SKILLEMALL.ai
GitHub ↗ RU Sign in

BD google-health-cli

Read your Google Health data from any agent. Lists data points for every Google Health data type (heart rate, resting heart rate, sleep, steps, distance, weight, blood oxygen, VO2 max, exercise, and more), returns server-side daily roll-ups (one reconciled total per day), gives a parsed view of exercise sessions, and can GET any read-only v4 API path. A self-contained, read-only client for the Google Health v4 API: authenticates via OAuth2 (token cached locally and auto-refreshed) and emits JSON. It does NO filtering, merging, or writing — the caller decides what to do with the data. Single static binary, no Python or other runtime. NOTE: needs your own Google Cloud OAuth client and a one-time interactive browser login; runs headless afterward.

ClawHub Agent Skills author: Steven Gates v1.0.9 MIT-0 63 files body ≈ 2 721 tokens Open the sourceclawhub.ai↗ analyzed 34 h ago

Read your Google Health data from any agent.

As a process D 45/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationGoogle CloudSoftware developmentAI and agentsFinancetype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
83/100
safety, quality, tests
Safety 60%
94
Quality 40%
66
Run on models
none yet
Process rating
D
45/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
  • 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 · 6

✓ No critical or high findings

Medium and low: 6
  • low Secrets in code secret-high-entropy-token internal/api/client_test.go:102
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    // Test…ace is the immutable guard for the
    fixture
  • low Secrets in code secret-high-entropy-token internal/api/client_test.go:110
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    func Test…ace(t *testing.T) {
    fixture
  • low Secrets in code secret-password-literal internal/auth/tokencache_test.go:18
    Hard-coded password / key literal (may be an example) (test fixture / example file)
    AccessToken:  "access-123",
    fixture
  • low Secrets in code secret-high-entropy-token internal/cli/commands_test.go:221
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    // Test…ror guards that the `api get` escape hatch's
    fixture
  • low Secrets in code secret-high-entropy-token internal/cli/commands_test.go:225
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    func Test…ror(t *testing.T) {
    fixture
  • low Secrets in code secret-high-entropy-token internal/cli/commands_test.go:442
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    func Test…ts2(t *testing.T) {
    fixture

Files scanned: 63. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 45/100

  • 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
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 2 mutating operations with no state check
  • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
  • 100Steps. 9 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2721 tokens
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low The response is described with custom markup (7 tags): a typed call is more reliable

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
  • -44 reference files, but SKILL.md never points to them: the model will not open them
  • -32 of 2 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +3Description length 754: enough signal without eating the budget
  • +4Structure: 11 headings
  • +3Step-by-step instructions: 9 items
  • +4Has examples (11 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.

External checks

ClawHub: suspicious
The skill is a disclosed read-only Google Health CLI, but its configurable API destination and OAuth scopes create review-worthy risk around sensitive health tokens and permissions.
LLM: suspicious (high) · 6 Sept 2026