profiling-statement-fingerprints
Ranks and analyzes statement fingerprints using aggregated SQL statistics from crdb_internal.statement_statistics to identify slow, resource-intensive, or error-prone query patterns. Use when investigating historical performance trends, identifying optimization opportunities, or diagnosing recurring slowness without DB Console access.
89
86%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 is an excellent skill description that clearly articulates specific capabilities (ranking/analyzing statement fingerprints from CockroachDB internal statistics), includes rich natural trigger terms spanning performance investigation scenarios, and explicitly states both what it does and when to use it. The domain-specific terminology like 'crdb_internal.statement_statistics' and 'DB Console' make it highly distinctive and unlikely to conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Ranks and analyzes statement fingerprints', 'using aggregated SQL statistics from crdb_internal.statement_statistics', 'identify slow, resource-intensive, or error-prone query patterns'. These are precise, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Ranks and analyzes statement fingerprints using aggregated SQL statistics...to identify slow, resource-intensive, or error-prone query patterns') and when ('Use when investigating historical performance trends, identifying optimization opportunities, or diagnosing recurring slowness without DB Console access'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'statement fingerprints', 'statement_statistics', 'slow', 'resource-intensive', 'error-prone', 'query patterns', 'historical performance trends', 'optimization opportunities', 'recurring slowness', 'DB Console'. Good coverage of terms a DBA or developer would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific references to 'crdb_internal.statement_statistics', 'statement fingerprints', and 'DB Console access' which clearly tie it to CockroachDB query performance analysis. Unlikely to conflict with other skills due to the narrow, well-defined niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%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 excellent executable SQL queries and good progressive disclosure to reference materials. Its main weaknesses are moderate verbosity in the conceptual sections (Core Concepts could be trimmed significantly) and workflows that lack explicit validation/verification checkpoints. The seven diagnostic queries are the standout strength—each is production-ready with clear interpretation guidance.
Suggestions
Trim the 'Core Concepts' section significantly—Claude doesn't need explanations of JSON operators (`->` vs `->>`), what a statement fingerprint is, or how time bucketing works. Keep only the CockroachDB-specific gotchas (sampled metrics NULL check, unit conversions).
Add validation checkpoints to workflows, e.g., 'Verify the fingerprint appears in multiple time buckets before concluding it's a persistent pattern' or 'Confirm execution count is statistically significant before acting on mean latency.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally well-structured but includes some unnecessary explanation (e.g., the 'Core Concepts' section explaining JSON operators, statement fingerprints vs live queries, and aggregated vs sampled metrics adds context Claude likely already knows or could infer). The diagnostic queries themselves are lean and well-annotated, but the overall document is quite long (~300+ lines) with some redundancy in safety/troubleshooting sections. | 2 / 3 |
Actionability | All seven diagnostic queries are fully executable, copy-paste ready SQL with proper type casting, time filters, and LIMIT clauses. Each query includes specific interpretation guidance and thresholds (e.g., '>20% contention', 'mean_run_lat_seconds > 5'). The workflows connect queries to concrete remediation steps. | 3 / 3 |
Workflow Clarity | The four workflows provide clear sequencing and logical progression, but they lack explicit validation checkpoints or feedback loops. For example, Workflow 1 doesn't specify how to verify that identified slow fingerprints are actually the root cause before proceeding to remediation. The workflows are more like checklists than validated step-by-step processes with error recovery. | 2 / 3 |
Progressive Disclosure | The skill has a clear overview structure with well-signaled references to JSON field reference, metrics catalog, SQL query variations, and related skills. Cross-references to sibling skills (triaging-live-sql-activity, profiling-transaction-fingerprints) are clearly signaled with context about when to use each. The main content stays at the right level of detail with deeper material delegated to reference files. | 3 / 3 |
Total | 10 / 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
- cockroachlabs/cockroachdb-skills
- Commit
84bc1e4
- 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.