AC heatmap-analyze
Ptengine Heatmap end-to-end analysis skill. Fetches real heatmap data via ptengine-cli and runs AI-powered CRO behavior analysis using a 4-stage psychology model. Self-contained — includes all analysis methodology, data transformation rules, and output schemas. Use this skill when the user wants to: analyze a webpage's heatmap data, understand user behavior on a page, compare audience segments, validate A/B test results, evaluate ad channel performance, analyze audience characteristics, find conversion barriers or opportunities, or optimize a landing page. Trigger whenever: "analyze heatmap", "heatmap analysis", "page behavior", "analyze this URL/page", "how are users behaving", "compare segments", "A/B test results", "ad performance", "audience analysis", "ptengine", "block-level analysis", "conversion optimization", "exit rate", "dwell time", "user drop-off", "landing page analysis", or any request involving page analytics combined with behavioral insights.
As a process C 60/100 · Has gaps — weak spots: result and completion, consistency, 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
- 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 Dangerous commands
cmd-pipe-to-shell-known-hostreferences/ptengine-cli.md:9Pipe-to-shell installer from a well-known host (still executes remote code)curl -sSL https://raw.githubusercontent.com/Kocoro-lab/ptengine-cli/v0.1.0/scripts/install.sh | sh
Files scanned: 14. 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 60/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (heatmap-analyze) differs from the folder (pte-heatmap-analyze)
- 60Tools and files. Uses tools (bash, web) 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
- 85Steps. 26 steps, 1 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 2495 tokens
- low 11 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 973: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 16 example trigger phrases
- +4Structure: 20 headings
- +3Step-by-step instructions: 26 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (11 of 11)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.