CtrlK
BlogDocsLog inGet started
Tessl Logo

intelligence-deception-operation

Use when planning military ambushes using double agents and staged evidence. Covers agent selection, credibility establishment, force coordination, and engagement triggers to lure enemies into prepared positions.

61

Quality

71%

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_205/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

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

The content is well-organized and concise for a short instructional skill, with a clear sequenced workflow and verification section. It is held back by some abstract, non-actionable steps and the absence of explicit feedback loops for a destructive operation.

Suggestions

Add concrete examples or criteria to the abstract steps - e.g., what makes an offer 'compelling' and what specific conditions qualify as engagement triggers.

Introduce explicit feedback loops around the Verification checks (e.g., 'If the cover story fails scrutiny, revise X then re-validate') rather than treating verification as a final after-the-fact list.

Remove or condense the 'Expected Outcomes' section, which states predictable results and duplicates intent already conveyed by the Steps and Overview.

DimensionReasoningScore

Conciseness

The body is reasonably lean and avoids explaining concepts Claude already knows, but the Overview duplicates the frontmatter description and the 'Expected Outcomes' section states predictable results rather than instructing, so it could be tightened.

2 / 3

Actionability

Several steps give concrete guidance (e.g., 'Position superior numbers in concealment near the target' and the staged-evidence example), but others like 'Create a compelling offer' and 'Set specific conditions' for engagement triggers remain abstract without enough concrete detail.

2 / 3

Workflow Clarity

Steps 1-7 are clearly sequenced and a Verification section provides pre-action checks, but there are no explicit feedback loops (validate -> fix -> retry) interleaved with the steps, which the rubric expects for destructive operations.

2 / 3

Progressive Disclosure

The skill is under 50 lines with no external references and is organized into clearly labeled sections (Overview, Steps, Risk Factors, Failure Points, Expected Outcomes, Verification), meeting the simple-skill standard for a top score.

3 / 3

Total

9

/

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 that clearly states both capability and trigger conditions with concrete, specific actions in a distinct niche. The main weakness is that several trigger terms lean toward technical jargon rather than natural user phrasing.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions - 'agent selection, credibility establishment, force coordination, and engagement triggers to lure enemies into prepared positions' - matching the anchor for listing several specific concrete actions rather than a vague domain mention.

3 / 3

Completeness

It explicitly answers both what ('Covers agent selection, credibility establishment, force coordination, and engagement triggers...') and when ('Use when planning military ambushes...'), with an explicit 'Use when' trigger clause.

3 / 3

Trigger Term Quality

It includes natural niche terms like 'planning military ambushes' and 'double agents', but more technical phrases such as 'credibility establishment' and 'engagement triggers' are jargon rather than terms a user would naturally say, leaving common variations uncovered.

2 / 3

Distinctiveness Conflict Risk

The niche - military ambushes via double agents and staged evidence - is highly specific and unlikely to overlap with or trigger for unrelated skills.

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.