panel-majority-vote
Runs 3 isolated reviewer sub-agents and consolidates a PASS/BLOCK verdict by majority. Use when the user requests an independent review of code changes, pull requests, design documents, or release notes.
75
92%
Does it follow best practices?
Impact
—
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 a strong skill description that concisely communicates a unique mechanism (multi-agent review with majority voting), lists concrete outputs (PASS/BLOCK verdict), and provides explicit trigger guidance via a 'Use when' clause with natural user terms. It uses proper third-person voice and is distinctive enough to avoid conflicts with simpler review or linting skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Runs 3 isolated reviewer sub-agents', 'consolidates a PASS/BLOCK verdict by majority'. These are precise, concrete mechanisms describing what the skill does. | 3 / 3 |
Completeness | Clearly answers both 'what' (runs 3 isolated reviewer sub-agents and consolidates a PASS/BLOCK verdict by majority) and 'when' (explicit 'Use when' clause specifying independent review of code changes, pull requests, design documents, or release notes). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'review', 'code changes', 'pull requests', 'design documents', 'release notes', 'independent review'. These cover common variations of how users would request this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with its specific mechanism (3 isolated sub-agents, majority verdict, PASS/BLOCK). The 'independent review' framing and multi-agent architecture clearly distinguish it from a simple code review or linting skill. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with clear workflow sequencing, good progressive disclosure, and efficient use of tokens. Its main weakness is that some critical steps (subagent spawning, deduplication logic) are described abstractly rather than with fully executable examples. The bash snippet for vote counting is a good start but the most complex parts of the workflow lack equivalent concrete guidance.
Suggestions
Add a concrete example of the `runSubagent` invocation showing the exact prompt structure and parameters passed to each reviewer.
Provide executable code or pseudocode for the deduplication and annotation logic (merging MUST-FIX/SHOULD-FIX items with '(N/3 reviewers)' counts).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. It avoids explaining what code review is, what majority voting means, or other concepts Claude already knows. Every section serves a clear purpose with no padding or unnecessary context. | 3 / 3 |
Actionability | The procedure provides concrete steps and includes an executable bash snippet for counting verdicts, but key parts remain abstract—e.g., how to 'spawn 3 reviewers using runSubagent' lacks a concrete invocation example, and the consolidation/deduplication logic is described rather than shown in code. | 2 / 3 |
Workflow Clarity | The 7-step procedure is clearly sequenced with explicit validation (step 1 scope validation), a hard gate logging step (step 7), and error recovery guidance (re-run on BLOCK, dispute after 3 consecutive BLOCKs). The feedback loop for BLOCK verdicts is well-defined. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references to related resources (panel-report.template.md, REFERENCE.md, observability-logging skill, team-lead-reference skill). Content is appropriately split between the main procedure and referenced materials. | 3 / 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
- monkilabs/opencastle
- Commit
cc13aaf
- 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.