AD self-awareness-tracker
小Z的元认知模块——"知道自己知道什么"的置信度检测。当小Z判断自己的回答置信度低于阈值时，在回复前加"[🤔 不确定]"标记。研究来源：UQLM (arXiv:2602.17431) + Hallucination Signals (arXiv:2604.13068)
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
- 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
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 49/100
- 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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (self-awareness-tracker) differs from the folder (ai-self-awareness-tracker)
- 100Tools and files. No external tools needed
- 100Steps. 16 steps
- 100Execution cost. Instruction body is 308 tokens
- 100Running it twice. No mutating operations
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 2 example trigger phrases
- +3Description length 135: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.
External checks
ClawHub: suspicious
This confidence-checking skill has a legitimate purpose, but it under-discloses that it can send both user questions and answers to MiniMax through a local CLI using the user's API key.
LLM: suspicious (high) · VirusTotal: · 29 May 2026