CtrlK
BlogDocsLog inGet started
Tessl Logo

military-reward-evaluation-process

Use when evaluating military achievements for reward conferral. Systematically compiles kill counts (斩首), captures (捕虏), and territory gained to determine appropriate titles (侯), fief increases, and punishments for failures.

75

Quality

92%

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

85%

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

The body is concise and well-structured with a clear multi-step workflow and explicit verification, but it stops short of giving the quantitative decision rules that would make the reward-determination fully actionable.

Suggestions

Add concrete thresholds mapping achievement levels to specific rewards (e.g., a table of kill-count ranges → fief increases or specific titles), so 'Determine Appropriate Rewards' is directly executable rather than descriptive.

Inline the verification steps into the workflow as checkpoints (e.g., 'After categorizing, confirm counts are verified before issuing the decree') with a feedback loop for when a check fails.

For failure cases, specify the commutation payment amounts or conditions so the 'Handle Failures' step yields an exact outcome instead of an option.

DimensionReasoningScore

Conciseness

Lean list-based structure with no concept explanations Claude already knows; every section (Overview, Steps, Expected Outcome, Verification) earns its place.

3 / 3

Actionability

Categories, tiers, and failure handling are concrete ('Death sentence, commutable by payment'), but no quantitative decision rules map achievement levels to specific rewards, leaving key actionable detail missing.

2 / 3

Workflow Clarity

A clear 1–6 sequence is paired with a dedicated Verification section containing three explicit checks (verified counts, consistent tier application, adjudicated failure cases), providing validation checkpoints despite the destructive punishment context.

3 / 3

Progressive Disclosure

Under 50 lines with no external references needed; content is well-organized into clearly labeled sections, satisfying the simple-skill exception for progressive disclosure.

3 / 3

Total

11

/

12

Passed

Description

100%

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 distinctive: it gives an explicit trigger plus a clear enumeration of what the skill does, with natural domain keywords. It does not over-claim or pad with buzzwords.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'compiles kill counts (斩首), captures (捕虏), and territory gained to determine appropriate titles (侯), fief increases, and punishments' — matching the anchor for listing several specific concrete actions.

3 / 3

Completeness

An explicit 'Use when evaluating military achievements for reward conferral' trigger answers 'when', and the rest of the sentence states 'what' (compiles achievements to determine titles, fiefs, punishments), satisfying both halves.

3 / 3

Trigger Term Quality

Covers natural domain terms a user would say — 'military achievements', 'reward', 'kill counts', 'territory gained', 'titles', 'fief increases', 'punishments' — with good breadth rather than jargon-only phrasing.

3 / 3

Distinctiveness Conflict Risk

A highly specific historical-administrative niche with distinctive terms (侯, 斩首, 捕虏) makes it unlikely to trigger for unrelated skills.

3 / 3

Total

12

/

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.