principle-outcome-oriented-execution

An agent skill by cursor, from cursor/plugins. Tags: architecture, delivery, migration, planning, workflow.

What it does

Apply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't preserve smooth intermediate states with throwaway compatibility code.

Install

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

npx skills add cursor/plugins --skill principle-outcome-oriented-execution

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-outcome-oriented-execution ~/.claude/skills/principle-outcome-oriented-execution

Safety box score

Grade A, minimal risk: 4 of 100 risk points, rated 2026-10-16. 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 workflow skill for planned rewrites and migrations. It does not ship code or touch the machine directly, but it does explicitly endorse planned intermediate breakage in service of reaching the target architecture.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	`SKILL.md` is plain guidance text only; there are no scripts, shell commands, or code execution paths.
Network access	0 (none)	The file contains no download, upload, API, or remote-host communication behavior.
Filesystem reach	0 (none)	It does not read, write, or delete files; it only describes migration strategy.
Secrets & credentials	0 (none)	There is no request to access tokens, keys, passwords, or other credentials.
Privilege & persistence	0 (none)	No sudo, global install, service registration, or OS-setting changes are present.
Instruction hijack surface	0 (none)	The text does not instruct the agent to ignore its rules, hide anything, or follow external instructions.
Irreversible actions	1 (low)	It intentionally permits `Intermediate breakage` during `planned rewrites and migrations`, which affects how aggressively an agent may act during a migration.
Transparency	0 (none)	There are no binaries, minified blobs, or decoded-at-runtime artifacts; the entire skill is readable markdown.

Before installing

Use it only for a migration plan with explicit rollback and verification checkpoints.
Confirm you are comfortable with temporary breakage in the touched area before enabling it.
Do not use it for routine maintenance or incremental feature work.

Rated 2026-10-16 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-outcome-oriented-execution/SKILL.md
Branch: main
Collection: cursor
Updated: 2026-09-23

figure-it-out — Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away.
principle-sequence-verifiable-units — Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs.
expo-project-structure — Framework (OSS). Folder structure for a new Expo app.
architect — Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.
new-branch-and-pr — Create a fresh branch, complete work, and open a pull request
orchestrate — Use only when the user explicitly types `/orchestrate <goal>` to decompose a large task.