AC arena-turn-accelerator
Seven offline mechanisms against slow/stale/zombie/sycophantic agent turns: prompt compaction, request fencing, zombie detection, CAPTCHA triage, anti-sycophancy spine, delivery register, invention quarry. Use when chat feels laggy, reconnects surface old answers, long chats degrade, or the agent caves under contradiction. JSON contracts; state per-agent under ~/.arena_turn; no network, no sudo.
Seven offline mechanisms against slow/stale/zombie/sycophantic agent turns: prompt compaction, request fencing, zombie detection, CAPTCHA triage…
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Concealment
en-hide-from-userscripts/selftest.sh:206Instruction to hide actions from the user (test fixture / example file; quoted — discussed, not commanded)assert '__main__' in src and '_run_all' in src, 'no runner: tests would silently execute nothing'
fixturequoted
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 23. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "trigger_words" - note
frontmatter-keyunknown frontmatter key "topics"
Process rating: all ten parameters 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 10 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1446 tokens
- 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 (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
- -31 of 13 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 398: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 10 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.