AB clawlink
Cross-instance agent communication for OpenClaw. ClawLink lets multiple OpenClaw sessions discover each other, delegate tasks, share knowledge, collaboratively edit files, and work as a coordinated agent mesh — across different machines on a local network. Use this skill whenever the user mentions connecting OpenClaw instances, multi-agent workflows, agent-to-agent communication, delegating tasks between sessions, collaborative AI work, agent discovery, or running agents on multiple machines. Also trigger when the user says things like "ask my other agent to...", "have another Claude work on...", "set up agent communication", "multi-machine", "agent mesh", "distributed agents", or "ClawLink". If the user wants two or more AI sessions to work together in any way, this is the skill to use.
As a process B 68/100 · Nearly there — weak spots: inputs and preconditions, consistency
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: 7. 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 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (clawlink) differs from the folder (openclaw-link)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 10 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 1241 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
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)
- -31 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 798: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 10 items
- +3Output format is stated explicitly
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.