Skills creating-skills
📦

creating-skills

Content revision r1 High Risk ⚡ Contains scripts⚙️ External commands📁 Filesystem access

Create AI Agent Skills With Structure

Building reusable agent skills is hard when structure, triggers, and validation rules are unclear. This skill guides design, scaffolding, verification, and packaging for Claude, Codex, and Claude Code.

Supports: Claude Codex Code(CC)
⚠️ 38 Poor

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/awais68-creating-skills.md and its manifest at https://skillstore.io/api/skills/awais68-creating-skills/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

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/awais68-creating-skills.md Signed manifest GET /api/skills/awais68-creating-skills/manifest Signed lockfile GET /api/skills/awais68-creating-skills/lockfile

Test it

Using "creating-skills". I need a skill for reviewing pull requests.

Expected outcome:

A concise trigger description, a SKILL.md outline, and a short list of optional review references.

Using "creating-skills". My skill activates too often.

Expected outcome:

A revised trigger, clear exclusion conditions, and notes explaining how each change reduces collisions.

Using "creating-skills". Package this skill for sharing.

Expected outcome:

A validation checklist, packaging steps, and issues to fix before distribution.

Security Audit

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

Static findings are mostly false positives from Markdown backticks, prose examples, and intended local packaging code. A semantic concern remains because references/skill-activation.md teaches forceful activation prompts that can manipulate agent behavior.

7
Files scanned
926
Lines analyzed
0
Review items
0
False positives ignored

Confirmed security concerns (1)

High
references/skill-activation.md:35-39references/skill-activation.md:53-59
Prompt Injection Attempt Detected
The reference recommends a "Forced eval" activation pattern and tells agents that evaluating each skill is "MANDATORY" before proceeding. It also says aggressive words make instructions harder to ignore, which is prompt-manipulation guidance.
The exact wording appears in a reference file and is framed as a way to force agent behavior. It does not target this audit or exfiltrate data, so confidence is high but not maximal.

Risk Factors

⚡ Contains scripts (1)
references/skill-activation.md:35
⚙️ External commands (29)
scripts/init_skill.py:73 scripts/init_skill.py:74 scripts/init_skill.py:84 SKILL.md:51-62 SKILL.md:62-68 SKILL.md:68 SKILL.md:73-78 SKILL.md:78-82 SKILL.md:82-87 SKILL.md:87 SKILL.md:91-96 SKILL.md:96 SKILL.md:150-152 SKILL.md:152-156 SKILL.md:156-158 SKILL.md:158-160 SKILL.md:160-165 SKILL.md:165 SKILL.md:173 SKILL.md:175 SKILL.md:176-184 SKILL.md:184-198 SKILL.md:198-215 SKILL.md:215-217 SKILL.md:217-234 SKILL.md:234-236 SKILL.md:236-239 SKILL.md:239-241 SKILL.md:241-245
📁 Filesystem access (2)
scripts/package_skill.py:14 scripts/package_skill.py:68
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/awais68-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/awais68-creating-skills/security.svg)](https://skillstore.io/skills/awais68-creating-skills?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/awais68-creating-skills?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/awais68-creating-skills/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/awais68-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

Awais68. (2026). creating-skills security audit report (audit version 8) [Author version unspecified]. Skillstore. https://skillstore.io/skills/awais68-creating-skills/audits/8

BibTeX citation

@techreport{awais68-awais68-creating-skills-2026, author = {Awais68}, title = {creating-skills security audit report (audit version 8)}, institution = {Skillstore}, year = {2026}, number = {8}, url = {https://skillstore.io/skills/awais68-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: "Awais68" date-released: "2026-07-06" url: "https://skillstore.io/skills/awais68-creating-skills/audits/8" identifiers: - type: other value: "skillstore:awais68-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 18
Updated

2026-08-21

BPSAI

bpsai-creating-skills

Skillstore Score 78
Evidence Confidence High
Skillstore usage 10
Updated

2026-08-21

AgentWorkforce

agentworkforce-creating-skills

Skillstore Score 77
Evidence Confidence High
Skillstore usage 9
Updated

2026-08-21

Bae-ChangHyun

bae-changhyun-creating-skills

Skillstore Score 71
Evidence Confidence High
Skillstore usage 12
Updated

2026-08-21

Asmayaseen

asmayaseen-creating-skills

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 11
Updated

2026-08-21

Awais68 Current

awais68-creating-skills

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 9
Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: Medium
68
Architecture
85
Maintainability
87
Content
70
Community
91
Spec Compliance

What You Can Build

Create a New Skill

Plan SKILL.md, triggers, and supporting resources before writing a new agent skill.

Improve Existing Skill Structure

Review an existing skill for clear triggers, concise instructions, and useful resource separation.

Prepare Skills for Sharing

Validate required files and package a local skill into a distributable archive.

Try These Prompts

Create a First Skill 
Help me create a new skill for [task]. Ask for concrete examples first, then propose the SKILL.md structure and needed resources.
Improve Skill Triggering 
Review this skill description for clear trigger conditions. Suggest a shorter version with explicit exclusions and fewer workflow details.
Plan Reusable Resources 
Given these repeated skill tasks, identify which reusable scripts, references, or assets should be added and explain why each belongs there.
Review and Package 
Audit this skill for structure, trigger quality, resource relevance, validation readiness, and packaging risks before I share it with others.

Best Practices

  • Start with concrete user requests before writing instructions.
  • Keep SKILL.md short and move detailed material into references.
  • Validate the skill before packaging or sharing it.

Avoid

  • Do not put broad workflow summaries in the description.
  • Do not bundle example files that are unrelated to the skill purpose.
  • Do not use forceful prompt language that overrides normal agent judgment.

Frequently Asked Questions

What does this skill help me create?
It helps create AI Agent Skills with SKILL.md instructions, optional resources, validation, and packaging.
Can it update an existing skill?
Yes. It can review trigger text, structure, resources, and validation issues for an existing skill.
Does it work with Codex and Claude Code?
Yes. The report lists support for Claude, Codex, and Claude Code.
Does it write all domain content for me?
No. It needs concrete user examples and domain requirements to produce useful skill instructions.
What files can a skill include?
A skill requires SKILL.md and may include scripts, references, and assets when they add clear value.
Should I run the bundled scripts automatically?
Review script behavior first, then run only the commands needed for your local skill work.

Developer Details

Author

Awais68

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/Awais68/hackathon-2-phase-ii-full-stack-web-app/tree/main/.claude/skills/creating-skills

Ref

c4231f0153ccd2a2ed62274c5a372bf8f2386d3f

Maintenance freshness

7/18/2026

Usage

7 downloads · 182 views

File structure

📁 references/

📄 design-patterns.md

📄 skill-activation.md

📄 two-stage-review.md

📁 scripts/

📄 init_skill.py

📄 package_skill.py

📄 verify.py

📄 SKILL.md