dx-data-navigator
Query Developer Experience (DX) data via the DX Data MCP server PostgreSQL database. Use this skill when analyzing developer productivity metrics, team performance, PR/code review metrics, deployment frequency, incident data, AI tool adoption, survey responses, DORA metrics, or any engineering analytics. Triggers on questions about DX scores, team comparisons, cycle times, code quality, developer sentiment, AI coding assistant adoption, sprint velocity, or engineering KPIs.
60
70%
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 ./skills/dx-data-navigator/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.
This is a strong skill description with excellent trigger term coverage and completeness, clearly specifying both what the skill does and when to use it. Its main weakness is that the core action is somewhat generic ('Query') rather than listing multiple specific concrete actions like generating reports, comparing teams, or calculating specific metrics. The rich set of domain-specific trigger terms and explicit 'Use when' and 'Triggers on' clauses make it highly effective for skill selection.
Suggestions
Replace the single verb 'Query' with multiple specific actions such as 'Query, analyze, compare, and visualize Developer Experience (DX) data' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (DX data, PostgreSQL database) and mentions several data areas (PR metrics, deployment frequency, incident data, survey responses), but it describes what data can be queried rather than listing concrete actions like 'generate reports', 'compare teams', or 'calculate DORA metrics'. The primary action is just 'Query'. | 2 / 3 |
Completeness | Clearly answers both 'what' (query DX data via MCP server PostgreSQL database for developer productivity and engineering analytics) and 'when' (explicit 'Use this skill when...' and 'Triggers on...' clauses with detailed trigger scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'developer productivity metrics', 'PR/code review metrics', 'deployment frequency', 'DORA metrics', 'DX scores', 'cycle times', 'code quality', 'developer sentiment', 'AI coding assistant adoption', 'sprint velocity', 'engineering KPIs', 'team comparisons'. These are terms engineers and managers would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: DX Data MCP server, developer experience metrics, DORA metrics, AI tool adoption. The specificity of the data source (DX Data MCP server PostgreSQL database) and the domain-specific trigger terms make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with excellent, executable SQL examples covering a wide range of data domains, and it includes useful data quality warnings. However, it is far too verbose for a SKILL.md file—most of the detailed column listings and query examples should be in the referenced files rather than inline. The content would benefit significantly from being restructured as a concise overview with pointers to the existing reference files.
Suggestions
Move detailed column listings and domain-specific SQL examples into the corresponding reference files (e.g., references/developer-experience.md), keeping only 2-3 essential examples in the main skill file.
Reduce the main skill to a concise overview (~80-100 lines) covering: tool usage, the critical team table distinction, data quality notes, and a reference file navigation table.
Add an explicit workflow for handling query errors or empty results (e.g., 'If query returns no rows: 1. Verify team name exists via dx_teams query, 2. Check date ranges, 3. Inspect information_schema for column availability').
Remove duplicate SQL examples—the team scores query appears identically in both the 'Critical: Team Tables' section and the 'Core DX Metrics' section.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines, with extensive inline SQL examples that could be in reference files. Many query patterns are repeated (e.g., team scores query appears twice). Column listings for every table belong in reference docs, not the main skill file, especially since reference files already exist. | 1 / 3 |
Actionability | Every section provides fully executable SQL queries with correct joins, aggregations, and filtering. The tool invocation syntax is explicit, and queries are copy-paste ready with clear column references and expected output semantics (e.g., 'divide by 3600 for hours'). | 3 / 3 |
Workflow Clarity | The skill provides a good initial step (query information_schema first if uncertain) and clearly distinguishes the three team tables, but lacks an explicit multi-step workflow with validation checkpoints. There's no guidance on what to do when queries return unexpected results or empty sets, and no verification steps for complex joins. | 2 / 3 |
Progressive Disclosure | Reference files exist and are well-organized in the table at the bottom, but the main skill file contains massive amounts of detail (full column listings, dozens of SQL examples) that should live in those reference files. The skill fails to be a concise overview pointing to detailed materials—it duplicates what the references should contain. | 2 / 3 |
Total | 8 / 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
- pskoett/pskoett-ai-skills
- Commit
fe0da1c
- 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.