CtrlK
BlogDocsLog inGet started
Tessl Logo

escape-from-captivity

Use when captured by enemy forces and seeking to escape. Involves feigning death or injury, observing guards and resources, then seizing a sudden opportunity to commandeer a horse and flee to friendly territory.

66

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./kg/ontology/ontology-v1/skus/procedural/skill_210/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

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 skill with concrete actionable steps and verification checkpoints. The main gaps are minor redundant summary sections and the absence of error-recovery guidance for failed checkpoints.

Suggestions

Trim or merge the 'Key Success Factors' and 'Expected Outcomes' sections, which largely restate the numbered steps.

Add brief error-recovery guidance at the verification checkpoints, e.g. what to do if the feigned injury is not convincing or the escape route is blocked before committing to action.

DimensionReasoningScore

Conciseness

The body is mostly efficient and free of concept-overexplaining, but the 'Key Success Factors' and 'Expected Outcomes' sections largely restate the steps (e.g. 'Convincing performance of injury', 'Successful escape from captivity'), so it could be tightened.

2 / 3

Actionability

For an instruction-only skill it gives concrete, specific guidance — 'Pretend to be more severely wounded or dead', 'Mount a nearby horse', 'Push off or disable any rider', 'Seize available weapons' — meeting the actionable-guidance bar without needing code.

3 / 3

Workflow Clarity

The seven steps are clearly sequenced and include verification checkpoints ('Validate that an escape route and mount have been identified before committing to action'), but there are no error-recovery feedback loops (what to do if a checkpoint fails), which the 3 anchor requires.

2 / 3

Progressive Disclosure

At under 50 lines with no need for external references, the well-organized sections (Overview, Steps, Key Success Factors, Expected Outcomes, Verification) meet the simple-skill bar for full progressive-disclosure credit.

3 / 3

Total

10

/

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, third-person description with an explicit 'Use when' trigger and a concrete sequence of capabilities. Its only weakness is limited keyword variation coverage for its trigger terms.

Suggestions

Add a few natural trigger variations to broaden keyword matching, e.g. 'Use when captured, held prisoner, or trying to escape enemy captivity'.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'feigning death or injury, observing guards and resources, then seizing a sudden opportunity to commandeer a horse and flee' — matching the anchor for listing several specific concrete actions rather than just naming a domain.

3 / 3

Completeness

It explicitly answers both 'when' ('Use when captured by enemy forces and seeking to escape') and 'what' ('Involves feigning death or injury... commandeer a horse and flee'), satisfying the both-what-and-when anchor.

3 / 3

Trigger Term Quality

It includes relevant natural terms a user might say ('captured by enemy forces', 'seeking to escape'), but offers limited variation coverage compared to the multi-variation 3-anchor example, with no synonyms or alternate phrasings.

2 / 3

Distinctiveness Conflict Risk

The escape-from-captivity niche is highly specific with distinct triggers ('captured by enemy forces', 'commandeer a horse'), making it unlikely to fire for an unrelated skill.

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.