What do I need to use Scope Creep Response?

What the agreement actually says; The asks so far; Relationship context; Their goal.

Is Scope Creep Response 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.

Scope Creep Response

Q: How do I know the Scope Creep Response output is good?

The skill verifies itself against its own quality checks: Classification quotes the agreement (or names its absence as the root cause); The client's interpretation is steelmanned before being answered; Goodwill grants are labeled as such in the wording — never silent; The send-ready text is warm; the boundary lives in the process, not the tone.

🔵 Stable🕐 updated 2026-07-17 🔷 SkillSpec L3 pm-freelance

Handle scope creep on client work without torching the relationship — classify the ask against the agreement, respond with the goodwill/change-order/renegotiate move that fits, and install the prevention language for next time. Use when asked my client keeps adding requests, is this scope creep, how do I say that's out of scope nicely, or write a change order email. Produces the classification of the ask, the graduated response with ready-to-send wording, and the contract language that prevents the rerun.

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

What to give it

▸What the agreement actually says — the scope text verbatim; if scope was never written down, that's the finding, and the response changes (you can't cite what doesn't exist)

▸The asks so far — list them; one gray-zone request and a drip of twelve "tiny things" are different situations

▸Relationship context — client value, history, how earlier extras were handled (silently absorbed extras set precedent that must be un-set gently)

▸Their goal — keep the client happily, get paid for the extras, or exit gracefully — the same classification routes to different responses

✅ 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.

✓Classification quotes the agreement (or names its absence as the root cause)

✓The client's interpretation is steelmanned before being answered

✓Goodwill grants are labeled as such in the wording — never silent

✓The send-ready text is warm; the boundary lives in the process, not the tone

✓Prevention language included whenever the pattern is recurring

⚠️ What it refuses to do

Do not absorb silently — every unlabeled extra resets the baseline

Do not meet a gray-zone ask with contract-lawyer tone — ambiguity is shared fault

Do not litigate the past on an unwritten scope — define forward instead

Do not fight the twelfth small ask individually — name the pattern and sell the structural fix

Do not say "no" where "yes, via change order" or "yes, in phase 2" is true — those keep the relationship AND the boundary

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="scope-creep-response"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Scope Creep Response is one of 591 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog