AB chat-with-anyone
Chat with any real person or fictional character in their own voice by automatically finding their speech online, extracting a clean reference sample, and generating audio replies. Also supports generating a matching voice from an uploaded image. Use when the user says "我想跟xxx聊天", "你来扮演xxx跟我说话", "让xxx给我讲讲这篇文章", "我想跟图片中的人说话", or similar.
As a process B 65/100 · Nearly there — weak spots: result and completion, consistency, progress reporting
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.
The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.
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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Secrets in code
secret-labelled-tokenscripts/voice_design.py:149Labelled token / key literal (vendor format unknown — verify it is not a live credential)api_key = norm…e64(api_key)
-
low Secrets in code
secret-password-literalscripts/voice_design.py:149Hard-coded password / key literal (may be an example)api_key = norm…e64(api_key)
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "permissions"
Process rating: all ten parameters 65/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (chat-with-anyone) differs from the folder (noizai-chat-with-anyone)
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 31 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Execution cost. Instruction body is 2062 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 4 example trigger phrases
- +3Description length 338: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 31 items
- +4Has examples (12 code blocks)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.