CtrlK
BlogDocsLog inGet started
Tessl Logo

psychological-warfare-siege-defense

Use when defending a besieged city with limited forces against a superior enemy. Combines divine legitimacy, psychological manipulation, feigned weakness, and surprise attack (e.g., Tian Dan's fire cattle) to shatter enemy morale.

70

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

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.

A well-structured instruction skill: clearly sequenced phases with concrete examples and a genuine verification/checkpoint section gating the risky final assault. The only ding is minor token redundancy in the intro and the ornamental quote.

Suggestions

Drop the opening restatement line since the description already covers it, or replace it with a one-line tactical summary that adds new information.

Trim or contextualize the 'Key Principle' quote so it reads as guidance rather than ornament, or fold its 'lull then strike' idea into Phase 3/4 where it is operationally relevant.

DimensionReasoningScore

Conciseness

The body is lean and avoids explaining known concepts, but the opening line restates the description and the 'Key Principle' quote is partly ornamental — mostly efficient but could be tightened, matching the score-2 anchor rather than the every-token-earns-its-place score 3.

2 / 3

Actionability

Concrete, example-backed instructions — 'Send old people and women to man the walls', 'fire cattle with swords on horns', the nose-cutting rumor — provide specific guidance; per the instruction-skill note, absence of code is not penalized when guidance is this concrete.

3 / 3

Workflow Clarity

Phase 1–4 is clearly sequenced and the dedicated Verification section gates the final assault ('before launching', 'before execution', 'before committing'), matching the score-3 anchor of explicit validation steps with checkpoints.

3 / 3

Progressive Disclosure

No bundle files exist and the skill is under 50 lines with a single purpose; per the simple-skills note, well-organized sections (phases, Key Principle, Expected Outcomes, Verification) are sufficient for a score of 3.

3 / 3

Total

11

/

12

Passed

Description

85%

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 description: it pairs an explicit 'Use when' trigger with a concrete list of techniques in a highly distinctive niche. The only weakness is limited trigger-term variation, which keeps trigger quality at 2.

DimensionReasoningScore

Specificity

Lists multiple concrete techniques — 'divine legitimacy, psychological manipulation, feigned weakness, and surprise attack (e.g., Tian Dan's fire cattle)' — matching the multi-action anchor rather than the single-domain score-2 example.

3 / 3

Completeness

Explicit 'Use when' clause answers when, and 'Combines ... to shatter enemy morale' answers what, mirroring the score-3 example that pairs capability list with an explicit trigger.

3 / 3

Trigger Term Quality

Relevant natural phrases ('defending a besieged city', 'limited forces', 'superior enemy') are present, but coverage is a single scenario without common variations or synonyms, matching the score-2 anchor rather than the broad synonym coverage of score 3.

2 / 3

Distinctiveness Conflict Risk

The niche is highly specific ('besieged city', 'Tian Dan's fire cattle') and unlikely to overlap with other skills, matching the clear-niche score-3 anchor rather than the generic score-2 example.

3 / 3

Total

11

/

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.