BD nautilus-polymarket-stops
NautilusTrader Polymarket STOP LOSS / TRAILING STOP / HARD STOP process sidecar (zero Nautilus PR). Official Nautilus docs: STOP_MARKET / TRAILING_STOP unsupported on Polymarket. Run beside live Nautilus node on same funder — protective SELLs stamp Zac builderCode while Nautilus keeps entries. Installable docker compose via npm pack @hypelens/hypelens-agent-guard@0.1.18 → package/compose. Same package as polymarket-stops / agent-guard. Use when: nautilus, nautilustrader, nautilus polymarket, process sidecar, docker compose, stop loss, trailing stop. Install: clawhub install nautilus-polymarket-stops. Also: polymarket-risk / polymarket-exits aliases. MCP desk_loop every session. Keywords: nautilus, nautilustrader, nautilus-polymarket-stops, polymarket-stops, agent-guard, sidecar, docker-compose, compose, stop loss, trailing stop, hard stop, portfolio stop, openclaw, mcp.
NautilusTrader Polymarket STOP LOSS / TRAILING STOP / HARD STOP process sidecar (zero Nautilus PR).
As a process D 38/100 · Unfinished process — weak spots: steps, result and completion, when it triggers
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: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "topics"
Process rating: all ten parameters 38/100
- 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
- 20When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 282 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 882: 120–800 characters recommended
- +4Structure: 2 headings, hard to scan
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- -31 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.