protracted-strategy

触发：当目标长期、任务复杂、资源暂时处于劣势，或短期无法速胜但又不能放弃时调用；常见信号包括 long-term effort、phased plan、endurance、战略耐心、需要分阶段推进。 English: Trigger when the work is long-horizon, difficult, and unlikely to be won quickly. Use this skill to divide the effort into stages, keep strategic confidence, and accumulate small wins into overall victory.

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

77%

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

The body delivers a clear, actionable, well-sequenced workflow with explicit checkpoints and a concrete operation template. Its main weaknesses are atmospheric quote-padding that could be tightened and a referenced support file (original-texts.md) that does not exist in the bundle.

Suggestions

Either add the missing references/original-texts.md or remove the dangling reference so progressive disclosure resolves to real files.

Trim the Mao epigraphs to one anchor quote and consolidate the overlapping '何时使用' and '不适用场景' sections to improve token efficiency.

Consider moving the common-errors table and stage details into a single one-level-deep reference to keep SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	It avoids explaining concepts Claude already knows and is purposefully organized, but the repeated Mao quotations, atmospheric framing, and overlap between '何时使用', '不适用场景', and the methodology add tokens that could be tightened, fitting 'mostly efficient but includes some unnecessary explanation'.	2 / 3
Actionability	Provides concrete executable guidance: a mandated stage-assessment table, a literal fill-in template, explicit stage definitions, and required actions ('必须同时给出局部进攻点', '设置阶段检查点'), which is actionable without needing code per the instruction-skill scoring note.	3 / 3
Workflow Clarity	A clearly sequenced six-step methodology is reinforced by an operation procedure with explicit validation checkpoints ('在完成 [具体里程碑] 后，重新调用此 skill 评估阶段', '转入下一阶段的条件：当 [具体条件] 时') that function as feedback loops.	3 / 3
Progressive Disclosure	Sections are well-organized, but the body is a ~160-line monolithic overview and the single external reference ('详细原著依据见 original-texts.md') points to a file that is not present in the bundle, so the one-level-deep reference does not resolve.	2 / 3
	Total	10 / 12 Passed

Description

90%

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-structured with an explicit trigger clause and clear natural-language signals, covering both what and when. Its only weakness is that the stated capabilities are strategic abstractions rather than concrete, listable technical actions.

Suggestions

Pair the abstract strategic actions with at least one concrete deliverable (e.g., 'output a phased stage-assessment table and action plan') so the what-it-does claim is tangible.

Tighten the bilingual framing so the English line stands alone as the primary description and the Chinese signals read as supporting keywords, reducing redundancy.

Dimension	Reasoning	Score
Specificity	Names the domain and several actions ('divide the effort into stages', 'keep strategic confidence', 'accumulate small wins into overall victory'), but these are abstract strategic concepts rather than concrete operational actions like 'extract text and fill forms', so it stops short of the most specific anchor.	2 / 3
Completeness	Explicitly answers both what ('divide the effort into stages, keep strategic confidence, and accumulate small wins into overall victory') and when ('触发：当...调用' / 'Trigger when the work is long-horizon, difficult, and unlikely to be won quickly'), with an explicit trigger clause equivalent to 'Use when'.	3 / 3
Trigger Term Quality	Provides good coverage of natural trigger terms a user would say — 'long-horizon', 'long-term effort', 'phased plan', 'endurance', '战略耐心', '需要分阶段推进' — alongside explicit signal conditions.	3 / 3
Distinctiveness Conflict Risk	The trigger conditions (long-horizon, disadvantaged, cannot win quickly but cannot abandon, phased endurance) carve a distinct niche that is unlikely to fire for the wrong skill.	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: HughYau/qiushi-skill
Path: skills/protracted-strategy/SKILL.md
Commit: 6710791

Reviewed: 6 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.