CtrlK
BlogDocsLog inGet started
Tessl Logo

sqlite-expert

SQLite expert for WAL mode, query optimization, embedded patterns, and advanced features

57

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./crates/openfang-skills/bundled/sqlite-expert/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The body is a lean, action-dense reference with exact PRAGMA values and real SQL syntax and clean section structure, but it is reference-style rather than a sequenced workflow and carries an opening paragraph plus some rationale that re-explain what Claude already knows.

Suggestions

Trim or remove the opening descriptive paragraph and the trailing rationale clauses (e.g. the WAL non-blocking explanation) so the file leads directly with actionable guidance.

For schema migration and incremental vacuum, add an explicit validate→fix→retry loop (e.g. run EXPLAIN QUERY PLAN / PRAGMA integrity_check, fix, re-check, then proceed) to turn the guidance into a sequenced, checkpointed workflow.

DimensionReasoningScore

Conciseness

The bullets are dense and assume SQLite competence, but the opening paragraph ("A database specialist with deep expertise... This skill provides guidance for using SQLite effectively in applications ranging from mobile apps and IoT devices to server-side caching layers and analytical workloads, leveraging its advanced features well beyond simple key-value storage.") re-states the description and trailers like "it allows readers to proceed without blocking writers and vice versa" explain concepts Claude already knows, matching the score-2 anchor of mostly efficient with some unnecessary explanation rather than the every-token-earns-its-place bar of a 3.

2 / 3

Actionability

Concrete, executable specifics abound — exact PRAGMA values ("synchronous=NORMAL, cache_size=-64000, mmap_size=268435456, temp_store=MEMORY") and real SQL syntax ("CREATE VIRTUAL TABLE docs USING fts5(title, body)", "INSERT ... ON CONFLICT (column) DO UPDATE SET", "json_extract(), json_each()") — matching the score-3 anchor of specific, copy-paste-ready guidance rather than the pseudocode of a 2.

3 / 3

Workflow Clarity

Content is organized into sections rather than a sequenced process, and while EXPLAIN QUERY PLAN is mentioned as a check ("verified with EXPLAIN QUERY PLAN showing COVERING INDEX"), there is no explicit validate→fix→retry feedback loop for destructive/batch-adjacent operations like schema migration or incremental vacuum, so per the guidelines workflow_clarity is capped at 2 rather than reaching the explicit-checkpoint bar of a 3.

2 / 3

Progressive Disclosure

The body is under 50 lines with no bundle files present and is organized into clear, well-separated sections (Key Principles, Techniques, Common Patterns, Pitfalls to Avoid), so per the simple-skills note progressive_disclosure scores 3 on well-organized sections alone with no need for external references.

3 / 3

Total

10

/

12

Passed

Description

57%

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, third-person, and clearly SQLite-scoped, but it reads as a topic catalog rather than an action list and lacks any explicit "Use when..." trigger guidance, leaving its strongest gaps in trigger coverage and completeness.

Suggestions

Add an explicit trigger clause, e.g. "Use when working with SQLite databases, tuning query performance, configuring WAL mode, or designing embedded/local data storage."

Replace topic-area phrasing with concrete actions and natural trigger terms, e.g. "Optimize SQLite queries, configure WAL mode and PRAGMAs, build FTS5 full-text search, and design embedded database schemas."

Drop the generic "advanced features" tail in favor of a second concrete capability to lift specificity from a topic list to an action list.

DimensionReasoningScore

Specificity

Quotes "SQLite expert for WAL mode, query optimization, embedded patterns, and advanced features" — it names the domain and several topic areas but lists no concrete actions (e.g. 'optimize', 'migrate', 'tune'), and "advanced features" is vague, matching the score-2 anchor of naming a domain without comprehensive actions rather than the multiple concrete actions of a 3.

2 / 3

Completeness

The description answers "what" (a SQLite expert for the listed areas) but contains no "Use when..." clause or equivalent explicit trigger, so per the guidelines completeness is capped at 2 even though the what-side is reasonably stated.

2 / 3

Trigger Term Quality

"SQLite" and "WAL mode" are natural user terms, but "embedded patterns" and "advanced features" are unlikely user phrasings and common variations like "database", "SQL", "slow query", or "database performance" are missing, fitting the score-2 anchor of some relevant keywords but missing common variations rather than the broad coverage of a 3.

2 / 3

Distinctiveness Conflict Risk

"SQLite" pins the skill to a clear, specific niche unlikely to be confused with other skills, matching the score-3 anchor of a clear niche with distinct triggers; it is not generic enough to fall to the 2 anchor.

3 / 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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
RightNow-AI/openfang
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.