value-prop-statements

An agent skill by phuryn, from phuryn/pm-skills. Tags: copy-editing, documents, marketing, office.

What it does

Generate value proposition statements for marketing, sales, and onboarding from existing value propositions. Use when writing marketing copy, creating sales messaging, or crafting onboarding messages.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add phuryn/pm-skills --skill value-prop-statements

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/phuryn/pm-skills
cp -r pm-skills/pm-marketing-growth/skills/value-prop-statements ~/.claude/skills/value-prop-statements

Safety box score

Grade A, minimal risk: 5 of 100 risk points, rated 2026-10-17. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This is a documentation-only prompt skill for generating marketing/value-proposition copy from user-provided inputs. It does not ship code, run commands, or touch files; the main consideration is that it asks the model to adopt a persuasive marketing persona and includes one external reference link.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	No scripts, shell commands, or code execution are included; the skill is a single markdown prompt file.
Network access	0 (none)	It does not instruct any fetch/upload/API call; the only outbound reference is a static "Further Reading" link in the markdown.
Filesystem reach	0 (none)	There are no read/write/delete instructions for local paths, dotfiles, or project files.
Secrets & credentials	0 (none)	The skill never asks for tokens, passwords, .env contents, keychains, or other secrets.
Privilege & persistence	0 (none)	No sudo, installs, services, shell startup edits, or global system changes are mentioned.
Instruction hijack surface	1 (low)	The prompt sets a persona — "You are an experienced product growth expert" — but it does not ask the agent to ignore higher-priority instructions or fetch remote content.
Irreversible actions	0 (none)	It only generates copy for marketing/sales/onboarding; it does not send messages, deploy, publish, pay, or modify external systems.
Transparency	0 (none)	The entire skill is readable markdown; there are no binaries, encoded blobs, or generated installers.

Before installing

Read `SKILL.md` end-to-end; it is documentation-only and should not execute anything.
If your agent can browse, decide whether you want it to follow the external "Further Reading" link at all.
No sandboxing or secret rotation is needed for this skill, since it does not access files, credentials, or network APIs.

Rated 2026-10-17 by an automated review of 1 file from the skill's repository.

Source

Repository: phuryn/pm-skills (all skills from this repository)
Path: pm-marketing-growth/skills/value-prop-statements/SKILL.md
Branch: main
Updated: 2026-09-19

google-docs — Author and edit Google Docs with the google-docs tools - structured writing, character and paragraph styling, lists, tables, images, headers/footers.
draft-nda — Draft a detailed Non-Disclosure Agreement between two parties covering information types, jurisdiction, and clauses needing legal review.
grammar-check — Identify grammar, logical, and flow errors in text and suggest targeted fixes without rewriting the entire text.
gtm-strategy — Create a go-to-market strategy covering marketing channels, messaging, success metrics, and launch timeline.
privacy-policy — Draft a detailed privacy policy covering data types, jurisdiction, GDPR and compliance considerations, and clauses needing legal review.
release-notes — Generate user-facing release notes from tickets, PRDs, or changelogs.