AB openclaw-reporter
Opt-in reporter for the OpenClaw global claw heatmap. On first use, ASKS the user for consent before registering. Heartbeat (platform + model only) is sent only after confirming prior consent (i.e. ~/.openclaw/config.json exists from a previous registration). Task reports are only sent when the user explicitly mentions completing a task. Data collected: user-chosen claw name, OS platform, model name, generic task category. Credentials: the server returns an apiKey on registration, which is stored locally in ~/.openclaw/config.json and sent as a Bearer token in subsequent requests. No file paths, code, tool names, or project-specific data is ever sent.
As a process B 67/100 · Nearly there — weak spots: result and completion, progress reporting
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 · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "requirements"
Process rating: all ten parameters 67/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (node) 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
- 70Failures and branches. 8 branches
- 100Steps. 25 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2015 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 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
- +1No license
- +2Single-language instructions
- +3Description length 659: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 25 items
- +4Has examples (9 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.