strategy-red-team

An agent skill by phuryn, from phuryn/pm-skills. Tags: debugging, design, documents.

What it does

Red-team a PRD, roadmap, or strategy by attacking its load-bearing assumptions before reality does. Steelmans then attacks each claim, ranks failure modes by impact × likelihood × cheapness-to-test, and returns the cheapest test and kill criteria for each. Use when stress-testing a plan, pressure-testing a strategy, challenging assumptions, or preparing a doc for executive review.

Install

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

npx skills add phuryn/pm-skills --skill strategy-red-team

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-execution/skills/strategy-red-team ~/.claude/skills/strategy-red-team

Safety box score

Grade A, minimal risk: 5 of 100 risk points, rated 2026-10-18. 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 pure analysis/writing skill: it reads a plan and returns a red-team critique with assumptions, tests, and kill criteria. It does not ship code, touch files, call services, or require credentials; the main notable issue is light role/instruction framing, not operational risk.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	No shell commands, code evaluation, or native scripts are present; the only content is `SKILL.md` prose.
Network access	0 (none)	It contains only static reference links in the `Further Reading` section and does not fetch or send anything automatically.
Filesystem reach	0 (none)	There are no instructions to read, write, or delete local files outside the provided prompt.
Secrets & credentials	0 (none)	It does not ask for tokens, passwords, `.env` files, browser sessions, or other credentials.
Privilege & persistence	0 (none)	No sudo, installs, services, shell/profile edits, or OS-level changes are requested.
Instruction hijack surface	1 (low)	The skill explicitly instructs a persona shift — `You are a sharp, fair adversary` — which counts as role/instruction framing, but it does not tell the agent to ignore higher-priority instructions or hide anything.
Irreversible actions	0 (none)	It only analyzes a user-provided plan and formats a critique; it does not deploy, send, purchase, or modify external systems.
Transparency	0 (none)	There are no binaries, generated blobs, minified code, or uninspectable installers; the entire skill is readable markdown.

Before installing

Read `SKILL.md`; it is documentation-only and contains no executable setup.
If you care about tone constraints, verify the persona language (`sharp, fair adversary`) fits your use case.
No special sandboxing or credential checks are needed for this skill.

Rated 2026-10-18 by an automated review of 1 file from the skill's repository.

Source

Repository: phuryn/pm-skills (all skills from this repository)
Path: pm-execution/skills/strategy-red-team/SKILL.md
Branch: main
Updated: 2026-09-19

writing-guidelines — Review docs/prose for Writing Guidelines compliance.
design-md — Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files
stitch::extract-static-html — Extract self-contained static HTML from a built web application or React components by inlining CSS and images.
stitch::manage-design-system — Manage design systems in Stitch using MCP tools. Includes retrieval of assets, creating/updating design systems in Stitch, and applying them to screens.
create-prd — Create a Product Requirements Document using a comprehensive 8-section template covering problem, objectives, segments, value propositions, solution.
customer-journey-map — Create an end-to-end customer journey map with stages, touchpoints, emotions, pain points, and opportunities.