CtrlK
BlogDocsLog inGet started
Tessl Logo

five-punishments-judicial-procedure

Use when adjudicating criminal cases or determining punishments under the five-tier system. Applies graduated verification from 五刑 to 五罚 to 五过, with doubt-based amnesty protocols and fine schedules for 3,000 categorized crimes.

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 delivers a clear, well-structured procedural framework with concrete decision logic, fine schedules, and a validation checklist. The main improvements are removing the generic 'Expected Outcomes' padding, defining the undefined flaw terms, and adding an explicit validation-retry feedback loop.

Suggestions

Remove or sharpen the 'Expected Outcomes' section, which reads as generic benefit statements rather than instruction.

Define the undefined flaw terms (官狱, 内狱) under 'Handling Judicial Errors' so the mitigation step is actionable.

Add an explicit feedback loop to the Validation section (e.g., 'if a check fails, re-run the graduated process or grant amnesty per the doubt protocol') to push workflow clarity toward 5.

DimensionReasoningScore

Conciseness

The body is mostly efficient with tight tables and bullet lists; the 'Expected Outcomes' section ('Fair adjudication with graduated response', 'Reduced wrongful convictions') is generic benefit language that could be trimmed, keeping it just below the lean/5 anchor.

4 / 5

Actionability

Concrete, specific guidance is present — an explicit graduated decision tree (五刑→五罚→五过), a fine-rate table, and crime counts — with minor gaps such as 官狱/内狱 being listed without definition, so it sits above the incomplete/3 anchor but not at fully executable/5.

4 / 5

Workflow Clarity

A clear sequenced process (initial hearing → graduated judgment → error handling → doubt/amnesty) is paired with a Validation section, and validation is present so the destructive-operation cap does not apply; it misses a 5 because there is no explicit 'if validation fails, fix and re-check' feedback loop.

4 / 5

Progressive Disclosure

The skill is self-contained with well-organized, clearly headed sections and no nested references; at slightly over 50 lines it is not the textbook simple-skill case for a 5, and the fine schedule / crime-category tables could arguably live in reference material, placing it at good-structure/4.

4 / 5

Total

16

/

20

Passed

Description

87%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 well-crafted: it pairs an explicit 'Use when' trigger with a concrete, specific statement of capabilities in a distinctive niche. Minor gains are possible by adding synonymous trigger phrasings and tightening coverage to fully comprehensive.

DimensionReasoningScore

Specificity

Lists several concrete actions ('adjudicating criminal cases', 'determining punishments', 'graduated verification from 五刑 to 五罚 to 五过', 'doubt-based amnesty protocols', 'fine schedules') with only minor coverage gaps, fitting the 'several specific actions' anchor rather than the fully comprehensive 5.

4 / 5

Completeness

Explicitly answers both 'what' (graduated verification, amnesty protocols, fine schedules) and 'when' ('Use when adjudicating criminal cases or determining punishments') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

'adjudicating criminal cases or determining punishments' are natural phrases a legal user would say, giving good keyword coverage; not a 5 because common synonyms or varied phrasings of those triggers are absent.

4 / 5

Distinctiveness Conflict Risk

The five-tier punishment niche with 五刑/五罚/五过 terminology is a clear, distinct domain with minimal overlap risk against other skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
baojie/shiji-kb
Reviewed

Table of Contents

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.