the-jury

Use when a question, decision, plan, tradeoff, or claim needs a rigorous verdict and one perspective is not enough. Spawns a panel of 3 to 5 subagent jurors that form independent blind opinions, deliberate anonymously under an anti-anchoring and anti-sycophancy protocol, and return one committed verdict with confidence, preserved dissent, and a concrete next action. Domain-agnostic across engineering, architecture, data, product, hiring, strategy, vendor choice, build-vs-buy, and research design. Trigger phrases include "convene a jury", "have agents debate and decide", "get a panel to decide", "multi-agent decision", "stress-test this and decide", "monte um juri", "tribunal de agentes", "painel para decidir". Do NOT use to only critique without deciding (use the-fool for that), to build a plan or write the solution itself, or for simple factual lookups.

Quality

92%

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.

A well-structured protocol skill with clear sequenced workflow, strong validation feedback loops, and exemplary progressive disclosure backed by real bundle files. Minor conciseness loss from reinforced rules and slight actionability loss from delegated prompt templates keep it just below the top band on those two dimensions.

Suggestions

Consolidate the flip-must-cite-reason and homogeneity-cap rules into a single canonical statement, then cross-reference it from the other phases to remove the repetition.

Inline at least the Round 1 blind prompt template (or its key fields) in SKILL.md so the most critical operational step is fully executable without opening references/deliberation-craft.md.

Dimension	Reasoning	Score
Conciseness	Dense, instructive, and assumes Claude's competence ('apply it, do not lecture about it'), but the flip-must-cite rule and homogeneity cap are each repeated across Phase 3, Phase 4, Constraints, and Troubleshooting, which is mild reinforcement-padding.	4 / 5
Actionability	Provides concrete executable guidance: exact phase sequence, juror return-block fields, the tally command with full JSON shape, a by-hand cascade, and a copy-paste verdict template; the only gap is Round 1/2 prompt templates being delegated to a reference rather than inline.	4 / 5
Workflow Clarity	Clear six-phase sequence with explicit validation checkpoints (blind Round 1 gate, anonymization, flip-audit, SUSPECT fallback to independent aggregate, adaptive stop, 2-round cap, tie-break rule) plus a troubleshooting section for error recovery.	5 / 5
Progressive Disclosure	Verified against the actual bundle: SKILL.md is an overview and references/juror-archetypes.md, references/deliberation-craft.md, and scripts/tally.py are all real one-level-deep files, clearly signaled in a dedicated 'Reference files (read on condition)' section with read-timing guidance.	5 / 5
	Total	18 / 20 Passed

Description

100%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 that concretely states multiple capabilities, supplies exhaustive natural and multilingual trigger phrases, and explicitly scopes both when to use and when not to use the skill. Voice is correctly third-person throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions (form independent blind opinions, deliberate anonymously under an anti-anchoring/anti-sycophancy protocol, return one committed verdict with confidence, preserved dissent, and a concrete next action) with comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (spawns 3-5 jurors, blind opinions, anonymous deliberation, committed verdict) and when (Use when a question/decision/plan/tradeoff/claim needs a rigorous verdict) with concrete trigger phrases and negative guidance.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including synonyms ('convene a jury', 'have agents debate and decide', 'get a panel to decide', 'stress-test this and decide') and multilingual variants, exceeding the 'a few terms missing' level below.	5 / 5
Distinctiveness Conflict Risk	Clear niche of multi-agent deliberated verdict with distinct triggers and explicit disambiguation against the-fool ('Do NOT use to only critique without deciding'), minimizing conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tech-leads-club/agent-skills
Path: packages/skills-catalog/skills/(decision-making)/the-jury/SKILL.md
Commit: 120b676

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.