AB deep-planner
A meta-skill that activates before complex tasks to enforce structured planning, step-by-step execution, and self-reflection. Works like Claude Code's TodoList — generates a visible task plan, persists it to `.todolist/`, checks off steps as they complete, and pauses at critical decision points for user confirmation. Trigger this skill whenever: - The request involves 3+ steps or multiple tools/skills chained together - Keywords like "research", "analyze", "plan", "design", "compare", "write a report" appear - Key variables are undefined (audience, platform, format, scope, constraints) - The domain is unfamiliar or information may be time-sensitive - A task requires coordinating more than one other skill This skill does NOT produce the final output — it plans and supervises execution, then delegates to the appropriate domain skills (e.g. web search, code execution, platform-specific skills). Think of it as the project manager, not the worker.
As a process B 66/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
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: 3. 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 66/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 60Failures and branches. 2 branches
- 100Tools and files. No external tools needed
- 100Steps. 16 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 1455 tokens
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 958: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Structure: 14 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.