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

87%

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%

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-structured orchestration overview with strong sequencing, validation checkpoints, and clean progressive disclosure via one-level references. Its only weakness is actionability, since the copy-paste executable prompts live in the reference rather than the body.

Suggestions

Inline a minimal executable judge-invocation snippet or show the exact native result JSON shape inline so the body is copy-paste actionable without opening the reference.

Add a one-line example of a concrete target/scope argument to the `review/start(...)` call so the launch command is unambiguous.

Consider an inline minimal verdict/receipt example so the Output Contract's "exactly one final JUDGMENT" rule is demonstrable in place.

Dimension	Reasoning	Score
Conciseness	The body is lean and imperative — terse hard rules, a compact decision-gate table, and short numbered steps that assume Claude's competence with no padding or concept explanation, matching the score-3 anchor.	3 / 3
Actionability	Concrete guidance is present (e.g., `review/start(target, mode=judgment_day)`, exact terminal states `approved \| escalated`, exact receipt strings), but the fully executable judge/fix prompts are offloaded to the referenced file rather than inline, leaving key executable detail external, matching the score-2 anchor.	2 / 3
Workflow Clarity	Execution Steps 1-6 give a clear sequence with explicit checkpoints ("Wait for both," "Ask before round-one correction," bounded rounds) and a fix -> re-judgment -> escalate feedback loop, matching the score-3 anchor.	3 / 3
Progressive Disclosure	The body is a well-organized overview with clearly signaled one-level-deep references — the verified `references/prompts-and-formats.md` and the labeled canonical `../_shared/review-ledger-contract.md` — splitting detailed prompts out appropriately, matching the score-3 anchor.	3 / 3
	Total	11 / 12 Passed

Description

90%

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 packs an explicit trigger clause plus a clear what/when statement. It is strong on triggers, completeness, and distinctiveness, with only specificity slightly lower because the action list is not comprehensive.

Dimension	Reasoning	Score
Specificity	Names the review domain and concrete actions like "Run explicit blind dual review" and "scoped fix/re-judgment rounds," but does not enumerate a comprehensive set of specific actions, matching the score-2 anchor.	2 / 3
Completeness	It answers both what ("Run explicit blind dual review with at most two scoped fix/re-judgment rounds") and when (explicit "Trigger:" clause), satisfying the score-3 anchor for explicit triggers.	3 / 3
Trigger Term Quality	The explicit "Trigger: judgment day, dual review, adversarial review, juzgar" phrase gives good coverage of natural terms a user would say, including the alternate "juzgar," matching the score-3 anchor.	3 / 3
Distinctiveness Conflict Risk	The dual/adversarial review niche with distinct trigger terms ("judgment day," "dual review," "adversarial review") is unlikely to fire for unrelated skills, matching the score-3 anchor.	3 / 3
	Total	11 / 12 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: e01b114

Reviewed: about 14 hours 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.