The method for finding the gap between what a system is supposed to do and what the code actually does — the class of bug generic scanners miss because they have no model of intent. Defines what counts as documented intent, what counts as implementation evidence, which mismatches matter, and how to avoid hand-wavy findings.
安装
npx skills add phuryn/pm-skills --skill intended-vs-implementednpx skills add phuryn/pm-skills --skill intended-vs-implemented -a claude-code -gnpx skills add phuryn/pm-skills --skill intended-vs-implemented -a codex -ggemini skills install https://github.com/phuryn/pm-skills.git --path pm-ai-shipping/skills/intended-vs-implementedgh skill install phuryn/pm-skills intended-vs-implementedgit clone --depth 1 https://github.com/phuryn/pm-skills /tmp/phuryn__pm-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/phuryn__pm-skills/pm-ai-shipping/skills/intended-vs-implemented ~/.claude/skills/intended-vs-implemented # Claude Code
cp -R /tmp/phuryn__pm-skills/pm-ai-shipping/skills/intended-vs-implemented ~/.agents/skills/intended-vs-implemented # Codex, Cursor, Gemini CLI, Copilot, OpenCode