[Documentation] Use when generating, smart-merging or refactoring the root AI context (CLAUDE.md, AGENTS.md) and its Claude/Codex projections. Config file only: project-config.
中文简介正在准备中。当前显示原文说明。
[Content] Use when a workflow step or the user asks for marketing strategy: positioning, channels, messaging, campaigns, budget and KPIs.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Goal: Build comprehensive marketing strategy with positioning, channels, messaging, campaigns, budget, and KPIs.
Summary:
[N] mapped to a Sources row, and make KPIs specific, measurable, and time-bound.Workflow:
Key Rules:
[N] citation mapped to a Sources row (Title, URL, Author/Org, Date, Tier); reuse the market-analysis Sources rows for market facts. Factual claims rest on 2+ independent sources; a single-source claim is marked unverified and held below 60% confidence. Planning choices you set (budget split, KPI targets) state their basis as labelled assumptionsBe skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).
When invoked by workflow-research marketing mode, read the exact parent-provided
MARKET_ANALYSIS_PATH; never derive a second slug. If that workflow artifact is missing, mark market
facts N/A and cap market-evidence confidence at 60% — do not silently substitute inline context.
Standalone inline context is allowed only when labelled Unverified inline market context. In that
mode, do not claim it is the market-analysis artifact, do not introduce uncited market-size figures,
mark unsupported market facts N/A, and cap market-evidence confidence at 60%. Extract only what the
evidence provenance supports: competitor landscape, target segments, SWOT, and market size.
Based on competitive analysis:
For each channel:
| Channel | Purpose | Budget % | Expected ROI | Priority |
|---|---|---|---|---|
| {channel} | {awareness/acquisition/retention} | {%} | {X:1} | P0/P1/P2 |
Total budget % must equal 100%.
| Phase | Timeline | Objective | Tactics | KPIs | Budget |
|---|---|---|---|---|---|
| Launch | M1-M3 | Awareness | {list} | {metrics} | {$} |
| Growth | M4-M6 | Acquisition | {list} | {metrics} | {$} |
| Scale | M7-M12 | Retention | {list} | {metrics} | {$} |
| Risk | Likelihood | Impact | Mitigation |
|---|---|---|---|
| {risk} | H/M/L | H/M/L | {strategy} |
Write to docs/knowledge/strategy/marketing/{descriptive-slug}.md using enforced template from .claude/templates/marketing-strategy-template.md. List every cited source in its Sources table with Title, URL, Author/Org, Date and Tier; every [N] resolves to a row and every row is cited.
[IMPORTANT] Use
TaskCreateto break ALL work into small tasks BEFORE starting.
IMPORTANT MUST ATTENTION Goal: Build comprehensive marketing strategy with positioning, channels, messaging, campaigns, budget, and KPIs.
IMPORTANT MUST ATTENTION Main steps: load market analysis → define positioning → plan channels, budget, and ROI → craft messaging → build campaign roadmap and KPIs → assess risks and mitigations.
IMPORTANT MUST ATTENTION break work into small todo tasks using TaskCreate BEFORE starting
IMPORTANT MUST ATTENTION cite every factual claim and number inline [N] mapped to a Sources row (Title, URL, Author/Org, Date, Tier); reuse the market-analysis Sources rows for market facts
IMPORTANT MUST ATTENTION back factual claims with 2+ independent sources; mark a single-source claim unverified and hold it below 60% confidence
IMPORTANT MUST ATTENTION add a final review todo task to verify work quality
[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using TaskCreate.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
[Documentation] Use when generating, smart-merging or refactoring the root AI context (CLAUDE.md, AGENTS.md) and its Claude/Codex projections. Config file only: project-config.
中文简介正在准备中。当前显示原文说明。
[Code Quality] Use when a workflow step or the user asks for AI code or plan review: LLM calls, prompts, agents, RAG, evals and guardrails. --mode={code|plan}; --report-only is read-only.
中文简介正在准备中。当前显示原文说明。
[Architecture] Use when a workflow step or the user asks for architecture design, compliance review, scalability grading or whole-project audit via --mode={design|review|scalability|full}.
中文简介正在准备中。当前显示原文说明。
[Content] Use when a workflow step or the user asks for product/feature ideation with ranked opportunities and validation tests. --mode={roadmap|scope}.
中文简介正在准备中。当前显示原文说明。
[Content] Use when a workflow step or the user asks for business viability: Business Model Canvas, financials, risks and go-to-market recommendation.
中文简介正在准备中。当前显示原文说明。
[Code Quality] Use when a workflow step or the user asks for a focused code-change review: staged, unstaged, branch diff or simple pull request. --fix-loop fixes and re-reviews. Complex pull request: workflow-review-changes; rationale: why-review.
中文简介正在准备中。当前显示原文说明。