AB backlog-planner
Turn a feature idea, conversation context, or rough notes into researched, detailed, dependency-ordered checkbox tasks appended to the project's roadmap/backlog file — exactly the format goal-runner consumes, so a fresh unattended session can execute them. Grounds every task in the actual codebase before writing it (grep/read or Explore scouts; think-like-fable rigor if installed), puts what + done-when on the checkbox line with verified files, acceptance criteria, and a verification command in plain sub-bullets, and labels assumptions. Appends to the existing ROADMAP.md/BACKLOG.md/TODO.md; when none exists it asks once and defaults to ROADMAP.md. Use this skill whenever the user says "add this to the backlog", "add it to the roadmap", "plan these tasks", "break this down into tasks", "capture this as roadmap tasks", "turn these notes into a task list", or "/backlog-planner" — even if they don't name the skill. Not for executing tasks (goal-runner, task-executor, autopilot) — this writes the plan only.
Turn a feature idea, conversation context, or rough notes into researched, detailed, dependency-ordered checkbox tasks appended to the project's…
As a process B 76/100 · 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: 2. 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 76/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Result and completion. Does not say what the result is
- 55Failures and branches. 1 branches
- 100Tools and files. No external tools needed
- 100Steps. 44 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2458 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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 1017: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- -212 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 11 headings
- +3Step-by-step instructions: 44 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.