Build Claude Code Skills
Creating valid Claude or Codex skills can be hard when structure, metadata, and disclosure rules are unclear. This skill provides templates, checklists, and examples for building organized skills.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "Skill Builder" from https://skillstore.io/skills/ruvnet-skill-builder.md and its manifest at https://skillstore.io/api/skills/ruvnet-skill-builder/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 Builder". I need a skill that helps write release notes for product teams.
Expected outcome:
A structured release-notes skill outline with frontmatter guidance, quick start steps, resource suggestions, and a validation checklist.
Using "Skill Builder". Improve this skill so Claude loads less context.
Expected outcome:
A progressive disclosure rewrite that keeps core instructions in SKILL.md and moves long references into docs and resources.
Using "Skill Builder". Plan an advanced skill with scripts and templates.
Expected outcome:
A package plan covering script purpose, resource folders, usage steps, and testing notes without generating executable files directly.
This skill is a documentation-only tutorial (a single SKILL.md, 911 lines) that teaches authors how to build Claude Code skills. All 178 static findings were adjudicated as false positives: the flagged 'backtick execution' patterns are Markdown code fences and inline code spans; the 'path traversal' matches are illustrative relative Markdown links; the 'hidden file' matches all reference ~/.claude/skills/, the documented install location; and the 'hardcoded URLs' are documentation links and example.com placeholders. No executable scripts, no runtime commands, no network calls, and no prompt-injection or data-exfiltration intent were found.
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/ruvnet-skill-builder/audits/10?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/ruvnet-skill-builder?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/ruvnet-skill-builder?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/ruvnet-skill-builder/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/ruvnet-skill-builder.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>ruvnet. (2026). Skill Builder security audit report (audit version 10) [Author version unspecified]. Skillstore. https://skillstore.io/skills/ruvnet-skill-builder/audits/10@techreport{ruvnet-ruvnet-skill-builder-2026,
author = {ruvnet},
title = {Skill Builder security audit report (audit version 10)},
institution = {Skillstore},
year = {2026},
number = {10},
url = {https://skillstore.io/skills/ruvnet-skill-builder/audits/10},
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 Builder security audit report (audit version 10)"
version: "unspecified"
type: report
authors:
- name: "ruvnet"
date-released: "2026-07-20"
url: "https://skillstore.io/skills/ruvnet-skill-builder/audits/10"
identifiers:
- type: other
value: "skillstore:ruvnet-skill-builder:audit:10"
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
0xraduan-skill-builder
2026-08-21
dnyoussef-skill-builder
2026-08-21
ruvnet-skill-builder
2026-08-21
Build a clear skill for repeated local development, writing, or research tasks.
Define shared project skills with consistent metadata, folders, resources, and review checklists.
Draft skill instructions, examples, and validation steps before packaging a public skill.
Create a minimal skill for [workflow]. Include the required name and description fields. Add a short quick start and checklist.
Design a project skill for [team workflow]. Show the SKILL.md outline, folder layout, and resource files that should exist.
Review my current skill instructions for [goal]. Suggest frontmatter, disclosure levels, examples, and file references that improve usability.
Create a full skill plan for [domain]. Include templates, scripts, resources, tests, and publishing checks for Claude Code and Codex users.
Author
ruvnetLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
dbe0e719813583400773166a0621f8a9b8185c72
Maintenance freshness
7/20/2026
Usage
11 downloads · 380 views
File structure
📄 SKILL.md
Coordinate Multi-Agent Swarms
Coordinating many agents is hard when roles, topology, and task flow are unclear. This skill provides swarm patterns, hook workflows, and coordination practices for agentic-flow.
Orchestrate Advanced Multi-Agent Swarms
Complex projects need coordinated agents, dependencies, memory, and recovery. This skill provides reusable Claude Flow patterns for research, development, testing, analysis, and monitoring.
Build Adaptive ReasoningBank Agents
AI agents lose useful lessons when outcomes are not recorded. This skill shows how to capture experiences, learn patterns, and recommend better strategies.
Structure Software Delivery with SPARC
Complex software work often lacks a consistent path from requirements to completion. This skill applies SPARC phases, specialized modes, and coordinated development workflows.
Coordinate Advanced Claude Flow Agent Swarms
Complex projects require coordinated agents, durable context, and transparent decisions. This skill guides Claude Flow swarms through queen-led roles, consensus, memory, and sessions.
Build AgentDB Vector Search
Teams need fast semantic retrieval without designing vector storage from scratch. This skill guides AgentDB setup, embedding storage, similarity search, and RAG retrieval workflows.
Create Reusable Lark CLI Skills
by larksuite
Building reusable Lark automation requires consistent API research, permissions, and workflow documentation. This skill guides Claude and Codex through focused lark-cli skills for single APIs or multi-step workflows.
Improve Claude Code Components Systematically
by C0ntr0lledCha0s
Claude Code components can have vague descriptions, excessive permissions, weak triggers, or incomplete documentation. This skill turns quality findings into focused, reviewable improvements while preserving intended behavior.
Manage Context-Driven Development
by wshobson
AI-assisted projects lose consistency when context lives in scattered notes. This skill provides a structured Conductor workflow for product, stack, workflow, and track artifacts.
Orchestrate Multi-Model Skill Cascades
by DNYoussef
Complex AI work often needs several skills, models, and quality checks. This skill helps design cascades with routing, sandbox testing, swarm coordination, and memory.
Build Streamed Multi-Agent Workflows
by DNYoussef
Sequential AI workflows often lose context between steps. This skill defines stream-chain patterns that pass each result into the next task.
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.