AC whatsapp-ultimate
You put 5 agents in a WhatsApp group. They all respond at once. Your API bill does a backflip. Protocol v2 fixes that — congestion control, conversation lifecycle, and budget-aware scheduling. Agents that know when to talk, when to shut up, and when to burn unused tokens before reset. Built for the TinkerClaw fork — github.com/globalcaos/tinkerclaw. Also ships four opt-in maintenance scripts that read your WhatsApp session credentials, enumerate group contacts, and patch your OpenClaw source tree — each refuses to run without an explicit --yes. See Permissions, Data Flow & Consent.
You put 5 agents in a WhatsApp group.
As a process C 52/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
-
low Risky intent
intent-offensive-securitySKILL.md:30Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)security: "The documentation half of this skill is inert — it describes actions of OpenClaw's own WhatsApp channel and needs no permissions. The four bundled scripts in scripts/ are NOT inert and are
quoted
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6523 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 52/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 36 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 6523 tokens
- 85Steps. 58 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- low 15 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (6 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 588: enough signal without eating the budget
- +4Structure: 59 headings
- +3Step-by-step instructions: 58 items
- +4Has examples (39 code blocks)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.