CtrlK
BlogDocsLog inGet started
Tessl Logo

military-deception-feigned-weakness

Use when facing a superior mobile enemy force, especially nomadic cavalry like the Xiongnu. Builds long-term deception through feigned cowardice, resource stockpiling, and a devastating ambush when the enemy grows overconfident.

68

Quality

83%

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

78%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 compact, well-structured instruction-only skill with a clear sequenced workflow and verification checkpoints. Adding failure-recovery guidance for failed verification checks would round out the workflow.

Suggestions

Add feedback-loop guidance for the Verification section: specify what to do if enemy overconfidence is not yet evident or elite forces are not yet positioned before baiting.

Trim the opening sentence which restates the description verbatim, letting the body dive straight into the steps.

Optional: add brief operational specifics to the trap step (e.g., coordination signals or timing) to raise actionability.

DimensionReasoningScore

Conciseness

Largely lean and efficient with no padding of concepts Claude already knows, though the opening sentence restates the description and could be trimmed.

4 / 5

Actionability

Provides concrete, ordered directives with sub-actions ("Stockpile supplies, train troops, strengthen fortifications"; "Select elite forces and position them for ambush"), with minor operational-detail gaps typical of strategic guidance.

4 / 5

Workflow Clarity

A clear 7-step sequence is paired with an explicit Verification section (confirm stockpiling, validate enemy overconfidence, ensure ambush positioned before bait), but it lacks error-recovery feedback loops for failed checks.

4 / 5

Progressive Disclosure

Under 50 lines with no need for external references and well-organized sections (Steps, Key Principle, Historical Example, Expected Outcomes, Verification), satisfying the simple-skill exception.

5 / 5

Total

17

/

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 strong, specific description with an explicit 'Use when' clause and concrete actions in third-person voice. Minor synonym coverage gaps keep trigger-term quality and specificity just below the top anchor.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ("feigned cowardice, resource stockpiling, and a devastating ambush"), but does not reach comprehensive coverage of the full deception playbook.

4 / 5

Completeness

Explicitly answers both what ("Builds long-term deception through feigned cowardice, resource stockpiling, and a devastating ambush") and when ("Use when facing a superior mobile enemy force...") with concrete triggers.

5 / 5

Trigger Term Quality

Good natural trigger coverage ("superior mobile enemy force", "nomadic cavalry like the Xiongnu") a user might say, though a few synonymous phrasings are absent.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (feigned-weakness deception against superior nomadic cavalry) with distinct triggers and minimal overlap risk with other skills.

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.