protective-deception-for-heir-preservation

Use when protecting a vulnerable heir from systematic elimination by powerful enemies. Covers multi-layered deception: concealment, substitute infant decoys, staged betrayal to convince enemies the heir is dead, long-term secret raising, and eventual restoration when political conditions shift.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

65%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 compact, well-structured instruction skill with a clear sequenced workflow and a verification section, but its guidance stays at a high level and its destructive steps lack interleaved validation checkpoints.

Suggestions

Add explicit validation checkpoints between destructive phases (e.g., before executing the sacrifice, confirm the substitute cannot be distinguished from the heir and that the betrayer's cover will hold) to lift workflow clarity above the destructive-operation cap.

Make steps more actionable by specifying concrete criteria or signals (e.g., what 'political conditions have shifted' looks like, how to verify a leak has not occurred) rather than abstract directives.

Tighten generic phrases like 'Maintain absolute secrecy' into specific operational practices to push conciseness to fully lean.

Dimension	Reasoning	Score
Conciseness	Lean, terse steps with no over-explanation of concepts Claude already knows; not a 5 because a few phrases ('Maintain absolute secrecy', 'Arrange for a protector to betray') are slightly generic and could be tightened.	4 / 5
Actionability	Steps name specific actions ('Obtain a substitute infant of similar age', 'Create a false trail') but give no concrete executable detail; this is instruction-only guidance at a high level rather than copy-paste-ready specifics.	3 / 5
Workflow Clarity	Six phases are clearly sequenced and a Verification section exists, but this involves destructive operations (killing the substitute, eliminating enemies) with validation only as a post-hoc checklist rather than interleaved checkpoints, so it is capped at 3 per the destructive-operation rule.	3 / 5
Progressive Disclosure	Under 50 lines, single-purpose, well-organized into clear sections (Overview, Prerequisites, Steps, Critical Success Factors, Verification) with no external references needed; qualifies for 5 under the simple-skill exception.	5 / 5
	Total	15 / 20 Passed

Description

87%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 description with an explicit 'Use when' trigger and a concrete enumeration of the deception layers it covers. It clearly answers both what the skill does and when to invoke it, with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('concealment, substitute infant decoys, staged betrayal... long-term secret raising, and eventual restoration'), comprehensive in coverage though the framing phrase 'multi-layered deception' is somewhat abstract; not a 5 because the actions are enumerated as a list rather than fully unpacked.	4 / 5
Completeness	Explicitly answers both 'what' ('Covers multi-layered deception: concealment, substitute infant decoys, staged betrayal... restoration') and 'when' ('Use when protecting a vulnerable heir from systematic elimination') with concrete trigger phrasing.	5 / 5
Trigger Term Quality	'Use when protecting a vulnerable heir from systematic elimination by powerful enemies' is a natural trigger phrase with good domain keywords, but coverage lacks common synonyms or variations; a few natural terms missing for a 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a very clear niche (heir preservation via staged deception) with distinct triggers; minimal realistic overlap with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

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
Path: kg/ontology/ontology-v1/skus/procedural/skill_115/SKILL.md
Commit: 6b836e3

Reviewed: 13 days ago

Table of Contents

Discovery Implementation Validation

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.