analyzing-query-performance
Execute use when you need to work with query optimization. This skill provides query performance analysis with comprehensive guidance and automation. Trigger with phrases like "optimize queries", "analyze performance", or "improve query speed".
60
52%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/database/query-performance-analyzer/skills/analyzing-query-performance/SKILL.mdQuality
Discovery
40%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description suffers from vagueness in its capability claims, relying on buzzwords like 'comprehensive guidance and automation' rather than concrete actions. While it includes some trigger phrases, it lacks specificity about what kind of queries it handles and what concrete outputs or actions it performs. The awkward opening 'Execute use when' also suggests poor craftsmanship.
Suggestions
Replace vague capability claims with specific concrete actions, e.g., 'Analyzes SQL query execution plans, identifies missing indexes, rewrites slow joins, and suggests schema improvements'.
Specify the query type (SQL, NoSQL, etc.) and add more natural trigger term variations like 'slow query', 'execution plan', 'index optimization', 'database performance', '.sql'.
Restructure the 'when' clause to be more explicit, e.g., 'Use when the user asks about slow database queries, needs help reading execution plans, or wants to optimize SQL statements'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'query performance analysis with comprehensive guidance and automation' without listing any concrete actions. It doesn't specify what types of queries, what optimization techniques, or what outputs are produced. | 1 / 3 |
Completeness | It attempts to answer both 'what' and 'when' but the 'what' is extremely vague ('query performance analysis with comprehensive guidance and automation'), and the 'when' is present via trigger phrases but lacks specificity about the actual use cases. | 2 / 3 |
Trigger Term Quality | It includes some relevant trigger phrases like 'optimize queries', 'analyze performance', and 'improve query speed', but misses common variations like 'slow query', 'SQL optimization', 'execution plan', 'index', or 'database performance'. | 2 / 3 |
Distinctiveness Conflict Risk | The term 'query optimization' provides some specificity, but 'analyze performance' is generic enough to conflict with other performance-related skills. It doesn't specify the type of queries (SQL, NoSQL, API) which could cause overlap. | 2 / 3 |
Total | 7 / 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, highly actionable skill with real executable SQL queries, specific diagnostic thresholds, and practical examples with measurable outcomes. Its main weaknesses are the monolithic structure (all three databases in one file without progressive disclosure) and the lack of explicit validation checkpoints in the workflow, particularly important given that some operations (like VACUUM FULL or index creation) can impact production systems. Minor verbosity in the overview and prerequisites sections could be trimmed.
Suggestions
Add explicit validation checkpoints after index creation and query rewrites (e.g., 're-run EXPLAIN ANALYZE to confirm the new plan uses the index; if not, check statistics with ANALYZE and retry')
Split database-specific guidance into separate reference files (e.g., POSTGRESQL.md, MYSQL.md, MONGODB.md) and keep SKILL.md as a concise overview with cross-references—MongoDB is mentioned in prerequisites but barely covered in the instructions
Trim the overview paragraph to avoid restating what the title and section headers already communicate
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with real SQL commands and specific thresholds, but includes some unnecessary verbosity—the overview restates what the title already conveys, the prerequisites section explains what pg_stat_statements does parenthetically, and the examples section could be more compact. The error handling table, while useful, is somewhat lengthy. | 2 / 3 |
Actionability | Provides fully executable SQL queries for every diagnostic step, specific thresholds (e.g., >10,000 rows, cache ratio below 0.95, dead ratio above 0.2), concrete CREATE INDEX patterns, and real-world examples with measurable before/after metrics. The guidance is copy-paste ready throughout. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced from identification through analysis to recommendation and prioritization. However, there are no explicit validation checkpoints or feedback loops—step 8 mentions comparing before/after on staging but doesn't enforce a validate-fix-retry cycle. For operations that could impact production databases, this gap is notable. | 2 / 3 |
Progressive Disclosure | The content is a monolithic single file with no bundle files to reference. At ~120 lines covering PostgreSQL, MySQL, and MongoDB, the database-specific guidance could be split into separate reference files. The external resource links at the end are helpful but the inline content is dense and could benefit from better structural separation. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
3a2d27d
- 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.