AB masterplan-builder
Build a complete, production-ready masterplan for a new project/system from scratch (0 to 100%) — websites, web apps, mobile apps, local AI assistants/agents, desktop apps, backend/APIs, browser extensions, CLI tools, etc. Use whenever the user wants to plan, design, or scope a new project/product before or instead of writing code — e.g. "help me plan/build/design a [website/app/assistant]", "I want to create a project for X", "buatkan masterplan untuk...". Not for reviewing an existing plan (use dev-plan-reviewer) or quick one-off scripts. Interviews the user topic by topic (name, users, tech stack, features, database, frontend/backend integration, and more, down to the smallest detail), researches current best options live on the web for every major decision instead of relying on stale training knowledge, and outputs a markdown masterplan saved to docs/masterplan/ in the project directory — detailed enough that code built from it is production-ready, nothing left at prototype quality.
Build a complete, production-ready masterplan for a new project/system from scratch (0 to 100%) — websites, web apps, mobile apps, local AI assistants/agents…
As a process B 78/100 · Nearly there — weak spots: result and completion, inputs and preconditions
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 78/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Result and completion. Does not say what the result is
- 85Steps. 11 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2526 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +3Description length 1001: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 10 headings
- +3Step-by-step instructions: 11 items
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.