analyzing-database-indexes
Process use when you need to work with database indexing. This skill provides index design and optimization with comprehensive guidance and automation. Trigger with phrases like "create indexes", "optimize indexes", or "improve query performance".
64
77%
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/database/database-index-advisor/skills/analyzing-database-indexes/SKILL.mdQuality
Discovery
89%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 adequately covers when to use the skill with explicit trigger phrases and identifies the domain clearly. However, it suffers from vague capability language ('comprehensive guidance and automation') and the awkward opening 'Process use when' is confusing. The specificity of actual actions the skill performs could be significantly improved.
Suggestions
Replace vague phrases like 'comprehensive guidance and automation' with specific concrete actions such as 'analyze query execution plans, recommend composite indexes, identify missing or redundant indexes, generate CREATE INDEX statements'.
Fix the awkward opening 'Process use when you need to' — this appears to use second person ('you') which should be replaced with third person voice, e.g., 'Designs and optimizes database indexes for improved query performance.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (database indexing) and mentions 'index design and optimization' but lacks specific concrete actions beyond that. 'Comprehensive guidance and automation' is vague filler rather than listing specific capabilities like 'analyze query plans, suggest composite indexes, detect unused indexes'. | 2 / 3 |
Completeness | Explicitly answers both 'what' (index design and optimization) and 'when' (trigger phrases like 'create indexes', 'optimize indexes', 'improve query performance'). The 'Use when' and 'Trigger with' clauses are clearly present. | 3 / 3 |
Trigger Term Quality | Includes natural trigger phrases users would say: 'create indexes', 'optimize indexes', 'improve query performance', and 'database indexing'. These cover common variations of how users would phrase requests in this domain. | 3 / 3 |
Distinctiveness Conflict Risk | Database indexing is a clear, specific niche. The trigger terms ('create indexes', 'optimize indexes', 'improve query performance') are distinct enough to avoid conflicts with general database skills or other optimization skills. | 3 / 3 |
Total | 11 / 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 strong, highly actionable skill with real executable SQL queries and a logical workflow progression from diagnosis to recommendation. Its main weaknesses are moderate verbosity explaining concepts Claude already understands (index selectivity, partial indexes, covering indexes), and the lack of explicit validation/verification checkpoints in a workflow that includes destructive operations like dropping indexes. The monolithic structure works but would benefit from splitting advanced topics into referenced files.
Suggestions
Add explicit validation checkpoints after index creation (e.g., 'Run EXPLAIN ANALYZE on the target query to confirm the new index is used') and after index drops (e.g., 'Monitor write latency for 1 hour to confirm improvement').
Trim explanatory text that teaches Claude known database concepts—remove sentences like 'Partial indexes are smaller and faster than full indexes when the filter eliminates most rows' and 'The INCLUDE columns are stored in the index leaf pages, enabling index-only scans without heap access'.
Split MySQL-specific guidance into a separate MYSQL.md reference file, since the skill mentions MySQL in prerequisites but all queries are PostgreSQL-specific.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with real SQL queries and concrete guidance, but includes some unnecessary verbosity in explanations (e.g., explaining what sequential scans mean, what partial indexes are, what INCLUDE does). Claude already knows these database concepts. The examples section, while useful, is somewhat narrative-heavy and could be more compact. | 2 / 3 |
Actionability | Excellent actionability with fully executable SQL queries throughout, specific column references, concrete CREATE INDEX and DROP INDEX statements, and real EXPLAIN usage. Every step provides copy-paste ready commands with clear parameters and expected interpretations. | 3 / 3 |
Workflow Clarity | The 10-step workflow is clearly sequenced from identification through recommendation, but lacks explicit validation checkpoints and feedback loops. There's no 'verify the index was created correctly' step, no 'confirm query performance improved after index creation' checkpoint, and no error recovery loop within the main workflow despite this being a potentially destructive operation (dropping indexes). | 2 / 3 |
Progressive Disclosure | The content is a monolithic single file with no bundle files for supporting material. The error handling table, examples, and resources sections are well-structured internally, but the detailed 10-step instructions, MySQL-specific guidance, and advanced topics (partial indexes, covering indexes) could benefit from being split into separate referenced files. For a skill of this length (~120+ lines of substantive content), more structure would help. | 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
69c73e9
- 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.