CC nex-pricewatch
Competitive price monitoring and alert system for tracking competitor and supplier pricing across websites. Monitor pricing pages from competitors (concurrenten) using CSS selectors, XPath, or regex patterns to extract prices from dynamic and static websites. Automatically detect when competitors change their pricing (prijs wijzigen) and receive alerts when prices increase or decrease significantly. Configure custom alert thresholds for price movements (default: 5% increases, 10% decreases). View complete price history with timestamps, identify pricing trends (UP, DOWN, STABLE), and compare price changes over time. Track multiple pricing targets per competitor to monitor different product tiers, packages, or bundles. Optional Telegram notifications alert you immediately when prices change. Export price history data in CSV or JSON formats for competitive analysis, pricing strategy reviews, and business decision-making. Perfect for Belgian agencies, resellers, and business owners who need to monitor competitor pricing, adjust their own rates competitively, and stay informed about market changes. All price tracking data remains local and private.
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, 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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Shorten the description to 1024 characters.
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Dangerous commands
cmd-shell-rcREADME.md:327Writes to a shell startup fileecho 'export NEX_PRICEWATCH_TELEGRAM_BOT_TOKEN="token"' >> ~/.bashrc
-
medium Dangerous commands
cmd-shell-rcREADME.md:328Writes to a shell startup fileecho 'export NEX_PRICEWATCH_TELEGRAM_CHAT_ID="id"' >> ~/.bashrc
-
low Exfiltration
exfil-webhook-urllib/alerter.py:203Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)url = f"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/sendMessage"placeholder -
low Exfiltration
exfil-webhook-urlREADME.md:315Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)- Get ID from https://api.telegram.org/bot<TOKEN>/getUpdates
placeholder
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1161 chars, limit 1024 - warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Competitive price monitoring and alert system for tracking competi… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
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
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 74 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2063 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 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 1161: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 37 headings
- +3Step-by-step instructions: 74 items
- +4Has examples (19 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 47.