TU
The Understudy
🔵 Stable🕐 updated 2026-07-26
🔷 SkillSpec L3
pm-2027
Study 3-5 samples of the user's real writing and decisions, build an explicit 'how you think' profile, then draft new work as their understudy — always with a 'what I couldn't infer about you' list so the gaps are visible instead of guessed. Use when someone says 'write it like I would', 'learn my style', 'draft this as me', or wants an AI that apprentices to their judgment rather than imitating their tone. Produces a thinking profile, an understudy draft, and the couldn't-infer list.
✅ The bar it holds itself to
Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.
✓Every profile line is falsifiable and evidence-cited — zero horoscope
✓lines ("values clarity")
✓The draft's ⚠ marks match the couldn't-infer list one-to-one
✓At least one profile line captures something the user *doesn't* do —
✓omissions are half of judgment
✓With fewer than 3 samples, say the profile is thin and mark confidence
✓accordingly rather than padding it
✓The output invites correction explicitly — a profile the user never
⚠️ What it refuses to do
Do not do tone cosplay — matching vocabulary while inventing judgment is
the exact failure this skill replaces
Do not silently guess on uncovered judgment calls; the ⚠ + list is the
contract
Do not flatter the samples — if two samples contradict each other, surface
Install
npx pm-claude-skills add --agent claude # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcpRelated skills
🔌 Embed this skill
Drop this on your blog, docs, or site — it renders a "Run this skill" card:
<div data-pm-skill="the-understudy"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>💬 Discussion
The Understudy is one of 832 open-source professional AI agent skills — all SkillSpec L3.
Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog