performance-engineer
Expert performance engineer specializing in modern observability,
15
0%
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/performance-engineer/SKILL.mdQuality
Discovery
0%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 is extremely weak across all dimensions. It reads as an incomplete fragment (ending with a comma) that uses vague role-based language ('expert performance engineer') instead of describing concrete capabilities. It also uses first/third-person role framing rather than action-oriented language, and completely lacks trigger guidance.
Suggestions
Replace the role-based framing with specific concrete actions, e.g., 'Analyzes application performance bottlenecks, configures distributed tracing, builds monitoring dashboards, and optimizes latency issues.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user mentions performance issues, slow responses, observability, metrics, tracing, monitoring, or APM tools like Prometheus, Grafana, Datadog, or OpenTelemetry.'
Complete the description—it currently ends with a comma—and ensure it clearly distinguishes this skill's niche from related skills like general debugging or infrastructure management.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language ('expert performance engineer') without listing any concrete actions. It does not describe what the skill actually does—no verbs like 'analyze', 'monitor', 'diagnose', etc. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. There is no 'Use when...' clause and the 'what' is extremely vague. The description also appears truncated (ends with a comma). | 1 / 3 |
Trigger Term Quality | The only potentially relevant keywords are 'performance' and 'observability', which are broad and jargon-heavy. Missing natural user terms like 'latency', 'metrics', 'tracing', 'monitoring', 'dashboards', 'APM', etc. | 1 / 3 |
Distinctiveness Conflict Risk | 'Performance engineer' and 'observability' are broad enough to overlap with many potential skills (monitoring, debugging, profiling, infrastructure). There are no distinct triggers to differentiate this skill. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a persona description and technology catalog rather than actionable guidance. It lists hundreds of tools and concepts Claude already knows without providing any concrete code, commands, configurations, or executable workflows. The content would need a fundamental restructuring to be useful—replacing the exhaustive lists with specific, actionable procedures and examples for the most common performance engineering tasks.
Suggestions
Replace the extensive 'Capabilities' bullet lists with 2-3 concrete, executable workflow examples (e.g., a complete k6 load test script, an OpenTelemetry setup snippet, a database query optimization walkthrough with EXPLAIN output).
Add explicit validation checkpoints to the workflow, especially around load testing safety (e.g., 'Before running: verify target environment is non-production with `kubectl get context`, confirm rate limits are set, ensure monitoring dashboards are open').
Remove sections that only catalog tools Claude already knows (Knowledge Base, most of Capabilities, Behavioral Traits) and replace with decision trees or concrete guidance (e.g., 'If latency > 500ms at p99, start with distributed trace analysis using: [specific command]').
Split detailed reference material (tool-specific configurations, platform-specific profiling commands) into separate bundle files and reference them from a concise SKILL.md overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and padded. The vast majority of content is exhaustive bullet-point lists of tools, platforms, and concepts Claude already knows. Sections like 'Capabilities', 'Knowledge Base', 'Behavioral Traits', and 'Example Interactions' are largely redundant catalogs that don't add actionable value. The skill could be reduced by 80%+ without losing useful guidance. | 1 / 3 |
Actionability | No concrete code, commands, or executable examples anywhere. The entire skill is abstract descriptions and tool name-dropping. The 'Instructions' section has four vague steps ('Collect traces, profiles, and load tests to isolate bottlenecks') with no specific commands, configurations, or code snippets. Nothing is copy-paste ready. | 1 / 3 |
Workflow Clarity | The 'Instructions' section lists 4 high-level steps and the 'Response Approach' lists 9, but both are vague and lack validation checkpoints, feedback loops, or concrete sequencing. For a skill involving potentially destructive operations like load testing production systems, there are no explicit verification steps or error recovery procedures. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no external references or file structure. All content is dumped inline in a single massive file with 12+ capability subsections that could be split into focused reference documents. No bundle files exist to support progressive disclosure. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
76aea27
- 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.