strategic-retreat-decision

Use when balancing honor-based commitments against tactical military advantage. Applies Duke Wen's three-stage retreat (三舍) framework: recalling past agreements, assessing current position, weighing long-term reputation versus immediate gains, and documenting decision rationale.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

71%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 decision framework with a clear sequence and verification checklist. Its weakest point is actionability, since the judgment steps remain conceptual without concrete evaluation criteria.

Suggestions

Add a concrete scoring rubric or thresholds for the ambiguous judgments (e.g., define how to weigh 'odds of victory' or when 'honor is paramount') so the decision branches are operational, not just conceptual.

Inline a validation gate within the Decision Process (e.g., 'Before deciding, confirm all past agreements are documented') rather than relegating checks to a separate post-hoc Verification section, creating an explicit validate-then-proceed loop.

Trim the redundancy between the Overview and Decision Criteria sections, which restate the description's considerations, to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence without explaining basic concepts, but the Overview and Decision Criteria sections mildly restate the description and overlap each other, so it is not quite the every-token-earns-its-place anchor.	4 / 5
Actionability	Concrete decision branches are present ('If agreement exists and honor is paramount → Retreat as promised'), but the assessment steps ('Evaluate military position and odds of victory') lack operational thresholds or a scoring rubric, leaving the executable guidance incomplete.	3 / 5
Workflow Clarity	A clear five-step Decision Process is followed by a dedicated three-item Verification section providing checkpoints, but validation is post-hoc rather than an inline feedback loop (validate → fix → retry), so it sits below the top anchor.	4 / 5
Progressive Disclosure	At under 50 lines with no need for external references, the body is organized into clearly labeled sections (Overview, Decision Criteria, Decision Process, Example Application, Expected Outcome, Verification), satisfying the simple-skill exception for the top anchor.	5 / 5
	Total	16 / 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 well-constructed description with explicit what/when triggers and a distinctive niche. Its only weakness is that the named actions are conceptual process steps rather than concrete operations, leaving specificity slightly below the top anchor.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('recalling past agreements, assessing current position, weighing long-term reputation versus immediate gains, and documenting decision rationale'), but they are abstract process verbs rather than concrete operations like file types or outputs, so it stops short of the comprehensive anchor.	4 / 5
Completeness	Explicitly answers both 'what' (the three-stage retreat framework with its four actions) and 'when' (the 'Use when balancing honor-based commitments against tactical military advantage' trigger), matching the explicit-trigger anchor.	5 / 5
Trigger Term Quality	Includes natural trigger terms ('retreat', 'honor-based commitments', 'tactical military advantage', 'reputation') and an explicit 'Use when balancing...' clause, though a few common synonyms (withdrawal, treaty, alliance) are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a narrow, distinctive niche (Duke Wen's 三舍 retreat decision) with triggers unlikely to collide with other skills, matching the clear-niche anchor.	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_094/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.