AD wellness-coach
Launch a personalized AI wellness coach video session (Baymax persona) using Tavus CVI + Claude. Fetches real wearable health data (sleep, HRV, recovery) and Google Calendar events, builds a personalized system prompt, creates a live Tavus conversational video session, and delivers a morning briefing link via Telegram. Use when the user wants a daily wellness briefing, wants to talk to an AI wellness coach, wants guided breathing/meditation based on their health data, or asks to start their morning routine. Requires TAVUS_API_KEY, TAVUS_REPLICA_ID, TAVUS_PERSONA_ID, and ANTHROPIC_API_KEY in .env.
As a process D 49/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Dangerous commands
cmd-autorun-instructionSKILL.md:127Instructs the agent to auto-run a script on every session**Tavus link expired** → Sessions last ~10 min. Always run `morning_context.py` and `send_briefing.py` together right before use.
-
low Exfiltration
read-dotenvSKILL.md:24Reads a .env filecp .env.example .env # fill in API keys
Files scanned: 5. 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 49/100
- 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
- 30Running it twice. 4 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 14 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 966 tokens
- 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)
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 603: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 14 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.