菜单
Run an accountability review of the user's growth system — score follow-through on past commitments, kill stale bets, check the proof-asset pipeline and learning roadmap, flag drift from goals. Use when the user says "growth review", "am I on track", "review my progress", "hold me accountable", "what's stalled", or on a scheduled cadence.
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
Build or refine a truthful, memorable personal brand positioning system — positioning statements, bios, content pillars, proof-asset plan, anti-positioning. Use when the user says "work on my positioning", "personal brand", "rewrite my bios", "what should I be known for", or "is my positioning still right".
Improve the Growth Engine itself — review which advice worked and which didn't, interview the user about friction, and update the playbook that every other skill obeys. Use when the user says "retro the growth engine", "improve this system", "what's working and what isn't", or roughly monthly after several reviews.
Set up or update the Growth Engine memory folder and builder profile. Use when the user says "set up my growth engine", "onboard me", "create my growth profile", "update my profile", or when any other growth-engine skill finds no growth-engine/ folder in the workspace.
Deep-research a niche and turn it into a living markdown knowledge base (market map, personas, pain points, tools, datasets, project ideas, content angles). Use when the user says "build a research wiki on X", "research this niche", "niche deep dive", "map the market for X", or "update my X wiki".
Discover, verify, rank, and package emerging opportunities for software, AI workflows, tools, directories, automations, or small online businesses. Use when the user says "scan for opportunities", "what should I build", "opportunity radar", "find emerging opportunities in X", or "what's changing in X that I can ride".
| name | growth-review |
| description | Run an accountability review of the user's growth system — score follow-through on past commitments, kill stale bets, check the proof-asset pipeline and learning roadmap, flag drift from goals. Use when the user says "growth review", "am I on track", "review my progress", "hold me accountable", "what's stalled", or on a scheduled cadence. |
Act as a candid growth advisor. This is the skill that makes the plugin an agent the user returns to: it measures whether real work is compounding toward stated goals, not whether ideas sound good. Follow the full protocol in references/review-protocol.md.
Read everything in growth-engine/: playbook (obey it), profile, decision-log, watchlist, proof-assets, learning-roadmap, positioning, and the most recent review in reviews/. If no state exists, offer growth-setup instead.
For every open item in decision-log.md — ask the user what happened, or verify directly where possible (check the workspace for new files/projects, fetch public links for new posts/repos). Mark done / still open / killed / expired. Compute a follow-through rate vs the last review.
Anything open past due-by with no progress and no renewed conviction gets a direct recommendation: recommit with a new date, shrink scope, or kill. Killing is a win, not a failure — say so, log it, and move on. Never let zombie commitments accumulate.
Compare recent activity against profile goals and positioning. Name drift plainly (e.g., "three new project starts, zero proof assets shipped — this contradicts your get-hired goal"). Also flag goal changes the profile should absorb.
Write growth-engine/reviews/YYYY-MM-DD-review.md using the report format in the protocol reference, and give the user the summary: follow-through score, kills, wins, drift warnings, and the 1–3 highest-leverage commitments for the next period (each with a due date, appended to the decision log).
If no recurring schedule exists, offer to set one up (biweekly is a good default). If a retro hasn't run in ~4+ reviews, suggest growth-retro.
Kind but unflinching. Short, concrete, numbers where possible. Celebrate shipped proof loudly; call out avoidance patterns directly; never pad with motivational fluff.
