CtrlK
BlogDocsLog inGet started
Tessl Logo

political-self-protection-through-greed

Use when entrusted with dangerous levels of military or political power by a suspicious ruler. Based on Wang Jian's (王翦) strategy — repeatedly requesting personal land, houses, and gardens to signal you seek wealth, not power, thereby reducing the ruler's fear of betrayal.

71

Quality

86%

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

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.

A well-organized, concise instruction skill with a clear sequenced workflow and an explicit validation section. The main improvement space is making the validation checkpoints read as a validate→fix→retry feedback loop and adding a couple of ready-to-use request phrasings.

Suggestions

Reframe the Validation section as an explicit feedback loop: after each checkpoint, state the corrective action when the check fails (e.g., 'If the ruler punishes corruption, abandon this strategy and choose another').

Add 1–2 ready-to-use phrasings for the reward requests so the guidance is copy-paste-ready rather than summarized.

Tighten Step 5 by replacing the single example quote with a concise rule plus one short example, keeping the instruction actionable and brief.

DimensionReasoningScore

Conciseness

Lean and efficient at ~50 lines; it assumes Claude knows the historical context (one-line attribution only) and every section earns its place with no padding or concept re-explanation.

5 / 5

Actionability

Gives concrete, specific guidance ("Ask for land, houses, gardens for descendants", "Make requests publicly or in official channels", "Send multiple follow-up requests") with only minor gaps — e.g., a single illustrative quote rather than multiple ready-to-use phrasings.

4 / 5

Workflow Clarity

A clear 5-step sequence is followed by an explicit Validation section with three checkpoints (ruler-character accuracy, public visibility, subordinate loyalty), but the error-recovery feedback loop is implicit rather than a validate→fix→retry pattern.

4 / 5

Progressive Disclosure

A simple, single-purpose skill under 50 lines with no external references needed and clean sectioning (Overview, Steps, Key Principle, Expected Outcomes, Validation), satisfying the simple-skill exception for a top score.

5 / 5

Total

18

/

20

Passed

Description

87%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.

A specific, well-scoped description with explicit what/when guidance and concrete trigger phrases; it is among the better examples in the reference set. Minor gains are available by converting the narrative into a tighter action list and adding a couple more trigger synonyms.

DimensionReasoningScore

Specificity

Names several concrete actions — "repeatedly requesting personal land, houses, and gardens", "signal you seek wealth, not power", "reducing the ruler's fear of betrayal" — but presents them as a narrative rather than a comprehensive enumerated list, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both what (request land/houses/gardens to signal greed) and when ("Use when entrusted with dangerous levels of military or political power by a suspicious ruler") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural triggers like "entrusted with dangerous levels of military or political power" and "suspicious ruler" match phrasing a user would say, though a few common synonyms (e.g. "ambitious general", "paranoid king") are absent.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — Wang Jian's greed-signaling strategy under a suspicious ruler — with distinct triggers and minimal overlap risk against any other skill.

5 / 5

Total

18

/

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.