Conciseness

Every line carries TqSdk-specific knowledge Claude would not already know — `iloc[-1]` is a forming bar, `insert_order()` return vs fill, `TargetPosTask` not mixed with manual orders, `KQ.m@` main-continuous contracts, `BacktestFinished` handling — with zero filler or basic-concept padding. This matches the 5 anchor ('lean and efficient; assumes Claude's competence; every token earns its place').

Actionability

Guidance is highly concrete: a runnable script ([scripts/check_environment.py](scripts/check_environment.py)), a specific status to branch on (`not_installed`), and exact fields and functions (`volume_left`, `last_msg`, `underlying_symbol`, `account=`, `finally: api.close()`). It stops short of the 5 anchor's 'copy-paste ready code or commands' since the body has no inline code snippet, but per the rubric's code-vs-instruction note this is a minor gap, not a failing.

Workflow Clarity

The 5-step 开始处理 sequence has explicit validation checkpoints and feedback loops: run the environment script, branch on `not_installed`, install per environment-setup.md, verify the import, then 验证并交付 requires syntax/import checks before data/output/backtest verification, plus a live-trading authorization check ('执行实盘下单或撤单前，确认操作参数在用户已有授权范围内'). This matches the 5 anchor (clear sequence, explicit validation, error-recovery loops).

Progressive Disclosure

SKILL.md is a concise overview with a task→reference table mapping 11 real, one-level-deep reference files (all verified to exist), plus the bundled script; the reference files themselves only link to sibling files and external URLs, with no nested chains. This matches the 5 anchor (clear overview, well-signaled one-level-deep references, easy navigation).

Specificity

The description lists multiple concrete actions — "获取行情与历史数据", "编写或排查交易与回测程序", "检查环境、安装缺失的 TqSdk" — covering the skill's data, code, troubleshooting, and environment scope comprehensively. It matches the 5 anchor (multiple specific concrete actions, comprehensive coverage); the 4 anchor ('minor gaps') would understate this breadth.

Completeness

Both what and when are explicit: what — "获取行情与历史数据、编写或排查交易与回测程序...检查环境、安装缺失的 TqSdk"; when — "适用于明确使用 TqSdk、TqApi、TargetPosTask 等接口的开发、数据和账户问题" plus the explicit exclusion "通用金融问答或其他数据产品不必使用本技能". This matches the 5 anchor (clear what AND when with concrete trigger phrases), exceeding the 4 anchor's 'when could be more explicit'.

Trigger Term Quality

Good keyword coverage with concrete trigger names users would say: "TqSdk", "TqApi", "TargetPosTask", "行情", "历史数据", "回测", "账户". It misses common natural synonyms such as the Chinese brand name "天勤"/"天勤量化", "shinny", or "期货", so it falls short of the 5 anchor's 'comprehensive coverage including synonyms'.

Distinctiveness Conflict Risk

The niche is unambiguous: it names the specific SDK and its interfaces ("TqSdk Python SDK", "TqApi", "TargetPosTask") and explicitly excludes generic finance Q&A and other data products, giving it clear distinct triggers with minimal conflict risk — a direct match to the 5 anchor.