talent-recommendation-best-practice

Use when building reputation and organizational strength through personnel recommendations. Prioritizes recommending those more capable than yourself (贤於己者) to create networks of competent allies and earn trust from superiors.

Quality

72%

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_206/SKILL.md

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 body is well-structured with a clear step sequence and explicit verification, but the guidance stays abstract and the Benefits/Expected Outcomes sections overlap, leaving actionability and conciseness at the middle level.

Suggestions

Add concrete, specific guidance to each step (e.g., concrete evaluation criteria, where/how to surface recommendations) to move from abstract philosophy to actionable instruction.

Merge the redundant 'Benefits' and 'Expected Outcomes' sections into a single concise list to remove overlapping padding.

Dimension	Reasoning	Score
Conciseness	The body is short and does not explain known concepts, but the 'Benefits' and 'Expected Outcomes' sections largely restate one another (reputation, network, loyalty) and the 'Core Principle' repeats the description, so it could be tightened per the verbosity penalty at anchor 2.	2 / 3
Actionability	The four steps are named but remain abstract ('Look for those with skills, integrity, and reputation exceeding your own,' 'appropriate positions') without concrete criteria or examples, matching anchor 2 rather than fully actionable anchor 3.	2 / 3
Workflow Clarity	A clear four-step sequence is paired with a dedicated Verification section containing explicit checks ('Confirm each recommended individual demonstrably exceeds your own capabilities,' 'Validate... based on merit and integrity'), matching anchor 3's clear sequence with validation steps.	3 / 3
Progressive Disclosure	The skill is under 50 lines, requires no external references, and is organized into clear well-labeled sections, qualifying for anchor 3 under the simple-skills scoring note.	3 / 3
	Total	10 / 12 Passed

Description

75%

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 answers both what and when with an explicit 'Use when' clause and occupies a distinctive niche, but its language is conceptual rather than natural request phrasing and its actions are not a crisp enumerated list.

Suggestions

Rewrite the trigger clause using natural request phrasing a user would actually say (e.g., 'Use when asked how to recommend colleagues, build a professional network, or advise on personnel decisions') to raise trigger term quality.

Replace the conceptual action summary with concrete enumerated actions (e.g., 'Identify, evaluate, and recommend personnel') to increase specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ('personnel recommendations') and several actions ('recommending those more capable than yourself,' 'create networks of competent allies,' 'earn trust from superiors') but is not a tight enumerated list of discrete concrete actions, matching anchor 2 rather than anchor 3.	2 / 3
Completeness	An explicit 'Use when...' clause provides the trigger ('Use when building reputation and organizational strength through personnel recommendations') while the body states what the skill does, clearly answering both what and when per anchor 3.	3 / 3
Trigger Term Quality	Contains some relevant domain keywords ('personnel recommendations,' 'recommending') but the framing ('building reputation and organizational strength') is abstract conceptual phrasing rather than natural request language a user would say, matching anchor 2.	2 / 3
Distinctiveness Conflict Risk	The niche (recommending more-capable personnel to build networks and trust) is distinctive and unlikely to trigger for unrelated skills, matching anchor 3 rather than the overlapping anchor 2.	3 / 3
	Total	10 / 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_206/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.