From mlforge
This skill should be used when the user wants a fully reviewed ML plan in one pass — when they say "autoplan", "plan this end to end", "run the full planning pipeline", "take this from idea to plan", or want framing + design + experiment + eval planning chained automatically with only judgment calls surfaced.
How this skill is triggered — by the user, by Claude, or both
Slash command
/mlforge:ml-autoplanThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
One command, fully reviewed plan. Chains the planning skills in sprint order with the iron laws encoded as decision principles — surfacing only genuine judgment calls to the user.
One command, fully reviewed plan. Chains the planning skills in sprint order with the iron laws encoded as decision principles — surfacing only genuine judgment calls to the user.
ml-office-hours → ml-system-design → experiment-design → model-evaluation (eval plan)
PROBLEM.md DESIGN.md pre-registration EVAL_PLAN.md
Run each stage's skill in full. Skip a stage only when its artifact already exists and is current (offer to reuse, don't assume).
[unverified].Batch these — one consolidated question round per stage maximum, not a drip.
A single plan document stitching the four artifacts, plus the gate ledger updated with problem_framed, design_reviewed, pre_registered, eval_plan entries. End with the execution strategy: dry-run on 1% → 1 epoch/short run → full run, with a verify step per stage, and the instruction to log the first experiment via ml-experiment-journal before any code runs.
experiment-design — autoplan on a tweak is ceremony, and the principles skill forbids ceremony.Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
npx claudepluginhub mbburabak/mlforge --plugin mlforge