judgment-day

Trigger: judgment day, dual review, adversarial review, juzgar. Run explicit blind dual review with at most two scoped fix/re-judgment rounds.

Quality

89%

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

96%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 an exceptionally lean, action-dense orchestration contract with a clear sequenced workflow, named actors, decision gates, and validation checkpoints. Its single weakness is a non-existent shared-reference path that slightly undermines progressive-disclosure navigation.

Suggestions

Fix or remove the broken reference '../_shared/review-ledger-contract.md' (the _shared directory is not present in the bundle), or note it as an optional external sibling to avoid a dead link.

Optionally inline a one-line example of the 'neutral findings result' shape the judges must return, so the Output Contract is fully copy-paste ready without opening the references file.

Dimension	Reasoning	Score
Conciseness	The body is a lean, directive contract that assumes Claude's competence — naming agents and rules without restating what a review or ledger is. Every section earns its tokens with no padding or known-concept explanation. Matches the top 'lean and efficient' anchor; not 4 because there are no noticeable over-explanation instances to trim.	5 / 5
Actionability	Provides concrete, executable guidance: named sub-agents ('jd-judge-a', 'jd-fix-agent', 'jd-fix-agent'), a precise Decision Gates table, and an exact Output Contract with terminal verdicts ('JUDGMENT: APPROVED / ESCALATED'). Coverage of common cases is complete. Matches the top anchor; not 4 because the guidance is copy-paste ready and covers the standard flow end to end.	5 / 5
Workflow Clarity	Execution Steps are explicitly sequenced with validation checkpoints ('Wait for both; never accept a partial judgment', 'Ask before round-one correction', bounded re-judgment rounds) and a Decision Gates feedback table. The destructive/batch cap is satisfied because fixes are gated on dual confirmation and round limits. Matches the top anchor with explicit validation and feedback loops; not 4 because checkpoints are present throughout rather than mostly.	5 / 5
Progressive Disclosure	The body is well-organized into clear sections and points one level deep to a real bundle file ('references/prompts-and-formats.md', which exists). However the second reference '../_shared/review-ledger-contract.md' does not exist in the bundle, a minor navigation gap. Fits 'good structure, references mostly clear'; not 5 because of the broken/external shared reference, and not 3 because most content is appropriately placed and signaled.	4 / 5
	Total	19 / 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 a tight, third-person trigger declaration that explicitly covers both what the skill does and when to invoke it, with distinctive trigger terms. Its only weakness is modest specificity about the full set of concrete capabilities, which the body elaborates.

Suggestions

Add one or two more concrete actions (e.g., 'merge findings into a frozen ledger', 'return APPROVED or ESCALATED verdict') to lift specificity beyond the 1-2-action anchor.

Consider listing common natural synonyms beyond 'juzgar' (e.g., 'compare two reviews', 'contested review') to widen trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('blind dual review') and 1-2 concrete actions ('run explicit blind dual review', 'scoped fix/re-judgment rounds') but is not comprehensive about the skill's full capability surface. Matches the anchor 'Names domain and 1-2 concrete actions'; below score 4 which expects several specific actions, and above score 2 which only names the domain.	3 / 5
Completeness	Explicitly answers both what ('Run explicit blind dual review with at most two scoped fix/re-judgment rounds') and when ('Trigger: judgment day, dual review, adversarial review, juzgar') with concrete trigger phrases. Fits the top anchor; not 4 because the when-clause is concrete and explicit, not merely adequate.	5 / 5
Trigger Term Quality	Includes multiple natural trigger terms via the explicit 'Trigger:' label ('judgment day, dual review, adversarial review, juzgar') with a synonym included. Good keyword coverage; a few natural variations might be missing, so it sits above score 3 and just below the comprehensive anchor at 5.	4 / 5
Distinctiveness Conflict Risk	The distinctive trigger terms ('judgment day', 'juzgar', 'adversarial review') carve a clear niche with minimal overlap risk against other skills. Matches the top anchor for a clear niche with distinct triggers.	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: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: Gentleman-Programming/gentle-ai
Path: internal/assets/skills/judgment-day/SKILL.md
Commit: 71cf25f

Reviewed: 4 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.