一键导入
full-launch
Use when starting marketing for a new product or brand from scratch - guided workflow through all marketing phases from research to launch
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Use when starting marketing for a new product or brand from scratch - guided workflow through all marketing phases from research to launch
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | full-launch |
| description | Use when starting marketing for a new product or brand from scratch - guided workflow through all marketing phases from research to launch |
Guided end-to-end marketing workflow for new products. Walks through each phase in sequence, invoking the right skill at each step. Tracks progress via docs/marketing/ files and lets you resume mid-workflow.
Announce at start: "I'm using the full-launch skill to guide you through the complete marketing workflow."
Step 1: Context and progress check
Check which docs/marketing/ files already exist:
| File exists | Phase complete |
|---|---|
market-research.md | Market research |
customer-personas.md | Customer personas |
brand-identity.md | Brand identity |
positioning-strategy.md | Positioning strategy |
launch-plan.md | Launch plan |
content-strategy.md | Content strategy |
landing-page.md | Landing page |
campaigns/*.md | Campaigns |
launch-retrospective.md | Retrospective |
If files exist, summarize: "You've already completed: [list]. Next phase is [phase]. Want to continue from there, redo any phase, or start fresh?"
If no files exist, ask: "What product or brand are we launching?" Then proceed to Phase 1.
Step 2: Walk through phases
Invoke each skill in order using the Skill tool. After each skill completes and writes its output file, present the checkpoint:
digraph workflow {
rankdir=TB;
node [shape=box];
"Context check" -> "Phase 1: Market Research";
"Phase 1: Market Research" -> "Checkpoint";
"Checkpoint" -> "Phase 2: Customer Personas" [label="continue"];
"Checkpoint" -> "Skip to next phase" [label="skip"];
"Checkpoint" -> "Stop here" [label="stop"];
"Phase 2: Customer Personas" -> "Checkpoint 2";
"Checkpoint 2" -> "Phase 3: Brand Identity" [label="continue"];
"Phase 3: Brand Identity" -> "Checkpoint 3";
"Checkpoint 3" -> "Phase 4: Positioning Strategy" [label="continue"];
"Phase 4: Positioning Strategy" -> "Checkpoint 4";
"Checkpoint 4" -> "Phase 5: Launch Plan" [label="continue"];
"Phase 5: Launch Plan" -> "Checkpoint 5";
"Checkpoint 5" -> "Phase 6: Content Strategy" [label="continue"];
"Phase 6: Content Strategy" -> "Checkpoint 6";
"Checkpoint 6" -> "Phase 7: Landing Page" [label="continue"];
"Phase 7: Landing Page" -> "Checkpoint 7";
"Checkpoint 7" -> "Phase 8: Campaigns" [label="continue"];
"Phase 8: Campaigns" -> "Done";
"Done" -> "Phase 9: Retrospective" [label="post-launch"];
}
| Phase | Skill to invoke | Output file |
|---|---|---|
| 1 | globalcoder-marketing:market-research | docs/marketing/market-research.md |
| 2 | globalcoder-marketing:customer-personas | docs/marketing/customer-personas.md |
| 3 | globalcoder-marketing:brand-identity | docs/marketing/brand-identity.md |
| 4 | globalcoder-marketing:positioning-strategy | docs/marketing/positioning-strategy.md |
| 5 | globalcoder-marketing:launch-plan | docs/marketing/launch-plan.md |
| 6 | globalcoder-marketing:content-strategy | docs/marketing/content-strategy.md |
| 7 | globalcoder-marketing:landing-page | docs/marketing/landing-page.md |
| 8 | globalcoder-marketing:campaign-builder | docs/marketing/campaigns/*.md |
| 9 | globalcoder-marketing:launch-retrospective | docs/marketing/launch-retrospective.md |
Phase 9 (retrospective) is only suggested post-launch — don't include it in the main flow.
After each phase completes:
Phase N complete. [skill name] output saved to
docs/marketing/[file].md.Next up: [Phase N+1 name] — [one-sentence description of what it does].
Continue to next phase, skip it, or stop here?
If the user returns mid-workflow (files already exist), pick up where they left off. Don't re-run completed phases unless explicitly asked.
Use when executing an implementation plan with four or more independent tasks touching different files, via the experimental agent-teams flag — parallel implementer teammates plus continuous async reviewers. Higher token cost; requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1.
Use when starting creative work — adding features, building components, adding functionality, modifying existing behavior, or any time the user describes a new idea or capability they want to build.
Use when adding, modifying, or removing database tables, columns, indexes, views, functions, or RLS policies — any schema change targeting a shared or production database
Use when facing two or more independent investigations or research tasks in the current session — debugging multiple unrelated failures, exploring different solution approaches, or running parallel reads. Not for executing implementation plans (use subagent-driven-development, agent-team-development, or tmux-parallel-development for those).
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup