review-performance
Performance review instructions for the expert agent
56
46%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./dot_config/opencode/skill/review-performance/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 critically underspecified. It fails to articulate what concrete actions the skill performs, provides no trigger guidance for when Claude should select it, and uses vague language ('instructions for the expert agent') that offers no differentiation from other skills. It would be nearly unusable in a multi-skill selection scenario.
Suggestions
List specific concrete actions the skill performs, e.g., 'Drafts employee performance reviews, generates competency ratings, summarizes peer feedback, and creates improvement plans.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about performance reviews, annual evaluations, employee feedback, self-assessments, or 360 reviews.'
Remove the vague 'expert agent' phrasing and replace with a clear statement of the skill's domain and scope to reduce conflict risk with other HR or writing skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description is extremely vague — 'performance review instructions' names a broad domain but lists no concrete actions (e.g., drafting reviews, rating competencies, generating feedback). 'Expert agent' is abstract jargon. | 1 / 3 |
Completeness | The description barely addresses 'what' (performance review instructions) and completely omits 'when' — there is no 'Use when...' clause or any explicit trigger guidance. | 1 / 3 |
Trigger Term Quality | The only potentially useful trigger term is 'performance review,' but it lacks natural variations users might say (e.g., 'annual review,' 'employee evaluation,' 'feedback,' '360 review'). 'Expert agent' is not a user-facing term. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so generic that it could overlap with any HR-related, writing, or feedback skill. There are no distinct triggers or scoping details to differentiate it. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
92%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, well-crafted performance review skill that is concise, actionable, and clearly structured. It excels at defining scope boundaries (what to report vs. escalate), provides specific thresholds and patterns to look for, and includes a precise output schema. The only minor weakness is that all content is inline rather than linking to supplementary reference material for the various issue categories.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and purposeful. No unnecessary explanations of what performance issues are or how Ruby/Rails works. Assumes Claude knows the domain and gets straight to actionable checklists. | 3 / 3 |
Actionability | Provides concrete, specific guidance: exact issue types to look for (N+1, missing indexes, callback multiplication), specific thresholds (100+ options, 1000+ rows), specific tools (git blame), and a precise JSON output schema. The exploration phase has clear numbered steps with specific actions. | 3 / 3 |
Workflow Clarity | Clear two-phase workflow: exploration first (with numbered steps), then findings output. Includes validation-like checkpoints (read full file before findings, check prior reviews, confirm origin with git blame). The escalation mechanism provides a clear boundary for scope management. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections (Phase 1, Scope, Escalations, Rules, Output), but everything is in a single file. For a skill of this complexity (~50 lines), this is borderline acceptable, but the scope section could benefit from linking to detailed examples or patterns for each issue type rather than listing them inline. | 2 / 3 |
Total | 11 / 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
- athal7/dotfiles
- Commit
07d79b6
- 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.