sqlite-ops

Patterns for SQLite databases in Python projects - state management, caching, and async operations. Triggers on: sqlite, sqlite3, aiosqlite, local database, database schema, migration, wal mode.

1.13x

Quality

—

Does it follow best practices?

Impact

100%

1.13x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A concise, highly actionable SQLite reference with clean code and well-structured progressive disclosure. The one gap is workflow clarity: as a database skill it lacks explicit validation/verification checkpoints that the rubric expects for risky operations.

Suggestions

Add an explicit validation checkpoint for risky operations, e.g. after migrations run 'PRAGMA user_version' / 'PRAGMA foreign_key_check' and only proceed when clean, to introduce a verify-then-proceed feedback loop.

Add a brief 'Verify' note for WAL/index changes such as checking 'EXPLAIN QUERY PLAN' before relying on a new index, turning the gotchas table into an actionable checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is lean: tight code blocks, scannable tables, and minimal useful inline comments ('Dict-like access', 'Better concurrency'), with no explanation of concepts Claude already knows. The only redundancy is the WAL PRAGMA reappearing, which is minor lookup-table reuse rather than padding, so it stays at level 3.	3 / 3
Actionability	All examples are fully executable and copy-paste ready — get_connection(), a db_transaction context manager, concrete PRAGMA statements, and real sqlite3 CLI commands — matching the level-3 anchor for executable, specific guidance.	3 / 3
Workflow Clarity	This is a patterns/reference skill with no sequenced multi-step workflow, and for a database-operations skill the rubric caps workflow_clarity at 2 when validation/feedback checkpoints are absent; the context manager's commit/rollback is error handling, not an explicit verify-then-proceed checkpoint.	2 / 3
Progressive Disclosure	The 'Additional Resources' section signals three one-level-deep references, each with a short description (schema/async/migration patterns), matching the level-3 anchor of a concise overview pointing to well-signaled detail files; no bundle was provided so scoring follows the references as written.	3 / 3
	Total	11 / 12 Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with explicit trigger guidance and good natural keyword coverage. Its main weakness is specificity: it lists capability areas rather than concrete, scannable actions.

Suggestions

Replace abstract capability areas ('state management, caching, and async operations') with concrete actions like 'create schemas, run migrations, manage WAL connections, and async CRUD with aiosqlite' to lift specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ('SQLite databases in Python projects') and capability areas ('state management, caching, and async operations'), but these are topic categories rather than the multiple concrete actions (e.g. 'create tables', 'run migrations', 'manage connections') that the level-3 anchor requires.	2 / 3
Completeness	It states what it does ('Patterns for SQLite databases... state management, caching, and async operations') and gives an explicit when via 'Triggers on: ...', the equivalent of a 'Use when...' clause, satisfying both halves required for level 3.	3 / 3
Trigger Term Quality	'Triggers on: sqlite, sqlite3, aiosqlite, local database, database schema, migration, wal mode' gives good coverage of natural terms a user would say, matching the level-3 anchor's breadth of natural keywords.	3 / 3
Distinctiveness Conflict Risk	SQLite-specific triggers (sqlite3, aiosqlite, wal mode) carve a clear niche unlikely to fire for the wrong skill; the more generic terms (local database, migration) add minor overlap risk but not enough to drop below the level-3 anchor.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: NeverSight/skills_feed
Commit: 26d37ce

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.