Create Agent Skills for Claude Code
Writing reusable AI skills requires clear scope, frontmatter, and validation. This skill guides Claude Code through skill structure, examples, testing, and troubleshooting.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "skill-writer" from https://skillstore.io/skills/dami-randle-skill-writer.md and its manifest at https://skillstore.io/api/skills/dami-randle-skill-writer/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.
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Using "skill-writer". I want a skill for reviewing Terraform plans.
Expected outcome:
A focused skill plan with a valid name, activation description, expected files, example workflow, and testing checklist.
Using "skill-writer". My skill does not activate when I ask for spreadsheet analysis.
Expected outcome:
A troubleshooting checklist covering description specificity, file location, frontmatter validity, and restart or debug steps.
Using "skill-writer". Convert our release checklist into a reusable skill.
Expected outcome:
A proposed skill scope, SKILL.md outline, supporting reference files, concrete examples, and validation criteria.
All static alerts were adjudicated as false positives caused by Markdown code fences, inline code, and documented .claude/skills paths. The skill is a skill-authoring guide and I found no prompt injection, data exfiltration, covert network use, or hidden persistence intent.
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
https://skillstore.io/skills/dami-randle-skill-writer/audits/9?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/dami-randle-skill-writer?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/dami-randle-skill-writer?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/dami-randle-skill-writer/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/dami-randle-skill-writer.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Dami-Randle. (2026). skill-writer security audit report (audit version 9) [Author version unspecified]. Skillstore. https://skillstore.io/skills/dami-randle-skill-writer/audits/9@techreport{dami-randle-dami-randle-skill-writer-2026,
author = {Dami-Randle},
title = {skill-writer security audit report (audit version 9)},
institution = {Skillstore},
year = {2026},
number = {9},
url = {https://skillstore.io/skills/dami-randle-skill-writer/audits/9},
note = {Author version unspecified}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "skill-writer security audit report (audit version 9)"
version: "unspecified"
type: report
authors:
- name: "Dami-Randle"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/dami-randle-skill-writer/audits/9"
identifiers:
- type: other
value: "skillstore:dami-randle-skill-writer:audit:9"
description: "Skillstore immutable audit report identifier"
Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
pytorch-skill-writer
2026-08-21
dami-randle-skill-writer
2026-08-21
Build a focused skill for a repeated personal workflow with clear activation language and validation steps.
Define shared conventions for project skills, frontmatter, examples, and troubleshooting guidance.
Turn an existing prompt, checklist, or process into a reusable Claude Code skill structure.
Help me create a Claude Code skill for [workflow]. Ask me for the scope, target users, required files, and activation phrases.
Review my SKILL.md frontmatter. Make the name valid, improve the description, and ensure it includes what the skill does and when to use it.
Design a multi-file skill for [domain]. Recommend the file structure, what belongs in SKILL.md, and which supporting files should use progressive disclosure.
My Claude Code skill does not activate for relevant requests. Check likely causes in the description, file location, frontmatter, and testing workflow.
Author
Dami-RandleLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
34f316ba14ef36c7a620fc09f2676d2429997a77
Maintenance freshness
7/18/2026
Usage
3 downloads · 269 views
File structure
📄 SKILL.md
Build Claude Code Agents
Designing reliable Claude Code agents is hard without structure. This skill provides templates, validation rules, and examples for agent prompts, triggers, tools, and metadata.
Review Features Through Customer Personas
Teams can miss usability issues when reviewing features from an internal perspective. This skill guides persona-based testing with Aftrac and Sirius customer viewpoints.
Map User Journeys and Workflows
Teams need clear views of how users move through a service. This skill creates structured journey maps that expose actions, emotions, pain points, and opportunities.
Audit UX with Heuristic Reviews
Teams miss usability issues before release. This skill guides structured UX audits with scores, critical issues, and prioritized recommendations.
Audit Accessibility for WCAG Issues
Accessibility defects can block users and create compliance risk. This skill reviews interfaces against WCAG 2.1 and returns prioritized fixes.
Create Effective AI Skills
by notedit
Teams need repeatable guidance to build useful AI skills without adding unnecessary context. This skill provides a structured process for planning, writing, validating, and packaging skills.
Plan Software Projects With Structured Documents
by Dwsy
Software projects often fail when requirements, design choices, and tasks are unclear. This skill turns project ideas into structured planning documents for Claude, Codex, and Claude Code workflows.
Generate Bilingual GitHub Release READMEs
by ZhanlinCui
Release notes and README updates can take time before each GitHub release. This skill generates bilingual release documentation and guides review, commit, and push steps.
Visualize Service Architecture
by AstraBit-CPT
Distributed services are hard to understand when metadata is spread across repositories. This skill aggregates catalog metadata and creates diagrams, tables, and summaries for architecture review.
Create Human-Ready AI Documentation
by Brownbull
Detailed AI context files are often too long for quick human review. This skill turns them into summaries, quick starts, and Mermaid visual guides.
Create FlowGram Component Docs
by bytedance
FlowGram material components need consistent docs, runnable Story examples, API tables, and bilingual review steps. This skill gives Claude, Codex, and Claude Code a structured workflow for producing those assets.