research-guide-updater

当用户明确要求"更新项目指南""同步指南""沉淀洞见到指南"，或要求使用旧名 guide-updater skill 时使用。将对话中新产生的可复用写作洞见实时沉淀到项目指南文件，保持术语口径一致、结构稳定、可检验与可复现。调用时必须指定指南文件路径。

Quality

87%

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 well-structured, actionable instruction skill with a clear sequenced workflow, explicit validation feedback loop, and clean one-level-deep progressive disclosure. The only drag on token efficiency is the tangential BenszAPI workspace and bug-collaboration boilerplate.

Suggestions

Move the BenszAPI task-workspace layout and bensz-collect-bugs collaboration sections into a separate reference file (or trim them to a one-line pointer) so SKILL.md focuses on the guide-update task and improves conciseness.

Add a one-line note in '更新后校验' on what to do when validate_guide.py reports missing headings (e.g., do not re-add them as new '##' sections — restore the original heading text instead), closing the validation feedback loop with an explicit fix path.

Dimension	Reasoning	Score
Conciseness	The core sections are lean actionable bullets with no concept-explanation, but the BenszAPI task-workspace and bensz-collect-bugs collaboration sections are tangential overhead not directly needed to update a guide, so it could be tightened.	2 / 3
Actionability	Provides concrete executable guidance: the '/research-guide-updater --guide-path <路径>' invocation, the 'python skills/research-guide-updater/scripts/validate_guide.py <指南文件路径>' validation command, and specific section-placement rules.	3 / 3
Workflow Clarity	A clear sequenced workflow (先决条件自检 → 抽取原子洞见 → 选择融入位置 → 以最小补丁写入 → 更新后校验) with an explicit validation feedback loop (run validate_guide.py and search for unintended new '##' headings).	3 / 3
Progressive Disclosure	Overview stays in SKILL.md while detail lives one level deep in real, well-signaled files (references/guide-structure-map.md, scripts/validate_guide.py), with a Resources table mapping directory to purpose.	3 / 3
	Total	11 / 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-targeted with explicit triggers and a clear what/when structure; it is distinct and unlikely to conflict. Its only weakness is that it expresses capabilities as properties rather than a list of distinct concrete actions.

Dimension	Reasoning	Score
Specificity	Names the core action ('将对话中新产生的可复用写作洞见实时沉淀到项目指南文件') and maintenance properties (术语口径一致/结构稳定/可检验与可复现), but lists properties rather than multiple distinct concrete actions, so it is below the multi-action anchor.	2 / 3
Completeness	It explicitly answers both 'what' (沉淀洞见, 保持口径/结构/可检验与可复现) and 'when' ('当用户明确要求…时使用'), with explicit trigger guidance.	3 / 3
Trigger Term Quality	Natural user-facing terms '更新项目指南''同步指南''沉淀洞见到指南' plus legacy aliases 'guide-updater'/'guide updater' give good coverage of phrases a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (research-writing project guide updater) with distinct triggers and a required guide-path argument, making unintended triggering of other skills unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: huangwb8/ChineseResearchLaTeX
Path: skills/research-guide-updater/SKILL.md
Commit: 01044a6

Reviewed: 3 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.