BD emoPAD-universe
emoPAD Universe - Emotion Universe Skill Helps users locate emotions in the PAD (Pleasure-Arousal-Dominance) coordinate system, and provides emoNebula feature: continuous real-time emotion PAD monitoring, with a popup window displaying the emotion nebula chart every 5 minutes. ## Cross-Platform Support Supports Linux and Windows operating systems: - **Linux**: Uses eog (Eye of GNOME) to display image windows - **Windows**: Uses the system default image viewer to display ## Auto-Start After installing this skill, the emoPAD service and emoNebula will start automatically, no manual operation needed. ## Supported Hardware - EEG: KSEEG102 (Bluetooth BLE) - PPG: Cheez PPG Sensor (Serial) - GSR: Sichiray GSR V2 (Serial) Theoretically, similar devices should also work. Future versions will gradually add support for mainstream brands, including: - Muse series EEG devices - Emotiv EEG devices - Oura Ring smart ring - Whoop smart wristband - Other mainstream EEG devices and wearable devices ## Dependency Installation Dependencies will be checked and installed automatically when installing the skill, no manual operation needed. ## Usage - `openclaw emopad status` - Get current PAD status - `openclaw emopad snapshot` - Manually generate emotion nebula chart - `openclaw emopad stop` - Stop service - `openclaw emopad start` - Restart service ## Important Notes **About Emotion PAD Calculation**: Currently based on heuristic methods, mapping relationships summarized from extensive literature. This method temporarily cannot reflect individual differences. Future versions will introduce personalized calibration training modules to truly achieve personalized emotion recognition.
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Dangerous commands
cmd-eval-dynamicemopad_cli.py:211Dynamic code execution from decoded/untrusted inputos.system(f"xdg-open {output_path} &")
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1703 chars, limit 1024 - warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
description-budgetdescription takes 1703 of the ~15000-char shared budget for all skills
Process rating: all ten parameters 46/100
- 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
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 27 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 854 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
- +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 1702: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +4Structure: 14 headings
- +3Step-by-step instructions: 27 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 46.