Skip to main content
skill CX Codex

skill-generalizer — Claude Code skill: publish a private skill

Turns a local skill into something you can publish: strips private paths, habits and credentials while keeping the reusable technique. Useful before a GitHub or marketplace release.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add hqhq1025/skill-optimizer --skill skill-generalizer -a claude-code
Open on GitHub

What skill-generalizer does

The skill walks a local skill through a release pass. It starts by reading the actual source skill and nearby repo files, then splits the reusable capability from personal implementation details. Private names, paths, hosts, credentials, account IDs and one-off project facts get redacted or replaced. After that the text is rewritten around general triggering conditions and portable steps.

Two references ship with it. references/publication-rubric.md covers a full release pass, redaction review and README rewrite; references/platform-compatibility.md is meant to be read before you claim support for Claude, Claude, Cursor, OpenCode, Gemini CLI or other coding agents. SKILL.md stays short — long rubrics, examples and scripts belong in bundled resources.

You need npx and GitHub access on the machine, otherwise npx skills add will not run. This is not the tool for tuning a skill to your own setup; that job belongs to skill-personalizer in the same repository.

What it helps with

  • publish a personal skill on GitHub without leaking private paths
  • swap internal hosts and account IDs for portable placeholders
  • rewrite a skill description around general triggering conditions
  • check target-agent compatibility before claiming support
  • package a README and marketplace copy that match the files that exist

Example prompts for the agent

  • Run skill-generalizer on my skill in ~/.claude/skills/deploy-helper — I want to open-source it
  • Audit SKILL.md and references/ for private paths and credentials before I publish
  • Build the public version and check compatibility with Claude and Cursor

How to install skill-generalizer

1Skills CLI (Vercel)

npx skills add hqhq1025/skill-optimizer --skill skill-generalizer -a claude-code

2Manually: put the files in place

~/.claude/skills/skill-generalizer/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/skill-generalizer/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about skill-generalizer

How do I install skill-generalizer in Claude Code?

Run npx skills add hqhq1025/skill-optimizer --skill skill-generalizer -a claude-code. The skill lands at ~/.claude/skills/skill-generalizer/SKILL.md.

What does skill-generalizer do?

It prepares a local skill for release: removes private paths, hosts, credentials and personal habits, then rewrites the text around general triggering conditions.

How is it different from skill-personalizer?

skill-generalizer is for publishing a skill outward, while skill-personalizer tunes a skill for your own machine.

Source text

SKILL.md · MIT
---
name: skill-generalizer
description: Use when turning local, private, or personal Agent Skills into publishable skills for GitHub, marketplaces, teams, or public sharing, especially when private paths, personal habits, credentials, internal hosts, or user-specific context must be removed.
---

# Skill Generalizer

## Overview

Convert a working local skill into a clean public artifact. The goal is to preserve the reusable technique while removing private context, personal assumptions, and machine-specific setup.

## When To Use

- A user wants to publish, share, promote, open-source, or package a local skill.
- A skill was born from personal workflows, private repos, local paths, transcripts, remote hosts, or team conventions.
- The output needs to be useful to strangers without leaking the author's environment.

Do not use for tuning a skill only for the user's own machine; use `skill-personalizer` for that.

## Workflow

1. Inspect the actual source skill and nearby repo files before judging.
2. If the source skill quality is unclear, run the audit checks from `skill-personalizer` first.
3. Separate the reusable capability from personal implementation details.
4. Redact or replace private names, paths, hosts, credentials, account IDs, transcripts, and one-off project facts.
5. Rewrite the skill around general triggering conditions, portable workflows, and bounded assumptions.
6. Keep `SKILL.md` concise; move long rubrics, examples, or scripts into bundled resources.
7. Check target-agent compatibility before writing install instructions or support claims.
8. Produce publication-ready packaging and honest promotion copy only when requested.
9. Verify frontmatter, file layout, install path, and at least one realistic usage prompt.

## Public Release Rules

- Frontmatter `description` should describe when to use the skill, not summarize its workflow.
- Public examples must be generic or explicitly sanitized.
- Claims in README or marketplace copy must match files that actually exist.
- Prefer portable commands and path placeholders over the author's home directory or private aliases.
- If a personal detail is essential, turn it into a configurable variable with setup guidance.

## References

Read [publication-rubric.md](references/publication-rubric.md) when doing a full release pass, redaction review, README rewrite, or promotional packaging.

Read [platform-compatibility.md](references/platform-compatibility.md) before claiming support for Codex, Claude Code, Cursor, OpenCode, Gemini CLI, or other coding agents.

© hqhq1025 · MIT · hqhq1025/skill-optimizer

Similar skills

All skills for Agent setup: memory, context, orchestration →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor