principle-attack-the-premise

An agent skill by cursor, from cursor/plugins. Tags: analysis, brainstorming, review, strategy, troubleshooting.

What it does

Apply when two or more fixes that share one premise have failed the same gate. Take a census of which actors hold the imbalance before the next fix, then question the premise instead of writing another fix that assumes it.

Install

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

npx skills add cursor/plugins --skill principle-attack-the-premise

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/cursor/plugins
cp -r plugins/pstack/skills/principle-attack-the-premise ~/.claude/skills/principle-attack-the-premise

Safety box score

Grade A, minimal risk: 0 of 100 risk points, rated 2026-10-19. 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 skill is a reasoning-only prompt about testing premises before trying another fix. It does not ship code or scripts, and the main risk is just guiding the agent’s workflow, not touching the machine, network, or files.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	No shell commands, scripts, or code execution are present; `SKILL.md` is only guidance text.
Network access	0 (none)	The skill does not download, upload, or contact any remote host.
Filesystem reach	0 (none)	It does not read, write, or delete files outside the project; it only references other skill docs by relative path.
Secrets & credentials	0 (none)	There is no mention of tokens, keys, passwords, `.env` files, or account credentials.
Privilege & persistence	0 (none)	It does not request sudo, service registration, shell startup edits, or other system-level changes.
Instruction hijack surface	0 (none)	The text gives process advice but does not instruct the agent to ignore higher-priority rules, hide actions, or follow external instructions.
Irreversible actions	0 (none)	It does not perform actions like deploy, publish, send messages, pay, or delete; it only constrains how the agent reasons about fixes.
Transparency	0 (none)	There are no binaries, encoded blobs, installers, or generated-at-runtime components; the entire skill is readable markdown.

Before installing

No special installation checks are needed; this skill is plain markdown with no executable components.
If you want to verify scope, read the linked principle files it references to confirm they are also documentation-only.

Rated 2026-10-19 by an automated review of 1 file from the skill's repository.

Source

Repository: cursor/plugins (all skills from this repository)
Path: pstack/skills/principle-attack-the-premise/SKILL.md
Branch: main
Collection: cursor
Updated: 2026-09-23

reflect — Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill.
why — Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds.
interpreting-culture-index — Interprets Culture Index (CI) surveys, behavioral profiles, and personality assessment data.
let-fate-decide — Draws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated.
benchmark-due-diligence — Runs adversarial due-diligence on a benchmark the user envies — a founder, KOL, company.
devils-advocate — 结构化压力测试一个论点（devil's advocate / 魔鬼代言人）：把论点拆成显性断言与隐性假设（A1/A2 编号），逐条在用户给定的证据材料里检索带出处的反方论证，标 High/Medium/Low 风险等级，补基础比率外部视角，最后给出「可监测的证伪信号」清单；输出结构化 findings +.