bun-sqlite
Use for bun:sqlite, SQLite operations, prepared statements, transactions, and queries.
60
68%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/bun/skills/bun-sqlite/SKILL.mdQuality
Discovery
72%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is concise and well-targeted to its niche (Bun's SQLite module), with good trigger terms that developers would naturally use. However, it lacks specific concrete actions (what the skill actually helps you do) and could benefit from a more explicit 'Use when...' clause describing triggering scenarios rather than just listing topics.
Suggestions
Add specific concrete actions like 'Create databases, run queries, manage transactions, use prepared statements with bun:sqlite'
Expand the trigger guidance with a 'Use when...' clause, e.g., 'Use when the user needs to interact with SQLite databases in Bun, create or query tables, or manage database transactions'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (bun:sqlite, SQLite) and some actions (prepared statements, transactions, queries), but doesn't list specific concrete actions like 'create tables', 'run migrations', 'batch insert rows'. The terms are more categories than concrete actions. | 2 / 3 |
Completeness | Has a 'Use for...' clause that partially addresses 'when', but it reads more like a topic list than explicit trigger guidance. The 'what does this do' is only implied through the listed topics rather than describing concrete capabilities. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'bun:sqlite', 'SQLite', 'prepared statements', 'transactions', 'queries'. These are terms developers naturally use when working with SQLite in Bun. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of 'bun:sqlite' specifically distinguishes this from generic database skills or other SQLite drivers. It clearly targets a specific runtime (Bun) and specific module (bun:sqlite), making conflicts unlikely. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, comprehensive reference for bun:sqlite with excellent actionability—nearly every section has executable, concrete code examples. The main weaknesses are moderate verbosity (the skill could be tightened by moving the Repository Pattern and some reference material to separate files) and missing validation/error-recovery workflows for multi-step operations like bulk inserts and transactions.
Suggestions
Add explicit validation/error-recovery steps to the Transactions and Batch Operations sections (e.g., try/catch with rollback guidance, verifying row counts after bulk inserts).
Move the Repository Pattern to a separate reference file to reduce the main skill's length and improve progressive disclosure.
Trim the Column Types section—the SQLite-to-JS type mapping table is basic knowledge; keep only the BigInt and Uint8Array edge cases.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good code examples, but includes some redundancy (e.g., the 'Opening Databases' section repeats patterns Claude would know, the Column Types section explains basic SQLite-to-JS type mappings, and some sections like Query Methods overlap with earlier examples). The Repository Pattern is quite lengthy and could be trimmed. | 2 / 3 |
Actionability | All code examples are fully executable TypeScript using the bun:sqlite API, with concrete imports, complete statements, and copy-paste ready patterns. Parameters, transactions, error handling, and batch operations all have specific, runnable examples. | 3 / 3 |
Workflow Clarity | The skill covers individual operations well but lacks explicit workflow sequencing for multi-step processes. For example, the batch operations section doesn't include validation or error recovery steps, and there's no guidance on verifying transaction success or handling partial failures in bulk inserts. | 2 / 3 |
Progressive Disclosure | The skill references `references/pragmas.md` and `references/fts.md` at the bottom with clear loading conditions, which is good. However, the main body is quite long (~300 lines) with sections like the Repository Pattern and Column Types that could be split into reference files. No bundle files are provided to verify the referenced paths exist. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- secondsky/claude-skills
- Commit
5e92b71
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.