CD gm-quant
掘金量化 Python SDK 专家技能。 当用户提到掘金、gm、gm.api、掘金量化、掘金策略、掘金SDK、掘金终端、 量化策略开发、回测、实时行情、订阅行情、历史行情、下单、委托、持仓、 order_volume、subscribe、history、set_token、get_symbols、get_symbol_infos、 get_history_symbol、history_n、current、last_tick、current_price、get_trading_dates、 order_percent、order_value、order_target_volume、algo_order、 get_orders、get_position、get_cash、bond_convertible、 L2行情、逐笔成交、逐笔委托、schedule定时任务、 财务数据、资产负债表、利润表、现金流量表、估值指标、PE/PB/PS/股息率、 市值、股本、流通股、成分股、行业分类、 可转债分析、转股溢价率、纯债价值、ETF成分股、基金净值、 期货合约信息、仓单数据、成交持仓排名、连续合约、 stk_get_fundamentals、stk_get_daily_valuation、stk_get_index_constituents、 stk_get_industry_category、stk_get_industry_constituents、stk_get_symbol_industry、 stk_get_sector_category、stk_get_sector_constituents、stk_get_symbol_sector、 stk_get_dividend、stk_get_ration、stk_get_adj_factor、stk_get_shareholder_num、 stk_get_top_shareholder、stk_get_share_change、stk_abnor_change_stocks、 stk_abnor_change_detail、stk_quota_shszhk_infos、stk_active_stock_top10_shszhk_info、 stk_get_money_flow、stk_get_finance_audit、stk_get_finance_forecast、 bnd_get_analysis、bnd_get_conversion_price、bnd_get_call_info、bnd_get_put_info、bnd_get_amount_change、 fnd_get_portfolio、fnd_get_etf_constituents、fnd_get_net_value、fnd_get_adj_factor、fnd_get_dividend、fnd_get_split、fnd_get_share、 fut_get_contract_info、fut_get_continuous_contracts、fut_get_transaction_rankings、fut_get_warehouse_receipt、 get_open_call_auction 时,自动加载此 skill。
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Shorten the description to 1024 characters.
- 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 · 0
✓ No critical or high findings
Files scanned: 39. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1396 chars, limit 1024 - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 6879 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 46/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (gm-quant) differs from the folder (gmquant)
- 70Execution cost. Instruction body is 6879 tokens
- 100Tools and files. No external tools needed
- 100Steps. 51 steps
- 100Progress reporting. Reports progress
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 1395: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- -313 of 14 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 39 headings
- +3Step-by-step instructions: 51 items
- +4Has examples (27 code blocks)
- +4Reference files are cited in the instructions (20 of 21)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 31.