CtrlK
BlogDocsLog inGet started
Tessl Logo

recruit-talent-from-rival-states

Use when recruiting talented individuals from rival states through discreet negotiation. Based on Duke Mu's recruitment of Baili Xi, guides target identification, concealment of intentions, low-value exchange tactics, and capability assessment.

66

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./kg/ontology/ontology-v1/skus/procedural/skill_019/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 body is a lean, well-structured instruction-only procedure with a clear sequenced workflow, decision branches, and a validation checklist. The main gaps are a few generic step bullets and validation that sits at the end rather than as inline checkpoints with a retry loop.

Suggestions

Tighten the generic step bullets ('Locate capable individuals', 'Assess their true value') into more concrete tactics, e.g. specific signals of capability or sources to search.

Convert the final Validation section into inline checkpoints after the risky steps (Negotiate, Secure and Release) with an explicit 'if validation fails, return to step N' retry loop.

Add one short worked example beyond Baili Xi to show the tactic generalizes, keeping the body concise.

DimensionReasoningScore

Conciseness

The body is lean (under 50 lines), uses tight bullets, and never explains concepts Claude already knows; every section earns its place, matching the 'lean and efficient; assumes Claude's competence' anchor; the only mild redundancy is the Overview restating the description, which still adds the 'without alerting them to the person's true value' framing.

5 / 5

Actionability

Concrete tactical guidance with specific examples ('Use a low-value exchange (e.g., five ram skins for Baili Xi)', 'Frame the request as recovering a minor servant or fugitive') fits the 'mostly executable guidance; minor gaps' anchor; not 5 because some steps remain generic ('Locate capable individuals', 'Assess their true value') without specifics on how.

4 / 5

Workflow Clarity

A clear six-step numbered sequence is paired with a Validation section and Decision Points providing feedback branches, matching 'clear sequence with most checkpoints present; minor validation gaps'; not 5 because validation is a post-hoc checklist rather than inline checkpoints between steps, and there is no explicit fix-and-retry loop.

4 / 5

Progressive Disclosure

With no bundle files present and the skill under 50 lines, the well-organized sections (Overview, Steps, Decision Points, Expected Outcomes, Validation) satisfy the simple-skill exception allowing a 5 on progressive disclosure with just well-organized sections.

5 / 5

Total

18

/

20

Passed

Description

71%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 explicit, third-person, and clearly answers both what and when with concrete sub-actions in a distinctive niche. Its main weakness is trigger-term breadth — a single narrow trigger phrase with no synonyms or variations.

Suggestions

Add synonyms and common variations to the trigger phrase, e.g. 'Use when recruiting talent from rival or enemy states, poaching advisors or ministers from other courts, or acquiring capable officials through discreet/low-profile negotiation'.

Broaden the 'when' clause to cover the realistic range of triggering situations rather than a single scenario, so Claude matches it more reliably.

Consider naming the output artifact or end-state (e.g. 'results in a recruited and vetted official appointed to authority') to make the 'what' even more concrete.

DimensionReasoningScore

Specificity

Names the domain ('recruiting talented individuals from rival states through discreet negotiation') and lists several concrete sub-actions ('target identification, concealment of intentions, low-value exchange tactics, and capability assessment'), matching the 'lists several specific actions; minor gaps' anchor; not 5 because coverage is narrow to one historical pattern rather than comprehensive.

4 / 5

Completeness

Explicitly answers both what ('guides target identification, concealment of intentions, low-value exchange tactics, and capability assessment') and when ('Use when recruiting talented individuals from rival states...'), matching the 'has both what and when; when could be more explicit' anchor; not 5 because the when is a single narrow scenario rather than a set of concrete trigger phrases.

4 / 5

Trigger Term Quality

The 'Use when recruiting talented individuals from rival states through discreet negotiation' phrase is a natural trigger, but it offers only one framing with no synonyms or common variations, fitting 'some relevant keywords but missing common variations'; not 4 because keyword coverage is thin for the niche rather than broad.

3 / 5

Distinctiveness Conflict Risk

The niche ('recruiting talented individuals from rival states through discreet negotiation') is highly specific with distinct triggers and minimal overlap with other skills, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.

5 / 5

Total

16

/

20

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.