DC invest
openInvest multi-asset AI investment committee — **daily use**. Read portfolio / live prices / strategy / decision history / adjust positions / run a 4-role LLM committee for an investment verdict. Supports any yfinance symbol (A-share / HK / US / ETF / crypto / commodities) and any currency. **Two paths** — (1) Coordinator, Claude Code spawns 4 subagents, saves DeepSeek tokens; (2) Direct, any agent (Codex / Hermes / OpenClaw / Cursor / Cline / plain script) runs `run.sh run_committee <SYM>` for a one-shot verdict. **Trigger scenarios** — "show portfolio / 看看我的持仓", "how is my P&L / 我现在涨了多少", "should I buy/sell X / 该不该买卖X", "analyze X / 分析一下X", "run committee on X / 跑委员会", "track AAPL / 跟踪苹果", "add/trim a position, log a trade / 加仓减仓记一笔". **First-time install uses a separate skill `invest-setup`** (switch to it when `doctor` returns `needs_setup`). Backend — longsizhuo/openInvest.
openInvest multi-asset AI investment committee — daily use.
As a process C 54/100 · Has gaps — weak spots: result and completion, when it triggers, consistency
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 tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
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
- 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.
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 6
-
high Concealment
en-hide-from-userreferences/onboarding.md:111Instruction to hide actions from the user`cash_recorded` in the same JSON is the cash this run wrote. If it is `{}`, do not tell the user
Medium and low: 5
-
medium Dangerous commands
cmd-autorun-instructionreferences/adding-assets.md:14Instructs the agent to auto-run a script on every sessioninto `status` / P&L. First run `run.sh status`: a symbol it already lists is in the ledger, so
-
medium Exfiltration
net-credential-usereferences/troubleshooting.md:74Credential used in a network call (verify the destination is the intended service)curl -H "Authorization: Bearer $DEEPSEEK_API_KEY" \
-
low Dangerous commands
cmd-pipe-to-shell-known-hostscripts/run.sh:26Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)echo "❌ uv 未安装。装一下：curl -LsSf https://astral.sh/uv/install.sh | sh" >&2
code literal -
low Dangerous commands
cmd-pipe-to-shell-known-hostscripts/run.sh:28Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)[ "${1:-}" != "mcp" ] && echo '{"status":"error","error":"uv 未安装","hint":"运行 `curl -LsSf https://astral.sh/uv/install.sh | sh` 后重试"}'code literal -
low Exfiltration
net-credential-useSKILL.md:222Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)add `Authorization: Bearer $INVEST_API_TOKEN` when curling.
quoted
Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 893 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
body-longSKILL.md body ≈ 5596 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 80, 87, 294): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 54/100
- 0Result and completion. Does not say what the result is
- 0Consistency. Frontmatter name (invest) differs from the folder (openinvest)
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5596 tokens
- 85Steps. 28 steps, 3 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (9 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 893: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Structure: 14 headings
- +3Step-by-step instructions: 28 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.