.claude/skills/publish-skill/SKILL.md
Creates a new GitHub repository for a Claude Code skill with proper README and directory structure. Use when you want to package and publish a skill so others can install it. Triggers on "publish skill", "publish this skill", "create skill repo", "package skill", "share this skill".
npx skillsauth add alexanderop/walkthrough publish-skillInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Package a Claude Code skill into a new GitHub repository with a polished README and proper directory structure — ready for others to install with npx skills add.
Collect everything needed to create the repo. The user may provide this upfront or you may need to ask.
Required information:
walkthrough, code-reviewer)If the user points to an existing skill directory (e.g., .claude/skills/my-skill/), read the skill.md to extract the description, usage triggers, and other metadata automatically. Only ask for what's missing.
If the user describes a skill concept without existing files, ask them to clarify the above before proceeding.
Create a new directory at /Users/alexanderopalic/Projects/mySkills/{skill-name}/ with this structure:
{skill-name}/
README.md
skills/
{skill-name}/
skill.md
references/ # only if the skill has reference files
*.md
examples/ # only if examples are provided
Copy skill files:
skills/{skill-name}/skill.md and any reference filesCreate a README.md following this template. Adapt section content based on the actual skill — do not include sections that don't apply.
# {Skill Name}
{One-line description of what the skill does.}
## What it does
{Describe what the skill produces or does:}
- **{Feature 1}** — description
- **{Feature 2}** — description
- **{Feature 3}** — description
## Usage
Trigger the skill with prompts like:
\`\`\`
{example prompt 1}
{example prompt 2}
{example prompt 3}
\`\`\`
{Brief description of what happens when triggered — the workflow steps.}
## Installation
### Quick install
\`\`\`bash
npx skills add https://github.com/alexanderop/{skill-name} --skill {skill-name}
\`\`\`
### Manual install
Copy the `skills/{skill-name}/` directory into your project's `.claude/skills/` folder:
\`\`\`
your-project/
.claude/
skills/
{skill-name}/
skill.md
\`\`\`
## Structure
\`\`\`
skills/{skill-name}/
skill.md # Main skill definition
references/ # Reference files (if any)
\`\`\`
{Brief description of what each key file does.}
README guidelines:
Run these commands sequentially:
cd /Users/alexanderopalic/Projects/mySkills/{skill-name}
git init
git add -A
git commit -m "Initial commit: {skill-name} skill"
gh repo create alexanderop/{skill-name} --public --source=. --push --description "{one-line description}"
If the user requested private visibility, use --private instead of --public.
Tell the user:
https://github.com/alexanderop/{skill-name}npx skills add https://github.com/alexanderop/{skill-name} --skill {skill-name}Before finishing, verify:
skill.md has proper frontmatter (name, description, allowed-tools, metadata)tools
Generates a self-contained HTML file with an interactive, clickable Mermaid diagram (flowchart or ER diagram) that explains how a codebase feature, flow, architecture, or database schema works. Designed for fast onboarding — each walkthrough is a visual mental model readable in under 2 minutes. TRIGGER this skill when ANY of these match: - The prompt starts with or contains "$walkthrough" (explicit trigger — always activate, even if no topic follows) - The user asks to "walk me through", "walkthrough", "trace the code path", "explain this flow", "show how X works", "how does X work step by step", "explain the architecture", "visualize the data model", "show the data structures", "show the relationships" - The user wants a visual/interactive explanation of code, flows, pipelines, or schemas When triggered, ALWAYS generate a walkthrough HTML file — never respond with just text. If "$walkthrough" is used with no topic, generate an overview walkthrough of the entire project.
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.