Menu
Improve a plan by asking a subagent to generate an alternative perspective, then comparing and combining results. Use when a plan already exists in the conversation and the user wants a second opinion, broader coverage, or to catch blind spots.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Write a "megaplan" planning notebook — a long-form Markdown doc for a multi-slice project that tracks scope, decisions, requirements, risks, and grounded research facts with cross-referenced IDs. Use when the user asks to write up a project plan, planning notebook, or "megaplan" doc, especially one spanning multiple tickets/PRs where decisions and raw research need to be preserved for later reference. Also use when bootstrapping a new megaplan from a vague idea. Use this skill every time you work on a `*.megaplan.md` file, or a Markdown file that has a work plan with tickets.
Strengthen a plan by running it through a subagent review loop — catching inaccuracies and oversights before execution.
Help the user develop a vague idea into a "plan" — a scoped, handoff-ready statement of intent
When the user has PR review feedback to address, CI failures to fix, or wants to automatically resolve common PR issues. Use when the user says "fix the PR," "address review comments," "CI is failing," "fix the build," "autofix," "pr feedback," "resolve comments," "fix merge conflicts," "babysit the PR," or when a PR needs updates before merge. Reads the review comments, diagnoses issues, and applies fixes.
Review code changes and return a prioritised list of issues — posted as GitHub PR review threads when a PR exists, or as plain text otherwise. Use when asked to review a PR, diff, or implementation for correctness, code quality, reuse, efficiency, safety, or test quality. When invoking, pass available details - the plan, git change range, files to review.
Iterative code review loop against a GitHub PR — atk-code-review posts findings as self-review threads, this skill fixes, replies, and resolves them, up to 10 passes.
| name | triangulate-plan |
| description | Improve a plan by asking a subagent to generate an alternative perspective, then comparing and combining results. Use when a plan already exists in the conversation and the user wants a second opinion, broader coverage, or to catch blind spots. |
Generates an independent second opinion on an existing plan and merges the best of both.
Find the plan produced earlier in this conversation. If none exists, abort.
From the existing plan, distill a brief containing only:
Do not include: implementation steps, tests to write, or any detail that wasn't in the original request. In particular, when the plan extends an existing system (a rules engine, enum, schema, classifier), do not leak which extension point the existing plan chose — name the target system and let the subagent pick its own. A second opinion that inherits the first plan's axis can't catch a wrong-axis mistake.
Use the brainstorm skill to generate an independent plan from the same brief:
Use brainstorm skill. Formulate a plan. Do not write a Markdown file — reply with the plan itself. Brief: {brief contents}
Compare the new plan against the existing one. Assess:
When both plans extend an existing system, also run these checks:
Present the assessment for the user to decide.
For subagent, use oracle agent type if available.
