CtrlK
BlogDocsLog inGet started
Tessl Logo

judicial-investigation-procedure

Use when conducting legal investigations following classical Chinese judicial principles. Covers official accountability (失刑则刑), evidence gathering, case processing for treason/property/misconduct, and proportional punishment without sparing the powerful (不避贵戚).

61

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./kg/ontology/ontology-v1/skus/procedural/skill_240/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, concise reference for a single-domain investigative procedure, but the body stays at the level of abstract maxims and high-level steps rather than concrete, actionable decision criteria. Tightening the fluff sections and adding specifics would lift the weaker dimensions.

Suggestions

Replace abstract maxims in 'Ethical Standards' and the 'Expected Outcomes' section with concrete decision rules or drop them, so every line drives an action.

Add specifics to the case-processing steps — e.g., what counts as 'coerced vs. willing', how to weigh 'need vs. greed', or explicit criteria for proportional punishment — so the guidance is actionable rather than directional.

Interleave verification checkpoints within each case-processing workflow (e.g., 'after gathering evidence, confirm testimonies cross-reference before proceeding') instead of a single end-of-document checklist.

DimensionReasoningScore

Conciseness

Mostly efficient structured bullets with translations, but sections like 'Expected Outcomes' and 'Ethical Standards' carry abstract fluff ('Death before dishonor of the law') that Claude could infer and that doesn't drive action.

2 / 3

Actionability

Procedural guidance is concrete in shape ('Investigate all connections', 'Trace to the root') but stays high-level with no specific examples, criteria, or decision rules, leaving key details unspecified.

2 / 3

Workflow Clarity

Numbered sequences exist for each case type and a Verification checklist is present, but checkpoints are tacked on at the end rather than interleaved, with no validate-fix-retry feedback loop.

2 / 3

Progressive Disclosure

Under 50 lines, self-contained, and organized into clear sections (Overview, Investigation Principles, Case Processing, Punishment, Verification) with no need for external references.

3 / 3

Total

9

/

12

Passed

Description

85%

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 description: explicit trigger, concrete capability list, and a distinct niche. The main weakness is reliance on untranslated classical-Chinese phrases as trigger terms, which limits natural keyword coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities ('conducting legal investigations', 'evidence gathering', 'case processing for treason/property/misconduct', 'proportional punishment'), matching the multi-action anchor.

3 / 3

Completeness

Explicitly answers both 'what' ('Covers official accountability... case processing... proportional punishment') and 'when' with a clear 'Use when conducting legal investigations' trigger.

3 / 3

Trigger Term Quality

Includes relevant terms ('legal investigations', 'evidence gathering') but leans heavily on untranslated classical-Chinese jargon ('失刑则刑', '不避贵戚') that users would not naturally say verbatim, missing common variations.

2 / 3

Distinctiveness Conflict Risk

Targets a highly specific niche ('classical Chinese judicial principles') with distinct triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

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.