AB amazon-daily-market-radar
Automated daily Amazon market digest. Given the user's own ASINs (1-10) and any competitor ASINs (up to 20), produces a daily change-detection briefing: price moves, BSR shifts, new entrants in the surrounding category, review wave detection, stockout signals. Output is a triaged alert dashboard (RED/YELLOW/GREEN) comparing today against yesterday's snapshot. Designed for unattended scheduled automation (cron-style daily run). Use when the user EXPLICITLY requests ongoing OPERATIONAL daily monitoring of their products and the surrounding market — a "what changed since yesterday" digest. Use when user asks: set up daily market monitoring for my ASINs, run my daily radar, what changed in my tracked market since yesterday, daily briefing on my tracked ASINs and competitors, emerging-brand or stockout alerts on my watchlist. Establishing monitoring and recurring runs always require the user's explicit opt-in — do not activate on vague update questions. Requires ZOODATA_API_KEY.
As a process B 79/100 · Nearly there — weak spots: running it twice
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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Exfiltration
net-redirectable-api-keyscripts/zoodata.py:74Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
Files scanned: 9. 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 79/100
- 30Running it twice. 6 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 36 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3408 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 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 988: 120–800 characters recommended
- +4No input/output examples
- -275 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +4Structure: 23 headings
- +3Step-by-step instructions: 36 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.