strategic-patience-warfare

Use when commanding a large army against a determined enemy or planning patient siege warfare. Based on Wang Jian's (王翦) conquest of Chu with 600,000 troops — refusing battle, maintaining troop welfare through recreation and shared conditions, then striking when the enemy withdraws.

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./kg/ontology/ontology-v1/skus/procedural/skill_144/SKILL.md

Quality

Content

78%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.

The content is a tight, well-structured instruction skill with a clear sequenced workflow and an explicit validation section, needing only minor tightening and inline placement of checkpoints. It is lean and actionable for its strategic domain.

Suggestions

Inline the validation checks as numbered checkpoints within the Steps sequence (e.g. after 'Strike at Withdrawal') so the feedback loops are visible in the workflow rather than appended separately.

Tighten the Overview so it does not restate the frontmatter description, or remove it to let the Steps carry the guidance.

Add a touch more specificity on force-sizing and timing thresholds to close the minor actionability gaps.

Dimension	Reasoning	Score
Conciseness	The body is lean, well-organized into brief bullets, and assumes Claude's competence without explaining basic concepts; the only minor trim is the Overview restating the frontmatter description, keeping it at anchor 4 rather than 5.	4 / 5
Actionability	Concrete, specific strategic instructions are given (e.g. 'Refuse all challenges to battle', 'When soldiers start "throwing stones and jumping distances" they are ready', 'Pursue immediately with full force') with only minor gaps such as quantifying 'more troops than seemingly necessary'; as an instruction-only skill the absence of code is not penalized.	4 / 5
Workflow Clarity	A clear five-step sequence is present and an explicit Validation section provides feedback-style checks (genuine withdrawal vs feigned retreat, full commitment of pursuit), but the validation lives in a separate section rather than as inline checkpoints within the numbered steps, fitting anchor 4.	4 / 5
Progressive Disclosure	The skill is under 50 lines, single-purpose, and well-organized with clear section headers (Overview, Steps, Expected Outcomes, Validation); no bundle files exist and none are needed, so the simple-skill exception yields a 5 for well-organized sections.	5 / 5
	Total	17 / 20 Passed

Description

71%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.

The description is distinctive and explicitly pairs a 'Use when' trigger with concrete strategic actions, though its keyword coverage lacks common synonyms and the 'what' is somewhat historiographically framed. It is strong but not maximally complete or comprehensive.

Suggestions

Add natural synonyms users might say, e.g. 'siege', 'outwait the enemy', 'war of attrition', or 'protracted campaign', to broaden trigger coverage.

Reframe the 'what' as a concise action list (e.g. 'Refuse battle, maintain troop welfare, then strike on enemy withdrawal') separate from the historical basis to sharpen capability clarity.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'refusing battle', 'maintaining troop welfare through recreation and shared conditions', 'striking when the enemy withdraws' — with only minor coverage gaps, fitting the 'several specific actions' anchor rather than the fully comprehensive anchor 5.	4 / 5
Completeness	Explicitly answers both 'what' (the patience/comfort/strike strategy) and 'when' ('Use when commanding a large army against a determined enemy or planning patient siege warfare'), but the 'what' leans on a historical basis rather than a clean action enumeration, so it sits at anchor 4 rather than 5.	4 / 5
Trigger Term Quality	Relevant natural phrases ('commanding a large army', 'determined enemy', 'siege warfare') are present, but common variations/synonyms like 'siege', 'outwait', 'war of attrition', or 'protracted campaign' are missing, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear, highly specific niche (Wang Jian's 600,000-troop siege of Chu) with distinct triggers and minimal realistic conflict risk with other skills.	5 / 5
	Total	16 / 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_144/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.