panel-majority-vote

Runs 3 isolated reviewer sub-agents; consolidates PASS/BLOCK verdict by majority. Use when user requests independent review of code changes, pull requests, design documents, or release notes.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a tight, well-sequenced workflow with executable bash and proper validation/feedback loops. Its main weakness is progressive disclosure: two referenced bundle files (panel-report.template.md, REFERENCE.md) and the referenced skills (observability-logging, team-lead-reference) are not present or located.

Suggestions

Add the missing bundle files referenced in the body (panel-report.template.md and REFERENCE.md), or remove the references if those materials are not part of this skill.

For each external skill referenced (observability-logging, team-lead-reference), note where it is found or how it is invoked so the navigation is resolvable rather than dangling.

Inline a minimal report skeleton in step 5 instead of pointing to an absent template, so the report-writing step is fully self-contained.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept over-explanation or padding; the procedural steps and bash block each earn their place, matching the "lean and efficient; every token earns its place" anchor.	5 / 5
Actionability	The grep/wc/jq counting block and the required reviewer output sections are mostly executable, but the "Write report" step relies on a panel-report.template.md that is not present, leaving a minor gap, matching anchor 4.	4 / 5
Workflow Clarity	The 7-step sequence has explicit validation (scope check in step 1, verdict logic in step 4) plus a feedback loop (Notes: re-run on BLOCK without re-wording) and a hard-gate logging step, matching the anchor 5 example.	5 / 5
Progressive Disclosure	Sectioning and the inputs/outputs table give some structure, but body references to panel-report.template.md and REFERENCE.md do not resolve to real bundle files (no references/ dir exists), and external skills are named without location, matching the "references present but not clearly signaled / could be better organized" anchor.	3 / 5
	Total	17 / 20 Passed

Description

82%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong, clearly answering both what the skill does and when to use it with concrete, natural trigger terms and a distinct niche. The only gap is that the capability list is compact rather than comprehensive, which keeps specificity at 3.

Dimension	Reasoning	Score
Specificity	"Runs 3 isolated reviewer sub-agents; consolidates PASS/BLOCK verdict by majority" names the domain and two concrete actions but is not a comprehensive enumeration of capabilities, matching anchor 3.	3 / 5
Completeness	It explicitly states both what it does (runs 3 reviewers, consolidates PASS/BLOCK by majority) and when to use it ("Use when user requests independent review of ...") with concrete trigger phrases, matching anchor 5.	5 / 5
Trigger Term Quality	"independent review of code changes, pull requests, design documents, or release notes" gives good natural keyword coverage a user would say, with only a few synonyms (diff, patch) missing, matching anchor 4.	4 / 5
Distinctiveness Conflict Risk	The multi-reviewer panel / majority-vote niche with distinct review triggers is unlikely to fire for the wrong skill, matching the "clear niche with distinct triggers; minimal conflict risk" anchor.	5 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: monkilabs/opencastle
Path: src/orchestrator/skills/panel-majority-vote/SKILL.md
Commit: f297837

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.