CtrlK
BlogDocsLog inGet started
Tessl Logo

deceptive-standoff-tactic

Use when a small force encounters a much larger enemy and retreat means destruction. Employs psychological deception by advancing, dismounting, and displaying calm to convince the enemy of a hidden ambush, forcing withdrawal.

66

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 well-organized, actionable instruction skill with a clear sequenced workflow and validation section. The main improvements are minor: trim Overview redundancy and weave verification into the step flow as explicit feedback loops.

Suggestions

Interleave verification checkpoints into the step sequence (e.g., validate discipline before dismounting) rather than relegating them to a terminal section.

Tighten the Overview to avoid restating the frontmatter description verbatim.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence, but the Overview partially restates the frontmatter description, a minor instance of over-explanation that could be trimmed.

4 / 5

Actionability

Provides concrete, specific instructions ('Halt approximately 2 li (about 1 km)', 'dismount and remove saddles', 'release horses to graze') with only minor gaps in variation examples.

4 / 5

Workflow Clarity

Seven steps are clearly sequenced with a Verification section providing checkpoints, but the validation is terminal rather than interleaved as recover-and-retry feedback loops.

4 / 5

Progressive Disclosure

A single-purpose skill under 50 lines with no need for external references, organized into clear sections (Overview, Steps, Decision Points, Expected Outcomes, Verification).

5 / 5

Total

17

/

20

Passed

Description

80%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 that clearly states both the trigger scenario and the deception actions, with only minor gaps in trigger-term variation and step coverage. It is highly distinguishable from generic skills.

Suggestions

Add a synonym or natural variation of the trigger (e.g., 'outnumbered' or 'outgunned') to broaden keyword coverage.

Mention holding the bluff through nightfall in the description to make the action set fully comprehensive.

DimensionReasoningScore

Specificity

Lists several concrete actions (advancing, dismounting, displaying calm, convincing of a hidden ambush, forcing withdrawal), with a minor gap in that the hold-to-nightfall element is omitted.

4 / 5

Completeness

Explicitly answers both 'when' ('Use when a small force encounters a much larger enemy and retreat means destruction') and 'what' (deception via advancing, dismounting, and displaying calm) with concrete trigger phrasing.

5 / 5

Trigger Term Quality

Contains scenario-relevant natural terms ('small force encounters a much larger enemy', 'retreat means destruction', 'psychological deception') but lacks common synonyms or variations a user might phrase differently.

3 / 5

Distinctiveness Conflict Risk

Occupies a clear, narrow niche (psychological standoff when outnumbered) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

17

/

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.

Validation — 16 / 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.