CtrlK
BlogDocsLog inGet started
Tessl Logo

five-criteria-official-evaluation

Use when evaluating candidates for government positions or assessing character suitability. Applies Li Ke's five-lens framework: 居视其所亲, 富视其所与, 达视其所举, 穷视其所不为, 贫视其所不取 to reveal values, generosity, judgment, principles, and integrity.

65

Quality

77%

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_119/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%

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

The content cleanly presents the five-lens framework with a useful verification checklist and good organization, but the per-criterion guidance is more descriptive than actionable and somewhat redundant. Tightening the bullets and adding a concrete observation-gathering method would raise the weaker dimensions.

Suggestions

Replace the restating bullet pairs with a single concrete observation prompt per criterion to remove redundancy.

Add a brief, concrete method for gathering and weighting evidence across the five life conditions (e.g., what sources to consult, how to reconcile conflicting signals).

Soften the 'without needing additional investigation' over-claim in Expected Outcome, which is stronger than the framework guarantees.

DimensionReasoningScore

Conciseness

The body is mostly lean, but each criterion restates the Chinese term, an English gloss, and two bullets that often restate the same idea (e.g., 'Their choice of companions reveals their values' / 'Look at their close friends and associates'), so it could be tightened.

2 / 3

Actionability

Guidance is framed as abstract observation prompts ('Do they share generously or hoard?', 'What lines will they not cross?') rather than a concrete method for gathering or weighing evidence, leaving the how incomplete.

2 / 3

Workflow Clarity

The Verification section supplies a 3-step validation checklist (confirm all five applied, validate cross-condition observations, check consistent patterns before deciding) that acts as explicit checkpoints before the appointment decision.

3 / 3

Progressive Disclosure

A sub-50-line single-purpose skill with no external references needed, organized into clear sections (Overview, Five Criteria, Expected Outcome, Verification) — well-organized sections suffice for a top score.

3 / 3

Total

10

/

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.

The description is well-constructed with an explicit Use-when trigger, a clear niche, and concrete enumeration of the five lenses and their revealed qualities. Its main weakness is trigger-term coverage, which is somewhat narrow for the domain.

Suggestions

Broaden trigger terms to include natural user phrasings like 'vetting officials', 'hiring for government roles', or 'appointment decisions' alongside 'evaluating candidates'.

Consider noting the outcome explicitly (e.g., 'to decide suitability for office') so the purpose is unambiguous at a glance.

DimensionReasoningScore

Specificity

Lists multiple concrete elements — the five named lenses (居视其所亲, 富视其所与, 达视其所举, 穷视其所不为, 贫视其所不取) and five revealed qualities (values, generosity, judgment, principles, integrity) — rather than vague abstractions.

3 / 3

Completeness

Explicitly answers both what ('Applies Li Ke's five-lens framework... to reveal...') and when via an explicit 'Use when evaluating candidates for government positions or assessing character suitability' trigger clause.

3 / 3

Trigger Term Quality

Relevant trigger keywords exist ('evaluating candidates', 'government positions', 'character suitability'), but coverage is narrow and misses common variations like hiring, vetting, or appointment decisions a user might naturally say.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear, narrow niche (Li Ke's specific five-lens official-evaluation framework) with distinct triggers unlikely to overlap with other 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.