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).

60

Quality

75%

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

71%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 well-organized, concise, and ends with explicit verification checkpoints, but its procedural guidance stays at a high level without the concrete detail that would make each step directly executable. Tightening actionability would lift the strongest remaining weakness.

Suggestions

Add concrete sub-steps or criteria to the case-processing flows, e.g. for property crimes specify how to value goods and what thresholds distinguish need vs. greed.

Insert an in-flow validation checkpoint within each case type (e.g. 'Before assigning punishment, confirm evidence is corroborated by ≥2 witnesses') rather than only a final Verification section.

Trim 'Expected Outcomes' (public trust, deterrence, rehabilitation) since it is aspirational and does not guide execution.

DimensionReasoningScore

Conciseness

The body is mostly lean terse bullets with translated classical quotes and little concept padding; only 'Expected Outcomes' and parts of 'Ethical Standards' restate principles already covered elsewhere and could be trimmed.

4 / 5

Actionability

Procedural steps are present ('Examine all witnesses', 'Determine value of stolen goods', 'Assess if violence was used') but remain high-level and lack the specific executable detail needed to carry them out, leaving key details implicit.

3 / 5

Workflow Clarity

Each case type has a clear numbered sequence and a dedicated Verification section supplies checkpoints ('Confirm…', 'Validate…', 'Check…'); minor gaps are the absence of in-flow validation feedback loops within each sub-process.

4 / 5

Progressive Disclosure

No bundle files exist or are needed; the skill is simple and single-purpose with well-organized section headers (Overview, Investigation Principles, Case Processing, Punishment, Verification), satisfying the simple-skill exception.

5 / 5

Total

16

/

20

Passed

Description

66%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 explicitly answers both what and when with a clear trigger clause and a distinctive niche, but its listed actions are category-level rather than granular and it lacks keyword synonyms. It is solid but could be sharpened with more concrete operations and natural variation terms.

Suggestions

Replace category-level phrases ('evidence gathering', 'case processing') with more concrete operations, e.g. 'examining witnesses, cross-referencing testimonies, tracing accomplices, and assigning proportional punishment'.

Add common user-facing synonyms to broaden trigger matching, e.g. 'legal investigation', 'judicial inquiry', 'case review'.

Make the 'when' clause more scenario-specific, e.g. 'Use when reviewing a legal case, assigning accountability, or determining proportional punishment under classical Chinese law'.

DimensionReasoningScore

Specificity

Names the domain and lists several coverage areas ('evidence gathering', 'case processing for treason/property/misconduct', 'proportional punishment', 'official accountability'), but these are category-level actions rather than granular concrete operations, so coverage is not comprehensive.

3 / 5

Completeness

It has both an explicit 'Use when…' clause (when) and a clear 'Covers…' enumeration (what); the 'when' is explicit but could name more concrete trigger scenarios to reach a 5.

4 / 5

Trigger Term Quality

'Use when conducting legal investigations following classical Chinese judicial principles' provides a natural trigger phrase plus domain keywords, but the niche domain leaves it missing common variations and synonyms users might actually say.

3 / 5

Distinctiveness Conflict Risk

'Classical Chinese judicial principles' with specialized phrases (失刑则刑, 不避贵戚) defines a clear, narrow niche with minimal overlap risk against other skills.

5 / 5

Total

15

/

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.

Validation — 16 / 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.