AD flexible-database-design
Guide agents and users to design and implement a "flexible database" on SQLite that can handle semi-structured, multi-source data. Typical scenarios: personal knowledge base, PDF/report archive, policy tracking, fragmented notes, custom form/questionnaire fields, multi-source data aggregation, event logging. When the user says things like "I want to build a knowledge base", "archive PDF reports", "search within report content", "collect policies or scattered information", this skill provides the end-to-end workflow. It includes: design principles, a three-layer model, agent workflows, schema templates, and reference Python scripts.
Guide agents and users to design and implement a "flexible database" on SQLite that can handle semi-structured, multi-source data.
As a process D 49/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- 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: 22. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
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
- 30Running it twice. 15 mutating operations with no state check
- 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. 31 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1493 tokens
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)
- +3Output format is not stated: the model decides each time
- -31 of 7 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 639: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 31 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (1 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.