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

73%

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 ./skills/research-guide-updater/SKILL.md

Quality

Content

67%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 body is well-structured and actionable with a real validation step, recovery section, and genuine one-level-deep references that exist on disk. It is held back by a repeated description sentence and a heavy block of generic infrastructure constraints that add tokens without skill-specific value.

Suggestions

Remove the verbatim repeat of the description at line 31 and trim or reference out the generic '公共硬约束' boilerplate so the body stays focused on guide-updating specifics.

Add one concrete before/after example of an incremental patch (an existing bullet plus the appended clarifying sentence) to move actionability toward copy-paste readiness.

Defer the full section-to-content placement map to references/guide-structure-map.md and keep only a one-line pointer inline, reducing duplication between SKILL.md and the reference.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete placement rules and commands, but it repeats the description sentence verbatim (line 31) and carries a large generic '公共硬约束' boilerplate block (API keys, SSRF, path traversal) only tangentially related to this skill's task, so it could be tightened.	3 / 5
Actionability	Provides concrete, executable guidance: a specific validation command ('python skills/research-guide-updater/scripts/validate_guide.py <指南文件路径>'), an explicit invocation form, and a section-to-content placement map; minor gaps remain (no worked before/after bullet example of an actual incremental patch).	4 / 5
Workflow Clarity	A clear sequence is present — 先决条件 self-check checklist → 输入 → 执行步骤 → 校验 (validate_guide.py plus searching for stray ## headings) → 失败与恢复 — with an explicit validation checkpoint and a recovery loop; it falls just short of 5 because the validation/error-handling detail is brief rather than a full fix-and-retry loop.	4 / 5
Progressive Disclosure	Structure is good: SKILL.md stays an overview with a table explaining scripts/ and references/ purposes, and points to the real one-level-deep bundle files (references/guide-structure-map.md, scripts/validate_guide.py) which both exist; minor gap is that the inline 写作哲学/命名与术语 mapping (lines 49-56) partially duplicates the reference file rather than deferring entirely.	4 / 5
	Total	15 / 20 Passed

Description

78%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 strong: it provides explicit trigger phrases with synonyms, a clear what/when pair in third person, and a distinctive niche. The main weakness is specificity — most clauses describe qualities of the output rather than multiple discrete concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain (guide updating) and a concrete 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' — but the remaining clauses ('术语口径一致、结构稳定、可检验与可复现') describe desired properties rather than additional distinct concrete actions, so coverage is not comprehensive.	3 / 5
Completeness	Explicitly answers both 'what' (distill reusable writing insights into the project guide, preserving terminology/structure/verifiability) and 'when' with concrete trigger phrases ('当用户明确要求…时使用'), matching the anchor that requires both with explicit triggers; voice is third-person, so no penalty applies.	5 / 5
Trigger Term Quality	Includes several natural user phrases — '更新项目指南', '同步指南', '沉淀洞见到指南', plus the legacy name 'guide-updater' — giving good synonym coverage; a few natural variants (e.g. '修订指南', '补充指南') are absent, so it falls just short of the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	The niche (incremental updates to a research-writing project guide) and triggers are fairly specific and distinct from generic doc-editing skills, but there is minor overlap risk with broad 'update documentation' skills, placing it just below the minimal-conflict anchor.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: huangwb8/ChineseResearchLaTeX
Path: skills/research-guide-updater/SKILL.md
Commit: dd19421

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.