BD aicoin-freqtrade
Use when user asks about Freqtrade — strategy creation, backtest, hyperopt, switching strategies / pairs / dry-run mode, querying live bot status / balance / open positions / 盈亏. Trigger words: 'write strategy', 'create strategy', 'backtest', 'switch strategy', 'switch to live', 'open positions', 'P&L', '写策略', '创建策略', '回测', '部署策略', '切策略', '切实盘', '当前持仓', '今天赚多少', '盈亏'. In CoinClaw containers (OpenClaw / Hermes / Claude Code) freqtrade is a supervisord-managed daemon on :8080 — this skill auto-detects engine + paths via lib/coinclaw-env.mjs and never spawns competing freqtrade processes. Outside CoinClaw it falls back to host mode (clone freqtrade + nohup). For prices/charts use aicoin-market. For exchange trading use aicoin-trading. For Hyperliquid use aicoin-hyperliquid.
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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 · 5
✓ No critical or high findings
Medium and low: 5
-
medium Exfiltration
net-redirectable-api-keylib/aicoin_data.py:92Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
low Secrets in code
secret-high-entropy-tokenlib/defaults.json:3High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"accessKeyId": "ronJ…E22",
quoted -
low Secrets in code
secret-high-entropy-tokenlib/defaults.json:4High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"accessSecret": "CWHZ…TwU"
quoted -
low Dangerous commands
cmd-pipe-to-shell-known-hostscripts/ft-deploy.mjs:208Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)run('curl -LsSf https://astral.sh/uv/install.sh | sh', { timeout: 60000 });code literal -
low Dangerous commands
cmd-pipe-to-shell-known-hostscripts/ft-deploy.mjs:237Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)throw new Error('Python 3.11+ required. Install options:\n• curl -LsSf https://astral.sh/uv/install.sh | sh && uv python install 3.12\n• brew install py…@….12\n• https://www.python.org/downloads/')code literal
Files scanned: 14. 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 43/100
- 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
- 30Running it twice. 26 mutating operations with no state check
- 60Tools and files. Uses tools (python, node) that frontmatter does not declare
- 100Steps. 26 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3358 tokens
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
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +3Description length 781: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 26 items
- +4Has examples (4 code blocks)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.