B sql-linker
Use this skill when you need to query, insert, update, or delete records in the configured MySQL/PostgreSQL/SQLite database and you know the target table name and approximate schema. Triggers include: (1) explicitly requesting a SELECT/INSERT/UPDATE/DELETE on a named table; (2) asking for a specific record by ID or a specific filter; (3) requesting audit log review for sql_audit_log; (4) explicitly asking to bootstrap or inspect the sql-linker configuration. Do NOT trigger on generic "database", "查数据库", "SQL", or "CRUD" without a specific target table or intent.
- Safety 60%
- Quality 40%
- Tests bonus
How to improve
- The SKILL.md body exceeds 5,000 tokens: move reference detail into references/ and load it on demand.
- Add evals/evals.json with 4–6 real requests and expected answers: the full check will then use your cases instead of a model draft.
- Add a spec.yaml with triggers and assertions (skilltest init): the behaviour contract for CI.
Guard findings · 3
✓ No critical or high findings
Medium and low: 3
-
low Exfiltration
net-credential-usescripts/service_layer/db_bridge.py:92Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)if ($Confirm -eq $Password) { break }quoted -
low Exfiltration
net-credential-usescripts/service_layer/db_bridge.py:193Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)if [ "$CONFIRM" = "$PASSWORD" ]; then
quoted -
low Dangerous commands
cmd-shell-rcscripts/service_layer/db_bridge.py:239Writes to a shell startup file (string literal in code, not executed)echo "Error: Could not find ~/.bashrc or ~/.zshrc" >&2
code literal
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Lint
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Unexpected scalar at node end at line 3, column 505: …figuration. Do NOT trigger on generic "database", "查数据库", "SQL", or "CRUD" wit… ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
body-longSKILL.md body ≈ 12443 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "requires"
Process maturity 61/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Execution cost. Instruction body is 12443 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 141 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 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 20 top-level sections: this looks like several domains in one skill
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
- -232 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 568: enough signal without eating the budget
- +4Structure: 101 headings
- +3Step-by-step instructions: 141 items
- +4Has examples (36 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.