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

80%

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

Fix and improve this skill with Tessl

tessl review fix ./src/orchestrator/skills/panel-majority-vote/SKILL.md

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 procedure is concise, sequenced, and actionable, with explicit validation checkpoints and error-recovery loops. Its one real defect is broken progressive disclosure: the body points to template/reference files that are missing from the skill bundle.

Suggestions

Add the missing panel-report.template.md and REFERENCE.md to the bundle, or inline the minimal report structure so step 5 does not depend on a nonexistent file.

Verify that the observability-logging skill and team-lead-reference resources are actually available, and state their expected location so steps 7 and the Notes are followable.

Dimension	Reasoning	Score
Conciseness	The body is lean and dense: an inputs/outputs table, terse numbered steps, and a single bash snippet that earns its place. It assumes Claude's competence and never explains concepts Claude already knows, matching the top anchor.	5 / 5
Actionability	Mostly executable: exact file paths, required reviewer output sections, and a concrete grep/jq snippet for tallying votes. However, step 5 builds the report from ./panel-report.template.md and step 7 calls the observability-logging skill, neither of which exists in the bundle, so guidance is not fully executable — a minor gap rather than the vague/pseudocode level of anchor 3.	4 / 5
Workflow Clarity	Clear 1–7 sequence with explicit validation (step 1 scope validation, step 7 hard-gate logging verification), an explicit majority rule (PASS if pass_count >= 2), and feedback loops for error recovery (on BLOCK: change work and re-run; after 3 consecutive BLOCKs: dispute protocol). This is not a destructive or batch operation, so the cap does not apply.	5 / 5
Progressive Disclosure	Sections are well organized (Inputs/Outputs, Procedure, Notes) and references are clearly signaled and one level deep, but the referenced files panel-report.template.md and REFERENCE.md do not exist anywhere in the bundle, so the navigation paths are broken. Scored against the actual (empty) bundle structure, this lands at anchor 3 rather than 4.	3 / 5
	Total	17 / 20 Passed

Description

75%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 concise, third-person, and cleanly answers what and when with explicit triggers. Its main weaknesses are modest action coverage and trigger overlap with generic code-review skills.

Suggestions

Add one or two more concrete actions (e.g., persisting reviewer outputs, writing a consolidated report) to lift specificity.

Add distinctive trigger phrases such as "majority-vote panel" or "multi-reviewer consensus" to differentiate from single-reviewer code-review skills.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ("Runs 3 isolated reviewer sub-agents"; "consolidates PASS/BLOCK verdict by majority") but omits other real capabilities (persisting outputs, report writing, logging gate), so it is not comprehensive. Anchor 4 would require several listed actions with only minor gaps.	3 / 5
Completeness	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 top anchor.	5 / 5
Trigger Term Quality	Good natural keyword coverage ("independent review", "code changes", "pull requests", "design documents", "release notes") that users would actually say. A few common variants like "code review", "PR review", or "sign-off" are missing, so it falls short of anchor 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	The majority-vote panel mechanism is a distinct niche, but the trigger phrases "independent review of code changes, pull requests" overlap substantially with generic code-review skills a user would invoke with the same words. Overlap risk is more than minor, so it sits at anchor 3 rather than 4.	3 / 5
	Total	15 / 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: c0f4566

Reviewed: 1 day 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.