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

63%

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

63%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 content is well-structured for a simple instruction-only skill with a clear sequence and a real verification section, but it carries redundancy between Benefits and Expected Outcomes and blends actionable steps with attitude statements. Merging the redundant sections and converting attitudes to concrete actions would improve it.

Suggestions

Merge the Benefits and Expected Outcomes sections, which repeat reputation/network/organization-strength points, to remove redundancy.

Rewrite steps 3-4 as concrete actions (e.g., 'Maintain ongoing contact with placed candidates' and 'Acknowledge their success publicly') instead of attitudes.

Interleave validation cues inside the steps rather than isolating them in a trailing Verification section to strengthen workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and does not pad with concepts Claude already knows, but the Benefits and Expected Outcomes sections overlap heavily (reputation, network, organization strength appear in both) and could be tightened into one, matching the 'mostly efficient but some unnecessary content' anchor.	3 / 5
Actionability	Steps 1-2 give concrete direction ('Look for those with skills, integrity, and reputation exceeding your own'; 'Put forward their names for appropriate positions'), but steps 3-4 ('Build a network of the capable', 'Accept that they may surpass you') read as attitudes/outcomes rather than executable actions, leaving guidance incomplete per the 'some concrete guidance but incomplete' anchor.	3 / 5
Workflow Clarity	A clear 4-step sequence is paired with a dedicated Verification section containing explicit checks (confirm capability exceeds yours, validate merit-based basis, confirm role fit), giving most checkpoints; it falls short of 5 only because validation is a separate after-the-fact block rather than interleaved feedback loops within the steps.	4 / 5
Progressive Disclosure	The skill is under 50 lines, single-purpose, needs no external references, and is organized into clearly headed sections (Overview, Core Principle, Steps, Benefits, Expected Outcomes, Verification), which satisfies the simple-skill exception for a top score with no bundle files present.	5 / 5
	Total	15 / 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 covers both what and when with a clear trigger clause and occupies a distinct niche, but its action list is narrow and trigger terms lean academic rather than natural user phrasing. Tightening with more concrete actions and plainer synonyms would lift it.

Suggestions

Add 1-2 more concrete actions beyond 'recommending' (e.g., how to assess or document a candidate's superiority) to improve specificity.

Replace academic phrasing like '贤於己者' with plain trigger terms users would actually say (e.g., 'recommending stronger colleagues for promotion').

Make the 'when' clause more concrete by listing explicit trigger situations (e.g., 'Use when asked to fill a role, endorse a colleague, or advise on hiring').

Dimension	Reasoning	Score
Specificity	Names the domain (reputation/org strength via personnel recommendations) and one concrete action ('recommending those more capable than yourself'), but coverage is not comprehensive — it is essentially a single action framed by its purpose, matching the '1-2 concrete actions' anchor rather than the 'several specific actions' level.	3 / 5
Completeness	It explicitly answers both what ('prioritizes recommending those more capable than yourself to create networks and earn trust') and when ('Use when building reputation and organizational strength through personnel recommendations'), but the 'when' is somewhat abstract rather than concrete user trigger phrases, so it sits below the level-5 anchor.	4 / 5
Trigger Term Quality	Phrases like 'building reputation', 'organizational strength', and 'personnel recommendations' are domain-relevant, but the academic framing ('贤於己者') and lack of common synonyms mean natural user-facing trigger variations are missing, fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The niche of recommending more-capable people for reputation-building is fairly distinct with minimal overlap risk against typical skills, but the broad soft-skill framing keeps it just short of the 'clear niche with minimal conflict risk' level-5 anchor.	4 / 5
	Total	14 / 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_206/SKILL.md
Commit: 6b836e3

Reviewed: 2 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.