CtrlK
BlogDocsLog inGet started
Tessl Logo

commandery-county-administration

Use when replacing feudal states with centralized commandery-county (郡县) administration. Establishes 36 commanderies with three-tier governance (守/尉/监), merit-based appointments, and centralized treasury stipends per Li Si's rationale.

70

Quality

85%

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 a well-structured, actionable governance procedure with clear sequencing and an explicit validation checklist, appropriate for a simple single-purpose skill with no external references. Its one weakness is mild verbosity in the Rationale and Expected Outcomes sections, which explain context Claude largely already knows.

Suggestions

Tighten the 'Rationale' section to Li Si's specific decision-relevant point rather than restating general reasons feudalism fails (blood ties weakening, lords as rivals), which Claude already knows.

Consider merging 'Expected Outcomes' into the existing 'Validation' section, since the outcomes largely restate what the validation checks already verify, to remove redundancy.

If operational specifics exist (e.g., reporting cadence, stipend-setting mechanism, merit-assessment criteria), add them to the relevant steps to push actionability from concrete to fully specified.

DimensionReasoningScore

Conciseness

The body is mostly lean, but the 'Rationale' (blood ties weaken, lords become rivals) and 'Expected Outcomes' sections include explanation Claude largely already knows and that partly restates the steps, fitting the score-2 'mostly efficient but includes some unnecessary explanation or could be tightened' anchor rather than the fully-lean score-3.

2 / 3

Actionability

As an instruction-only skill the steps give concrete, specific guidance — named structures ('Create 36 commanderies (郡)'), three named roles with Chinese terms (守/尉/监), and the treasury-stipend mechanism — which per the scoring note is actionable without code, matching the score-3 'concrete, specific guidance' bar rather than score-2's 'missing key details'.

3 / 3

Workflow Clarity

Six steps are clearly sequenced and a dedicated 'Validation' section provides explicit verification checks (all three positions filled, merit-based stipend appointments, operational reporting across 36 commanderies), satisfying the score-3 'clear sequence with explicit validation steps / checklist' anchor; the batch/destructive nature is covered by validation, so no score-2 cap applies.

3 / 3

Progressive Disclosure

The skill is under 50 lines, single-purpose, and has no bundle files; content is organized into clear sections (Overview, Steps, Rationale, Expected Outcomes, Validation), so per the simple-skills scoring note progressive_disclosure scores 3 on well-organized sections alone.

3 / 3

Total

11

/

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, distinctive, and complete with an explicit 'Use when...' trigger and concrete actions. Its main weakness is trigger-term breadth, covering the core domain terms but not the fuller range of natural phrasings a user might say.

Suggestions

Broaden trigger coverage by adding natural variations such as 'junxian system', 'centralized governance', or 'abolish feudalism / replace fiefdoms' alongside 'feudal states' and 'commandery-county'.

Consider mentioning the most likely user verb ('set up', 'establish', 'implement') explicitly in the trigger clause so the 'Use when...' phrasing matches how a user would phrase the request.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Establishes 36 commanderies with three-tier governance (守/尉/监), merit-based appointments, and centralized treasury stipends' — matching the score-3 anchor of several specific concrete actions rather than the narrower score-2 'some actions'.

3 / 3

Completeness

Explicitly answers both 'what' ('Establishes 36 commanderies with three-tier governance...') and 'when' via an explicit 'Use when replacing feudal states...' trigger, satisfying the score-3 requirement rather than the score-2 'when only implied' anchor.

3 / 3

Trigger Term Quality

Includes relevant natural terms ('feudal states', 'commandery-county', '郡县') but offers fewer variations than the score-3 anchor's broad coverage; common phrasings like 'junxian system' or 'centralized governance' are absent, so it sits at 'some relevant keywords but missing common variations'.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear, narrow niche (Qin-style commandery-county administration with bilingual 守/尉/监 terms) whose triggers are unlikely to fire for unrelated skills, matching the score-3 'clear niche with distinct triggers' 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.