review-performance
Performance review instructions for the expert agent
66
Quality
50%
Does it follow best practices?
Impact
93%
2.81xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./dot_config/opencode/skill/review-performance/SKILL.mdDiscovery
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 critically underdeveloped and would fail to help Claude select the appropriate skill. It lacks concrete actions, natural trigger terms, explicit usage guidance, and any distinguishing characteristics. The phrase 'for the expert agent' is internal jargon that provides no value for skill selection.
Suggestions
Specify concrete actions the skill performs (e.g., 'Drafts performance review feedback, structures evaluation criteria, generates improvement recommendations')
Add a 'Use when...' clause with natural trigger terms like 'performance review', 'employee evaluation', 'annual review', 'feedback for direct report', '360 review'
Remove internal jargon ('expert agent') and rewrite in third person describing what the skill does, not what it is
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language ('instructions for the expert agent') without describing any concrete actions. It doesn't specify what the skill actually does with performance reviews. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. There's no 'Use when...' clause and no explanation of capabilities—only a vague reference to 'instructions'. | 1 / 3 |
Trigger Term Quality | The only potentially useful trigger term is 'performance review', but 'expert agent' is technical jargon users wouldn't naturally say. Missing common variations like 'annual review', 'employee evaluation', 'feedback', etc. | 1 / 3 |
Distinctiveness Conflict Risk | The description is too vague to establish a clear niche. 'Instructions for the expert agent' could apply to almost anything, and 'performance review' alone doesn't distinguish it from other HR or feedback-related skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill that demonstrates best practices across all dimensions. It provides a clear two-phase workflow with mandatory exploration before findings, concrete examples of expected output formats, and well-scoped criteria. The escalation mechanism for out-of-scope issues and the pre-existing tag for base branch problems show thoughtful design.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, with no unnecessary explanations of concepts Claude already knows. Every section serves a clear purpose and the token budget is well-respected. | 3 / 3 |
Actionability | Provides concrete, executable guidance with specific examples of exploration logs, exact JSON output format, and clear categories of what to look for. The scope section gives precise, actionable criteria. | 3 / 3 |
Workflow Clarity | Excellent two-phase workflow with explicit validation checkpoint (Phase 1 exploration log must be output before findings). Clear sequence with feedback loop for verifying issues via git blame before reporting. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections (Phase 1, Phase 2, Scope, Escalations, Rules, Output Format). Content is appropriately structured for a single-file skill with no need for external references. | 3 / 3 |
Total | 12 / 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.
- 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.