BC videochat-withme
Real-time AI video chat that routes through your OpenClaw agent. Uses Groq Whisper (cloud STT), edge-tts (cloud TTS via Microsoft), and OpenClaw chatCompletions API for conversation. Your agent sees your camera, hears your voice, and responds with its own personality and memory. Requires: GROQ_API_KEY for speech recognition. Reads ~/.openclaw/openclaw.json for gateway port and auth token. Data flows: audio → Groq cloud (STT), TTS text → Microsoft cloud (edge-tts), camera frames (base64) + text → OpenClaw gateway → your configured LLM provider (may be cloud — frames leave the machine if using a cloud LLM). Installs a persistent launchd service (optional). Trigger phrases: "video chat", "voice call", "call me", "视频一下", "语音", "打电话给我", "我要和你视频", "videochat-withme".
As a process C 64/100 · Has gaps — weak spots: result and completion, progress reporting
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
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
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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
-
high Dangerous commands
cmd-persistencescripts/setup.sh:214Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load "$PLIST"
Medium and low: 1
-
medium Dangerous commands
cmd-persistencescripts/setup.sh:155Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)PLIST="$HOME/Library/LaunchAgents/${PLIST_LABEL}.plist"code literal
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 64/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 15 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 901 tokens
- 100Running it twice. Mutating operations check current state
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
- -2localhost URLs: will not work for another user
- -31 of 5 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 771: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.