Diagnoses live CockroachDB cluster performance issues by identifying long-running queries, busy sessions, and active transactions using SQL-only interfaces. Use when users report cluster slowness, high CPU, or need to find runaway queries and their source applications without DB Console access.
90
88%
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, includes natural trigger terms, explicitly states both what the skill does and when to use it, and occupies a distinct niche. It uses proper third-person voice and is concise without being vague.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'identifying long-running queries, busy sessions, and active transactions using SQL-only interfaces.' Also specifies the technology (CockroachDB) and the constraint (without DB Console access). | 3 / 3 |
Completeness | Clearly answers both what ('Diagnoses live CockroachDB cluster performance issues by identifying long-running queries, busy sessions, and active transactions using SQL-only interfaces') and when ('Use when users report cluster slowness, high CPU, or need to find runaway queries and their source applications without DB Console access'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would actually say: 'cluster slowness', 'high CPU', 'runaway queries', 'long-running queries', 'CockroachDB', 'performance issues', 'DB Console access'. These cover common variations of how users describe these problems. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: CockroachDB-specific, SQL-only diagnostics, live cluster performance. The combination of technology (CockroachDB), method (SQL-only), and constraint (without DB Console) makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%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 workflow clarity and concrete, executable SQL queries throughout. Its main weakness is length — the drill-down section and multiple workflow scenarios make it verbose when some of that content could be offloaded to reference files. The safety considerations and verification steps for destructive operations (cancellation) are well-handled.
Suggestions
Move the drill-down filter queries (by application, user, client, combined) to references/sql-queries.md and reference them from the main skill to reduce length
Condense the 'Key columns' explanations after each query — most column meanings are self-evident from the column names and context
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is well-structured but verbose for its purpose. There's some unnecessary explanation (e.g., 'Key columns' sections that explain obvious column names, the 'Core Diagnostic Approach' table that restates what the queries already show). The drill-down section has four very similar query patterns that could be condensed. However, it avoids explaining basic SQL concepts and stays focused on CockroachDB-specific knowledge. | 2 / 3 |
Actionability | All queries are fully executable, copy-paste ready SQL with concrete examples. The skill provides specific query_id/session_id examples for cancellation, customizable thresholds, and real application_name/user_name filter examples. Every diagnostic step has a concrete, runnable query. | 3 / 3 |
Workflow Clarity | The three common triage workflows are clearly sequenced with numbered steps, each building on the previous step's output. The cancellation workflow includes explicit safety warnings, verification steps ('re-run the triage queries to confirm'), and prerequisite checks. The troubleshooting table provides clear error-cause-fix mappings for common failure modes. | 3 / 3 |
Progressive Disclosure | The skill references external files (references/sql-queries.md, references/permissions.md) and related skills, which is good structure. However, the main SKILL.md itself is quite long (~300 lines) with drill-down queries and multiple workflow scenarios that could be moved to reference files. The core diagnostic queries and drill-down filters could be split out, keeping the SKILL.md as a leaner overview. No bundle files were provided to verify referenced paths exist. | 2 / 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.
84bc1e4
Table of Contents
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.