Skip to content
Back to skills

private-vs-publishable-skill-audit

ASecurity

Audit a private skill, prompt pack, or assistant workflow before publishing it. Use when extracting public reusable method from client, product, team, or repository-specific agent instructions. Mark private vs mixed vs reusable content, rewrite the mixed layer, and gate release on decontextualization.

  • 16 stars
  • 0 votes
  • 0 copies
  • 12 views
  • Added June 15, 2026
ai-agentsgo

Works with

  • cli

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned June 15, 2026

npx -y skills add markoblogo/abvx-agent-skills --skill private-vs-publishable-skill-audit --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of private-vs-publishable-skill-audit?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for private-vs-publishable-skill-audit
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/markoblogo-private-vs-publishable-skill-audit/badge)](https://www.skillsdirectory.com/skills/markoblogo-private-vs-publishable-skill-audit)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: private-vs-publishable-skill-audit
description: Audit a private skill, prompt pack, or assistant workflow before publishing it. Use when extracting public reusable method from client, product, team, or repository-specific agent instructions. Mark private vs mixed vs reusable content, rewrite the mixed layer, and gate release on decontextualization.
license: MIT
metadata:
  abvx_status: experimental
  abvx_origin: original
---

# Private Vs Publishable Skill Audit

Audit a private skill pack before turning any part of it into a public release.

## Goal

Separate:

- private operating detail that must stay internal;
- mixed content that needs rewriting;
- reusable method that can be published.

## Workflow

1. **Inventory the source pack**
   - list skills, references, templates, examples, and policy notes;
   - note which files carry product, client, or repo-specific detail.
2. **Classify each item**
   - `private`: should not be published;
   - `mixed`: useful core, but still carries contextual leakage;
   - `reusable`: already abstract enough to publish.
3. **Check for leakage**
   - product names;
   - internal role names;
   - routes, paths, commands, and runbooks;
   - operational constraints that only make sense inside the private system;
   - examples that reveal the original environment.
4. **Rewrite the mixed layer**
   - remove names and internal identifiers;
   - convert narrow examples into generic ones;
   - preserve the method, not the original context.
5. **Run the publication gate**
   - after cleanup, ask whether the artifact still makes sense outside the source environment;
   - if not, keep rewriting or keep it private.
6. **Package the release set**
   - publish only the reusable artifacts;
   - keep the private source pack separate from the public one.

## Release Gate

An artifact is publishable only if both are true:

- it remains useful after private names, paths, and roles are removed;
- it does not expose constraints or operating detail that belong only to the private source.

## Final Report

Return the classified inventory, the release-safe set, the rewritten mixed items, and the reasons for anything left private.

Files in this skill

  • SKILL.md2.1 KB
  • SKILL_CARD.md1.4 KB
  • agents/openai.yaml252 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.