CC ibkr-options-assistant
Interactive Brokers options & stock trading assistant. Provides real-time portfolio Greeks, option chain analysis, McMillan/Overby strategy recommendations, P&L statistics, Wheel strategy tracking, earnings warnings, risk simulation, and a complete toolkit for options traders. Use this skill whenever the user asks about specific options trades, position risk, buy/sell recommendations, IV environment, P&L, wheel strategy, earnings impact on options, or any IBKR account data — even if they don't explicitly mention "IBKR". For stock price queries, always use market_quote.py instead of web search.
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 8
-
high Dangerous commands
cmd-persistenceREADME.md:330Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load ~/Library/LaunchAgents/com.user.ibgateway.plist
-
high Dangerous commands
cmd-persistenceREADME.zh-CN.md:321Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load ~/Library/LaunchAgents/com.user.ibgateway.plist
Medium and low: 6
-
medium Dangerous commands
cmd-persistenceREADME.md:302Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)Create `~/Library/LaunchAgents/com.user.ibgateway.plist`:
quoted -
medium Dangerous commands
cmd-persistenceREADME.md:333Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)It will auto-restart Gateway whenever it dies. To stop: `launchctl unload ~/Library/LaunchAgents/com.user.ibgateway.plist`.
quoted -
medium Dangerous commands
cmd-persistenceREADME.zh-CN.md:293Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)创建 `~/Library/LaunchAgents/com.user.ibgateway.plist`：
quoted -
medium Dangerous commands
cmd-persistenceREADME.zh-CN.md:324Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)Gateway 挂掉就自动重启。想停：`launchctl unload ~/Library/LaunchAgents/com.user.ibgateway.plist`。
quoted -
low Exfiltration
read-dotenvREADME.md:226Reads a .env filecp .env.example .env
-
low Exfiltration
read-dotenvREADME.zh-CN.md:217Reads a .env filecp .env.example .env
Files scanned: 31. 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 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
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 4 branches
- 100Steps. 14 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1800 tokens
- 100Running it twice. No mutating operations
- low The skill ranks results itself: that belongs to the system behind the tool, not the model
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
- -32 of 18 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 600: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 14 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.