official-performance-evaluation-cycle

Use when evaluating official performance or deciding promotions and demotions. Implements a three-year cycle assessment over nine years, using documented achievements to determine advancement (陟) or removal (绌).

Quality

59%

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

Fix and improve this skill with Tessl

tessl review fix ./kg/ontology/ontology-v1/skus/procedural/skill_002/SKILL.md

Quality

Content

56%Weight 40%Scale 1-5

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

The skill body is concise, well-structured, and lays out a clear three-cycle workflow with a validation section, fitting a simple single-purpose skill. Its core weakness is actionability: the guidance stays abstract with no concrete artifacts, templates, or measurable criteria for executing or recording evaluations.

Suggestions

Add concrete, executable artifacts for each step, e.g. a simple evaluation-record template or rubric (official, duties, standards, Year-3 result, Year-6 result, Year-9 outcome) so the steps can be carried out rather than just described.

Tighten the Validation section into explicit, ordered checkpoints (e.g. 'Before the first cycle: confirm documented duties and measurable standards for every official') so validation reads as a gate, not a checklist summary.

Optionally fold the Overview, Expected Outcomes, and Decision Points sections to reduce overlap with the Steps, since several points repeat the same sequence.

Dimension	Reasoning	Score
Conciseness	The body is reasonably lean with short, well-sectioned bullet lists and no padded explanations of concepts Claude already knows; only a few overview/outcome lines could be trimmed further.	4 / 5
Actionability	The steps describe what to do at a high level ('Review achievements against assigned duties', 'Document successes and failures') but provide no concrete, executable guidance, specific commands, or examples for carrying out an evaluation or recording a decision.	2 / 5
Workflow Clarity	The three-cycle sequence (Year 3, 6, 9) is clearly laid out with a final promotion/demotion decision point and a dedicated Validation section that functions as checkpoints before decisions; minor gaps are that validation is described abstractly rather than as explicit per-step gates.	4 / 5
Progressive Disclosure	The content is short (well under 50 lines) with clean section headers and no bundle files needed; structure is appropriate for a simple skill, though the single-page layout leaves no room for one-level-deep references (which it does not require).	4 / 5
	Total	14 / 20 Passed

Description

62%Weight 40%Scale 1-5

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 clear and explicit, pairing a concrete 'what' with a 'Use when' trigger and a distinct niche around cyclical official performance review. Its main weakness is trigger-term coverage: the natural opening phrase is good but the rest leans on domain jargon rather than user-facing synonyms.

Suggestions

Add more natural trigger phrases and synonyms users would actually say, e.g. 'Use when reviewing official performance, deciding promotions or demotions, or running periodic merit evaluations'.

Consider dropping or downplaying the untranslated CJK outcome terms (陟/绌) in the description, or pairing them with plain-language equivalents, so the trigger reads naturally to a broader audience.

Dimension	Reasoning	Score
Specificity	Names the domain (official performance evaluation) and several concrete actions (evaluating performance, deciding promotions and demotions, three-year cycle assessment, using documented achievements to determine advancement or removal), with only minor gaps in coverage.	4 / 5
Completeness	It clearly states what the skill does (three-year cycle assessment over nine years using documented achievements) and gives an explicit 'Use when' clause naming the triggering situations; the 'when' is concrete but could enumerate a few more natural trigger variations.	4 / 5
Trigger Term Quality	It opens with a natural trigger phrase ('Use when evaluating official performance or deciding promotions and demotions'), but the remaining terms are domain-specific jargon ('three-year cycle assessment', '陟/绌') that a user would be less likely to voice, so common variations and synonyms are missing.	3 / 5
Distinctiveness Conflict Risk	The niche is fairly specific (cyclical official performance evaluation with promotion/demotion outcomes) and unlikely to collide with most other skills, with only minor overlap risk against generic evaluation skills.	4 / 5
	Total	15 / 20 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_002/SKILL.md
Commit: 6b836e3

Reviewed: 7 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.