Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

ulw-plan — Planning Consultant (Prometheus)

Turns a vague or large request into one decision-complete work plan: explores the codebase first, asks only the real forks, and writes the plan only after your explicit okay.

Dev & CodingAdvanced★ 67,531⑂ 5,507AI score 7/10Last updated: Aug 9, 2026

What it does

ulw-plan puts Claude into a strict planning persona ("Prometheus") that never touches product code.

  • Runs parallel read-only exploration (and outside research when the repo can't answer) before asking anything.
  • Classifies your request as CLEAR (outcome known) or UNCLEAR (fuzzy) and announces the verdict. CLEAR → asks only genuine owner-decisions; UNCLEAR → adopts and announces best-practice defaults instead of interviewing you.
  • Hard approval gate: nothing is written until you explicitly say okay, and approval authorizes writing the plan only — execution happens later in a separate worker session.
  • Emits .omo/drafts/<slug>.md (compaction-safe resume point) and, after approval, .omo/plans/<slug>.md with column-zero task rows (- [ ] 1. …, verifiers - [ ] F1. …), references, acceptance criteria, agent-executed QA, and commit units.
  • Saying "high accuracy" anywhere flips on a mandatory dual review (momus + an independent CLI review).

Who it's for

  • Developers who want the design locked down before handing a big refactor or feature to an agent.
  • Anyone tired of agents interrupting mid-implementation with clarifying questions.
  • Tech leads who need a reviewable plan artifact for the team.
  • Overkill for one-line fixes and quick edits.

Examples

  1. "ulw-plan: migrate our payment layer from Stripe to Adyen" → maps every call site, asks only about webhook verification and pinned SDK version, then writes a ~20-task plan after approval.
  2. "make auth better" → routed UNCLEAR: no interview, best-practice defaults researched and announced, high-accuracy review runs automatically.
  3. "add a 5/min-per-IP rate limit to /login, high accuracy" → CLEAR + review_required: minimal questions, plan written, dual review result reported before handoff.

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the packages/omo-codex/plugin/components/ultrawork/skills/ulw-plan folder from the GitHub repo code-yeongyu/oh-my-openagent into my ~/.claude/skills/ulw-plan/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/code-yeongyu/oh-my-openagent.git /tmp/oh-my-openagent && mkdir -p ~/.claude/skills && cp -r /tmp/oh-my-openagent/packages/omo-codex/plugin/components/ultrawork/skills/ulw-plan ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repo: git clone https://github.com/code-yeongyu/oh-my-openagent.git /tmp/oh-my-openagent
  3. Create the skills directory: mkdir -p ~/.claude/skills
  4. Copy the whole skill folder (its references/ and scripts/ subfolders are required): cp -r /tmp/oh-my-openagent/packages/omo-codex/plugin/components/ultrawork/skills/ulw-plan ~/.claude/skills/
  5. Verify Node.js is available with node -v (the scripts/scaffold-plan.mjs scaffolder needs Node or bun).
  6. Restart Claude Code and type something like ulw-plan this feature. You should see ULW-PLAN MODE ENABLED! as the first line.
  7. Artifacts land in .omo/drafts/ and .omo/plans/ inside your project — add them to .gitignore if you don't want them committed.
View source on GitHub ↗License: NOASSERTION