siege-feasibility-assessment

Use when evaluating siege feasibility or deciding whether to continue besieging a fortified city. Based on Xu Jia's advice against attacking Daliang (大梁) — systematically assessing defender strength, fortification quality, historical precedent, and cost of failure before committing.

Quality

85%

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

85%

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

The body is a compact, well-structured decision framework with a clear step sequence and a genuine validation checklist. Its main weakness is actionability: the guidance is advisory reasoning rather than concrete, executable procedures, which is inherent to the strategic-judgment domain but still leaves room for more decisive outputs.

Suggestions

Add a concrete decision-output template (e.g. a short go/no-go verdict block with fields for each assessed factor) so the skill produces a tangible artifact rather than open-ended reasoning.

Tighten the slight redundancy between the Steps and the Decision Criteria sections by merging repeated "do not besiege" rules into a single decision table.

Dimension	Reasoning	Score
Conciseness	The body is lean — short bullets under Overview, Steps, Decision Criteria, Expected Outcomes, and Validation — with no padding explaining concepts Claude already knows, so every section earns its place.	3 / 3
Actionability	Concrete examples ("300,000" defenders, "7-ren high walls") add specificity, but the guidance is an advisory reasoning framework ("Consider defender morale", "Would even legendary commanders succeed?") rather than executable, copy-paste-ready operations, fitting the some-concrete-guidance-but-incomplete anchor.	2 / 3
Workflow Clarity	A clearly sequenced 5-step process is paired with a dedicated Validation section containing three explicit checkpoints (historical-precedent test, external-factor accounting, alternative achievability), matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	The skill is under 50 lines with no need for external references, and its content is organized into well-signaled sections (Overview, Steps, Decision Criteria, Expected Outcomes, Validation), satisfying the simple-skill exception for a top score.	3 / 3
	Total	11 / 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.

The description is well-constructed: it pairs an explicit "Use when..." trigger with a concrete enumeration of the assessment dimensions and a distinctive historical grounding. Its only gap is limited trigger-term variation, which slightly narrows how users would discover it.

Suggestions

Broaden trigger terms to include natural phrasings users might actually say, e.g. "lay siege", "assault", "storm a walled city", or "attack a fortified position".

Consider naming the deliverable explicitly (e.g. "produce a go/no-go recommendation") so the "what" is as concrete as the assessment inputs.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete assessment actions — "assessing defender strength, fortification quality, historical precedent, and cost of failure" — matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (the four assessment dimensions) and when ("Use when evaluating siege feasibility or deciding whether to continue besieging a fortified city") with an explicit trigger clause.	3 / 3
Trigger Term Quality	Includes natural domain terms ("siege feasibility", "besieging a fortified city") but lacks common variations users might say ("lay siege", "assault", "walled city", "storm"), so it sits at the some-relevant-keywords level rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	A clear niche — siege feasibility grounded in Xu Jia's advice against attacking Daliang — with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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_149/SKILL.md
Commit: 79c272f

Reviewed: 4 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.