minister-selection-meritocracy

Use when selecting officials based on capability rather than favoritism or nepotism. Follows Qi Xi's impartial model: recommending personal enemies for their competence and relatives for their merit, with transparent evaluation criteria covering skills, character, and past performance.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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 content is token-efficient, well-organized, and provides a clear sequenced workflow with a verification checklist. Its chief weakness is actionability: the evaluation steps describe what to consider without defining concrete, reusable criteria for assessing candidates.

Suggestions

Make the 'Evaluate Candidates' step actionable by defining concrete evaluation criteria or a simple scoring rubric (e.g. a 1–5 scale for skills, track record, and character) instead of abstract directives like 'assess character and judgment'.

Add a short worked example showing how a candidate is scored against the documented criteria, so the merit-ranking step in 'Make Selection' has a copy-paste-ready template.

Specify what 'Test specific competencies' means in practice (e.g. sample task types or interview prompts) so the guidance is executable rather than descriptive.

Dimension	Reasoning	Score
Conciseness	The body is lean and bullet-pointed with no over-explanation of concepts Claude already knows; the intro and Overview are slightly redundant with the description but every section is brief and earns its place, matching the lean/efficient anchor; not a 2 because there is no padded explanatory prose.	3 / 3
Actionability	A concrete 5-step Selection Process and a named example (Jie Hu / Qi Wu) give real guidance, but evaluation steps like 'Assess character and judgment' and 'Test specific competencies' stay abstract with no defined criteria or scoring rubric, fitting the incomplete-guidance anchor at 2 rather than copy-paste-ready at 3.	2 / 3
Workflow Clarity	The Selection Process is a clearly numbered 1–5 sequence and a dedicated Verification section provides an explicit 3-point checklist, giving clear sequencing with validation; not a 2 because checkpoints are explicit rather than implicit, and this non-destructive task is not capped by the batch/destructive rule.	3 / 3
Progressive Disclosure	The skill is under ~50 lines with no need for external references and is organized into well-labeled sections (Overview, Recommendation Principles, Selection Process, Example, Expected Outcome, Verification), satisfying the simple-skill allowance for a 3; not a 2 because nothing that should be split out is inlined.	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 well-structured with an explicit trigger and concrete, distinctive capability framing. Its main weakness is trigger-term coverage, which leans on proper-noun jargon ('Qi Xi') rather than the everyday vocabulary users would naturally invoke.

Suggestions

Replace or supplement the proper-noun phrase 'Qi Xi's impartial model' with everyday trigger terms a user would actually say, such as 'hiring', 'appointments', 'promotions', or 'merit-based selection'.

Broaden trigger coverage to include synonyms users might use (e.g. 'staffing decisions', 'candidate evaluation', 'avoiding nepotism') so the skill surfaces for more natural phrasings.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'recommending personal enemies for their competence and relatives for their merit' plus 'transparent evaluation criteria covering skills, character, and past performance', matching the multiple-specific-actions anchor rather than the single-domain anchor at 2.	3 / 3
Completeness	Opens with an explicit 'Use when selecting officials...' trigger (the when) and follows with the Qi Xi model actions and evaluation criteria (the what), clearly answering both as required for a 3; not a 2 because the when is explicit rather than implied.	3 / 3
Trigger Term Quality	Natural terms like 'selecting officials', 'favoritism', and 'nepotism' are present, but 'Qi Xi's impartial model' is jargon a user would not naturally say and common variations (e.g. 'hiring', 'appointments', 'promotions') are missing, so it does not reach the full-coverage anchor at 3.	2 / 3
Distinctiveness Conflict Risk	The minister-selection meritocracy niche with named Qi Xi triggers is highly specific and unlikely to overlap with other skills, matching the clear-niche anchor; not a 2 because it does not read as a generic 'works with documents'-style description.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

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
Path: kg/ontology/ontology-v1/skus/procedural/skill_098/SKILL.md
Commit: 79c272f

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.