CtrlK
BlogDocsLog inGet started
Tessl Logo

deep-penetration-cavalry-raid

Use when planning rapid cavalry raids deep into enemy territory. Based on Huo Qubing's campaigns: select elite riders, travel light (约轻赍), live off enemy resources (取食於敌), strike symbolic targets like 狼居胥山, and return before enemy concentrates.

75

Quality

92%

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

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-structured, concise tactical procedure with a clear sequenced workflow and verification checkpoints. Its main weakness is actionability: as an instruction-only historical skill, some guidance is concrete but other items are aspirational rather than executable.

Suggestions

Tighten actionability by converting aspirational Success Factors like 'good fortune (天幸)' and 'demonstrate reach' into concrete, checkable actions or move them out of the actionable step list.

Add brief measurable thresholds to key steps (e.g., a target march distance or supply-resupply ratio) so 'travel light' and 'live off enemy resources' become verifiable rather than qualitative.

Make the Verification section explicitly map each checkpoint to a step, so the feedback loop ties validation back to the workflow stages.

DimensionReasoningScore

Conciseness

The body is lean bullet/step prose that assumes competence and never explains concepts Claude already knows; every section earns its place.

3 / 3

Actionability

Steps give specific tactical direction ('Limit baggage and supplies', 'Seize enemy food and supplies', 'Use captured horses') but several items are aspirational rather than executable ('good fortune (天幸)', 'demonstrate reach'), and as an instruction-only historical procedure it lacks truly concrete operations.

2 / 3

Workflow Clarity

Six clearly sequenced steps form an explicit advance→engage→sustain→achieve→return flow, and the Verification section provides validation checkpoints for the outcome.

3 / 3

Progressive Disclosure

A simple under-50-line skill with no external references, but well organized into Overview, Key Principles, Steps, Success Factors, Expected Outcome, and Verification sections — meeting the simple-skill bar.

3 / 3

Total

11

/

12

Passed

Description

100%

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 concise yet specific, pairing an explicit 'Use when' trigger with a list of concrete tactical actions and named historical anchors. It clearly answers both what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'select elite riders, travel light, live off enemy resources, strike symbolic targets like 狼居胥山, and return before enemy concentrates' — matching the top anchor.

3 / 3

Completeness

Explicit 'Use when planning...' trigger answers when, and the enumerated actions answer what, satisfying both halves at the top anchor.

3 / 3

Trigger Term Quality

Uses natural terms a user would say for this niche — 'rapid cavalry raids deep into enemy territory' and 'Huo Qubing's campaigns' — giving good coverage rather than technical jargon.

3 / 3

Distinctiveness Conflict Risk

The niche is sharply defined (Huo Qubing deep cavalry raids) with distinctive triggers, making conflict with other skills unlikely.

3 / 3

Total

12

/

12

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.