code/doc/decision) Acceptance criteria: - Observable checks (tests pass, output, link, screenshot, etc.) Constraints: - Scope boundaries, dependencies, must-use tools, performance limits
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split…
When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations —…
When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use…
When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up…
When the user wants to reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement…
Write B2B cold emails and follow-up sequences that get replies. Use when the user wants to write cold outreach emails,…