CtrlK
BlogDocsLog inGet started
Tessl Logo

virtue-reward-evaluation-framework

Use when analyzing whether virtue correlates with worldly success or questioning cosmic justice (天道). Compares virtuous sufferers (伯夷, 颜回) against prosperous villains (盗跖) using Sima Qian's method to assess 天道无亲常与善人 and inform ethical decision-making.

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_132/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 is well-structured with a clear sequenced workflow and an explicit validation checklist, and progressive disclosure is appropriate for a short single-purpose skill. Its weakness is actionability and minor conciseness redundancy: the analytical method lacks guidance on how to weigh or conclude, and the Overview/Expected Outcomes sections partially restate other parts.

Suggestions

Tighten by removing or merging the "Expected Outcomes" section, since it restates the conclusions already in step 4 and the description.

Strengthen actionability by specifying how to weigh cases (e.g. minimum number of contrasting pairs, how to handle ambiguous or mixed outcomes) so the comparison step is executable rather than just "Analyze whether".

DimensionReasoningScore

Conciseness

The body is mostly efficient at ~37 lines with specific evidence anchors (积仁絜行, 余甚惑焉), but the Overview and "Expected Outcomes" sections restate the description and step-4 conclusions, so it could be tightened — matching level 2 rather than the fully lean level 3.

2 / 3

Actionability

Steps give concrete examples (named figures, "starvation, early death vs. long life, wealth"), but the comparative method is incomplete — there is no guidance on sample size, how to weigh cases, or how to actually perform the assessment beyond "Analyze whether", fitting the level-2 anchor of concrete-but-incomplete.

2 / 3

Workflow Clarity

Four steps are clearly sequenced and followed by a Validation section with three explicit checkpoints (verify both sample types, confirm specific evidence, check uncertainty acknowledgment), matching the level-3 anchor of a clear sequence with a verification checklist.

3 / 3

Progressive Disclosure

At 37 lines with a single purpose and no external references needed, the well-organized sections (Overview, Steps, Expected Outcomes, Validation) satisfy the rubric's note that short single-purpose skills can score 3 without bundle files.

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 specific, complete, and highly distinctive, with explicit "Use when" triggers tied to a clear philosophical niche. Its main weakness is trigger-term coverage, which stays academic and misses the most natural ways a user might phrase the question.

Suggestions

Add common user phrasings to the trigger clause, e.g. "Use when a user asks why good people suffer, why bad people prosper, or whether virtue pays."

Consider including the plain-English gloss "Is virtue rewarded?" alongside the 天道 framing to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

It lists multiple concrete actions — "Compares virtuous sufferers (伯夷, 颜回) against prosperous villains (盗跖)", "using Sima Qian's method to assess 天道无亲常与善人" — rather than vague language, matching the level-3 anchor.

3 / 3

Completeness

It explicitly answers both what ("Compares virtuous sufferers ... using Sima Qian's method") and when ("Use when analyzing whether virtue correlates with worldly success or questioning cosmic justice"), matching the level-3 anchor.

3 / 3

Trigger Term Quality

"analyzing whether virtue correlates with worldly success" and "questioning cosmic justice (天道)" are relevant keywords, but common natural phrasings a user would say (e.g. "why do good people suffer", "do bad people prosper") are missing, so it stops at level 2.

2 / 3

Distinctiveness Conflict Risk

The niche is highly specific — Sima Qian's comparative virtue-reward analysis with named historical figures — making it unlikely to trigger for the wrong skill, matching the level-3 anchor.

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.