AA pad-mode
Turn messy requests into structured plans. PAD Mode (Plan → Act → Deliver) gives your AI agent project management superpowers — automatic task breakdown, live progress tracking, sub-agent parallel execution, and human approval gates. Use /pad for complex tasks that need more than a single-shot answer. Perfect for plan mode, project planning, task planning, workflow planning, and multi-step execution. Triggers: 1. Slash command: "/pad" in conversation 2. Explicit keywords: "pad mode", "plan mode", "make a plan", "plan this out" 3. Auto-detect: When the user's request is complex (3+ distinct tasks, multi-file changes, architectural decisions, or ambiguous requirements), proactively suggest entering PAD mode. Use when: user wants structured execution tracking for non-trivial tasks, not for simple one-shot questions or commands.
As a process A 82/100 · Runs to the end — 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: 5. 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 82/100
- 30Inputs and preconditions. Does not say what the process needs to start
- 40Result and completion. Does not say what the result is
- 85Steps. 119 steps, 2 vague phrases
- 100Tools and files. No external tools needed
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 13 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3073 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 13 top-level sections: this looks like several domains in one skill
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 838: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -228 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 19 headings
- +3Step-by-step instructions: 119 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.