BD sql-master
SQL智能助手，支持SQL执行、重写优化、质量分析、数据分析、智能补全、Schema查询、批量执行、数据导入导出。 使用场景： - 用户说"执行这个SQL" → execute 或直接 dbskiter sql "SELECT..." - 用户说"优化这个SQL" → rewrite - 用户说"分析SQL质量" → analyze - 用户说"分析数据" → data - 用户说"SQL补全" → complete - 用户说"查看表结构" → schema - 用户说"批量执行SQL文件" → batch - 用户说"导出数据" → export - 用户说"导入数据" → import 用法： - dbskiter --output-mode=ai --database=<name> sql "SELECT * FROM users" - dbskiter --output-mode=ai --database=<name> sql execute "SELECT * FROM users" - dbskiter --output-mode=ai --database=<name> sql rewrite "SELECT * FROM users WHERE id = 1" - dbskiter --output-mode=ai --database=<name> sql analyze "SELECT * FROM orders" - dbskiter --output-mode=ai --database=<name> sql data "SELECT * FROM sales" - dbskiter --output-mode=ai --database=<name> sql complete "SELECT * FROM " - dbskiter --output-mode=ai --database=<name> sql schema --table=users - dbskiter --output-mode=ai --database=<name> sql batch queries.sql - dbskiter --output-mode=ai --database=<name> sql export --table=users --output=users.csv - dbskiter --output-mode=ai --database=<name> sql import data.csv --table=users
As a process D 49/100 · 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.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1094 chars, limit 1024 - warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 49/100
- 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
- 40Consistency. Frontmatter name (sql-master) differs from the folder (dbskiter-sql-master)
- 100Tools and files. No external tools needed
- 100Steps. 37 steps
- 100Execution cost. Instruction body is 1552 tokens
- 100Running it twice. No mutating operations
- low The response is described with custom markup (16 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 1093: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 11 example trigger phrases
- +4Structure: 17 headings
- +3Step-by-step instructions: 37 items
- +4Has examples (21 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 49.