AB clear-task
Transform broad, ambiguous, or early-stage user requirements into executable work through Stage1 requirement understanding, Stage2 clarification, a required user confirmation gate, and Stage3 internal expert-guided task packaging. Use when Codex needs to understand a user's idea, model a workflow/product/tool/game/document request, ask precise follow-up questions, recommend defaults, produce a user-confirmable requirement handoff, let the user revise the requirement description or requirement details, and only after explicit confirmation continue with Codex, Claude, OpenClaw, coding agents, writing agents, product agents, design agents, testing agents, or workflow-building agents. Do not show the Stage3 package by default; use it as internal execution context unless the user asks to inspect, export, or review it.
As a process B 73/100 · Nearly there — weak spots: inputs and preconditions, consistency
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: 7. 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 73/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (clear-task) differs from the folder (cleartask)
- 50When it triggers. No condition that starts the skill
- 70Failures and branches. 6 branches
- 85Steps. 68 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Result and completion. Output format and completion criterion are stated
- 100Execution cost. Instruction body is 1861 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 10 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 824: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 11 headings
- +3Step-by-step instructions: 68 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.