What do I need to use Saying No?

The request; Why you want to decline; Constraints; Stakes.

Is Saying No free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Saying No

Q: How do I know the Saying No output is good?

The skill verifies itself against its own quality checks: The no is unambiguous — no false "maybe" that creates false hope; It acknowledges the request and the person before declining; The reason is honest and tied to priorities/trade-offs, not excuses; It offers a path (alternative, later, smaller, someone else) where possible.

🔵 Stable🕐 updated 2026-06-27 🔷 SkillSpec L3 pm-comms

Decline a request, push back on scope, or protect priorities without burning the relationship. Use when asked how to say no, turn down a request, push back on your boss/stakeholder, decline extra work, or protect the roadmap from a pet feature. Produces a graceful, firm response — the no, the honest why, an alternative or trade-off, and the exact wording, tuned to who's asking.

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

What to give it

▸The request — what's being asked, by whom (boss, peer, customer, exec), and the relationship/power dynamic.

▸Why you want to decline — capacity, priorities, fit, or it's the wrong call (the honest reason shapes the no).

▸Constraints — can you offer an alternative, a later yes, or a trade-off? Is a flat no required?

▸Stakes — how important the relationship and the request are.

✅ 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.

✓The no is unambiguous — no false "maybe" that creates false hope

✓It acknowledges the request and the person before declining

✓The reason is honest and tied to priorities/trade-offs, not excuses

✓It offers a path (alternative, later, smaller, someone else) where possible

✓For upward nos, it frames the trade-off and leaves the decision with them

✓There's a prepared line to hold the boundary if pushed

⚠️ What it refuses to do

Do not give a false maybe — "let me see" to avoid the moment creates a worse letdown later

Do not over-justify — a long list of reasons sounds defensive and invites picking each apart

Do not say a flat "no" to a boss when a trade-off works better — make the cost visible, let them choose

Do not apologise excessively — "I can't take this on" is fine; grovelling undermines the boundary

Do not cave on first pushback — decide the line beforehand and have a response ready

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-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="saying-no"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Saying No is one of 599 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog