AC quests
Track and guide humans through complex multi-step real-world processes. Use when a user needs help with a bureaucratic, legal, technical, or any multi-step procedure that requires organized tracking, step-by-step guidance, and progress monitoring. Triggers on requests like "help me with this process", "guide me through", "track this project", "create a quest", or any complex task that benefits from being broken into manageable steps presented one at a time. Also triggers for existing quests: "how's my quest going", "what's next on [process]", "update my progress". This is for multi-session/multi-day processes, not simple one-off tasks. The quest replaces scattered memory files — it IS the memory for long-running processes.
Track and guide humans through complex multi-step real-world processes.
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 14 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 65 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1647 tokens
- 100Progress reporting. Reports progress
- low The response is described with custom markup (38 tags): a typed call is more reliable
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 732: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 65 items
- +4Has examples (2 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.