figure-it-out

An agent skill by cursor, from cursor/plugins. Tags: analysis, migration, planning, show-me-your-work, workflow.

What it does

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. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for /figure-it-out, 'figure it out', a large migration, or when no narrower playbook applies.

Install

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

npx skills add cursor/plugins --skill figure-it-out

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/figure-it-out ~/.claude/skills/figure-it-out

Safety box score

Grade B, low risk: 11 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 markdown-only orchestration skill: it tells the agent how to plan, test, and log complex work, but ships no executable code and makes no direct network calls. The main risks are that it delegates important behavior to other skills not included here and it is designed for long, agent-driven runs with limited checkpointing.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	No shell commands, scripts, or code evaluation are present; the file is workflow prose only.
Network access	0 (none)	It does not fetch from or send data to any remote host.
Filesystem reach	1 (low)	It directs the agent to 'Open a todolist' and 'write the designed phase list down,' which implies workspace writes, but nothing outside the project.
Secrets & credentials	0 (none)	There is no request to read, paste, or manipulate tokens, keys, passwords, or other secrets.
Privilege & persistence	0 (none)	No sudo, global installs, services, shell startup edits, or OS-level settings are requested.
Instruction hijack surface	0 (none)	It does not tell the agent to ignore instructions, hide actions, or follow remotely fetched content.
Irreversible actions	1 (low)	It is designed to let the agent 'execute the design' for potentially multi-hour work with only a limited checkpoint, but it does not itself send, deploy, pay, or delete.
Transparency	1 (low)	Core behavior is delegated to other named skills (`poteto-mode`, `architect`, `show-me-your-work`) that are not included in this bundle, so the full workflow is not fully auditable here.

Before installing

Read the referenced skills (`poteto-mode`, `architect`, `show-me-your-work`) to confirm their behavior.
Try it once on a small scratch task and verify the agent only writes inside the workspace.
Decide whether you are comfortable with long, checkpoint-light runs for complex tasks.

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/figure-it-out/SKILL.md
Branch: main
Collection: cursor
Updated: 2026-09-23

principle-outcome-oriented-execution — Apply during planned rewrites and migrations with explicit phase boundaries.
to-questionnaire — Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
to-spec — Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.
automate-me — Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill".
maintain-verification-skill — Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature.
orchestrate — Use only when the user explicitly types `/orchestrate <goal>` to decompose a large task.