Skills creating-skills
📦

creating-skills

Content revision r1 Medium Risk ⚙️ External commands📁 Filesystem access

建立 Claude Code 技能

建立實用的 AI 技能需要清楚的觸發條件、結構與防護措施。本指南協助作者透過範例與品質檢查，撰寫精簡的 Claude Code 技能。

Supports: Claude Codex Code(CC)
Maintain this Skill? Claim it 📊 71 Adequate

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "creating-skills" from https://skillstore.io/skills/bae-changhyun-creating-skills.md and its manifest at https://skillstore.io/api/skills/bae-changhyun-creating-skills/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/bae-changhyun-creating-skills.md Signed manifest GET /api/skills/bae-changhyun-creating-skills/manifest Signed lockfile GET /api/skills/bae-changhyun-creating-skills/lockfile

Test it

Using "creating-skills". 我需要一個根據已合併 pull requests 建立 release notes 的技能。

Expected outcome:

一份精簡的技能大綱，包含 release-notes 名稱、著重觸發條件的 description、quick start、工作流程步驟、helper script 指引與審查檢查清單。

Using "creating-skills". 這個技能檔案太長，而且包含很多範例。

Expected outcome:

一份重構計畫，讓主要工作流程保持簡短，並將延伸範例、疑難排解與背景資料移到參考資料中。

Using "creating-skills". 檢查我的技能是否遵循 Claude Code 慣例。

Expected outcome:

一份審查摘要，涵蓋 frontmatter、命名、觸發片語、行數、helper script 價值與權限指引。

Security Audit

Medium Risk
v8 • 7/6/2026 Open versioned report

The static command and filesystem findings are false positives caused by Markdown examples, inline code spans, and standard Claude skills directory documentation. One semantic concern remains: the guide encourages broad Bash wildcard permissions, which can lead authors to grant generated skills more command access than necessary.

1
Files scanned
281
Lines analyzed
0
Review items
0
False positives ignored

Confirmed security concerns (1)

Medium
SKILL.md:231-250
Overbroad Bash Permission Guidance
The guide recommends wildcard Bash permissions such as Bash(git *), Bash(npm *), and Bash(mkdir *) for cleaner permissions. Generated skills could receive broader command access than needed.
The text directly recommends broad wildcard permission patterns and labels them cleaner. This is legitimate documentation, but it can weaken least-privilege controls in generated skills.

Risk Factors

⚙️ External commands (38)
SKILL.md:12-39 SKILL.md:39-45 SKILL.md:45-50 SKILL.md:50-54 SKILL.md:54-61 SKILL.md:61-65 SKILL.md:65-66 SKILL.md:66 SKILL.md:70-72 SKILL.md:72-75 SKILL.md:75-79 SKILL.md:79-88 SKILL.md:88-101 SKILL.md:101-102 SKILL.md:102-103 SKILL.md:103-120 SKILL.md:120-121 SKILL.md:121-134 SKILL.md:134-140 SKILL.md:140-155 SKILL.md:155-164 SKILL.md:164-172 SKILL.md:172-188 SKILL.md:188-192 SKILL.md:192-200 SKILL.md:200-205 SKILL.md:205-210 SKILL.md:210-216 SKILL.md:216-230 SKILL.md:230-231 SKILL.md:231-235 SKILL.md:235-237 SKILL.md:237-251 SKILL.md:251-256 SKILL.md:256 SKILL.md:257 SKILL.md:258 SKILL.md:259
📁 Filesystem access (6)
SKILL.md:14 SKILL.md:17 SKILL.md:165 SKILL.md:14 SKILL.md:17 SKILL.md:165
Audited by: codex View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/bae-changhyun-creating-skills/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/bae-changhyun-creating-skills/security.svg)](https://skillstore.io/skills/bae-changhyun-creating-skills?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/bae-changhyun-creating-skills?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/bae-changhyun-creating-skills/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/bae-changhyun-creating-skills.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

Bae-ChangHyun. (2026). creating-skills security audit report (audit version 8) [Author version unspecified]. Skillstore. https://skillstore.io/skills/bae-changhyun-creating-skills/audits/8

BibTeX citation

@techreport{bae-changhyun-bae-changhyun-creating-skills-2026, author = {Bae-ChangHyun}, title = {creating-skills security audit report (audit version 8)}, institution = {Skillstore}, year = {2026}, number = {8}, url = {https://skillstore.io/skills/bae-changhyun-creating-skills/audits/8}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "creating-skills security audit report (audit version 8)" version: "unspecified" type: report authors: - name: "Bae-ChangHyun" date-released: "2026-07-06" url: "https://skillstore.io/skills/bae-changhyun-creating-skills/audits/8" identifiers: - type: other value: "skillstore:bae-changhyun-creating-skills:audit:8" description: "Skillstore immutable audit report identifier"

Compare variants

6 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score
BrendanShields Recommended

brendanshields-creating-skills

Skillstore Score 79
Evidence Confidence High
Skillstore usage 56
Updated

2026-09-09

BPSAI

bpsai-creating-skills

Skillstore Score 78
Evidence Confidence High
Skillstore usage 16
Updated

2026-09-09

AgentWorkforce

agentworkforce-creating-skills

Skillstore Score 77
Evidence Confidence High
Skillstore usage 47
Updated

2026-10-22

Bae-ChangHyun Current

bae-changhyun-creating-skills

Skillstore Score 71
Evidence Confidence High
Skillstore usage 52
Updated

2026-09-09

Asmayaseen

asmayaseen-creating-skills

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 49
Updated

2026-10-25

Awais68

awais68-creating-skills

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 48
Updated

2026-09-09

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
85
Maintainability
87
Content
72
Community
91
Spec Compliance

What You Can Build

撰寫第一個技能草稿

建立乾淨的 SKILL.md 大綱，包含必要 metadata、簡短工作流程與聚焦規則。

審查技能結構

檢查現有技能的命名、觸發片語、token budget 與章節順序。

規劃支援參考資料

決定哪些範例、指南或 helper scripts 應放在主要技能檔案之外。

Try These Prompts

開始基本技能 
使用 creating-skills guide，為一個協助處理 [task] 的技能撰寫 SKILL.md。包含 frontmatter、quick start 與核心規則。
改善現有草稿 
使用 creating-skills checklist 審查我的 SKILL.md。找出不清楚的觸發條件、多餘細節、缺少的章節與權限風險。
拆分詳細參考資料 
幫我重新整理這個很長的技能。讓 SKILL.md 保持在 500 行以下，並將詳細範例移到參考檔案中。
設計技能套組 
為 [domain] 規劃一組相關的 Claude Code 技能。建議名稱、description、共用參考資料、helper scripts 與審查標準。

Best Practices

  • 撰寫 descriptions 時，說明技能會做什麼、何時使用，以及主要能力。
  • 讓 SKILL.md 保持聚焦，並將冗長範例移到參考檔案中。
  • 在進行檔案變更、破壞性命令或建立外部資源前，要求確認。

Avoid

  • 為代理可以直接執行的簡單命令建立 wrapper scripts。
  • 加入不會改變代理工作流程的廣泛背景說明。
  • 在任務特定權限可行時，使用過於寬泛的命令權限。

Frequently Asked Questions

這個技能能幫我建立什麼？
它能協助你撰寫 Claude Code 技能，包含清楚的 metadata、結構、範例與品質檢查。
它可以幫我建立檔案嗎？
它包含設定範例，但在寫入磁碟前，檔案建立仍應由使用者核准。
它能搭配 Codex 使用嗎？
這些指引對 Codex 輔助撰寫很有用，但技能格式是針對 Claude Code 技能。
它包含安全指引嗎？
它建議在關鍵動作前進行確認，但權限範例應針對正式環境技能進一步收窄。
我應該何時加入 helper scripts？
只有在可重複使用、複雜或結構化處理能提供明確價值時，才加入 scripts。
SKILL.md 應該多長？
本指南建議將主要檔案維持在 500 行以下，並將細節移到參考資料中。

Developer Details

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/Bae-ChangHyun/cc-plugins-bch/tree/main/plugins/utils/skills/creating-skills

Ref

c4231f0153ccd2a2ed62274c5a372bf8f2386d3f

Maintenance freshness

7/18/2026

Usage

7 downloads · 312 views

File structure

📄 SKILL.md

More from Bae-ChangHyun

View all

Related Skills

View all