AD agent-relay
Cross-agent context sharing via shared files. Agents write trends, highlights, and signals to a shared folder. Other agents read before acting — creating coordinated behavior without direct messaging. Use when: multi-agent setups need coordination, agents should know what other agents found, trends from one source should influence another agent's actions. NOT for: real-time communication, agent-to-agent chat, single-agent setups.
As a process D 37/100 · Unfinished process — weak spots: steps, result and completion, inputs and preconditions
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: 3. 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 37/100
- 0Steps. Prose only: no discrete steps
- 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
- 40Consistency. Frontmatter name (agent-relay) differs from the folder (agent-shared-context)
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Execution cost. Instruction body is 575 tokens
- 100Running it twice. No mutating operations
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
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 436: enough signal without eating the budget
- +4Structure: 11 headings
- +4Has examples (6 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.