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

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

78%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.

A dense, well-sequenced procedural body with executable vote-tallying code and explicit validation/hard-gate checkpoints. Its main weakness is progressive disclosure: the body links to a template and a REFERENCE.md that are not present in the bundle.

Suggestions

Add the referenced ./panel-report.template.md and ./REFERENCE.md to the bundle (or remove the links and inline the minimal report structure), so the signaled one-level-deep references resolve to real files.

Spell out the recovery branch when scope validation (step 1) fails — e.g. "if artifacts are insufficient or outside <runRoot>, stop and report what is missing" — to close the workflow_clarity feedback loop.

Make the reviewer-spawn step more directly actionable by showing the runSubagent call shape (prompt + constraints) instead of only describing it, so the actionability gap near copy-paste readiness is closed.

Dimension	Reasoning	Score
Conciseness	The body is lean and imperative, with no padding or explanation of concepts Claude already knows (e.g. no definition of "reviewer" or "majority vote"); every section (Inputs/Outputs table, 7-step procedure, bash block, Notes) earns its tokens.	5 / 5
Actionability	Provides executable bash (grep/jq vote tallying), exact file paths, the explicit "PASS if pass_count >= 2" rule, and required output sections, but the report step depends on a referenced template file that is absent and the runSubagent calls are described abstractly rather than as copy-pasteable invocations.	4 / 5
Workflow Clarity	A clearly sequenced 7-step procedure with an explicit scope-validation checkpoint (step 1) and a hard-gate logging step for verification (step 7), plus a BLOCK retry feedback loop in Notes; the minor gap is the lack of an explicit recovery branch when scope validation fails.	4 / 5
Progressive Disclosure	Structure is clean and references are signaled one level deep ([panel-report.template.md], [REFERENCE.md], and the observability-logging / team-lead-reference skills), but those referenced bundle files do not exist, so the navigation points to dangling targets — a real organizational defect beyond a minor gap.	3 / 5
	Total	16 / 20 Passed

Description

83%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.

A strong, third-person description with an explicit "Use when..." trigger clause and concrete, domain-specific actions. It clearly answers both what the skill does and when to invoke it, with only minor gaps in action breadth and trigger synonyms.

Dimension	Reasoning	Score
Specificity	"Runs 3 isolated reviewer sub-agents" and "consolidates PASS/BLOCK verdict by majority" name two concrete, domain-specific actions with mechanism detail (count, verdict type, voting rule), but the enumeration is not comprehensive enough for a 5.	4 / 5
Completeness	It explicitly answers both what ("Runs 3 isolated reviewer sub-agents; consolidates PASS/BLOCK verdict by majority") and when ("Use when user requests independent review of code changes, pull requests, design documents, or release notes") with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	"independent review of code changes, pull requests, design documents, or release notes" supplies several natural phrases users would say, but is missing a few common synonyms (e.g. "PR review", "design review") that would warrant a 5.	4 / 5
Distinctiveness Conflict Risk	The "panel majority vote" / "3 isolated reviewers" / "PASS-BLOCK majority" framing carves a distinct niche with specific triggers, but there is minor overlap risk with generic code-review or review-orchestration skills, keeping it just below 5.	4 / 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: fa0c341

Reviewed: 5 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.