Skip to content
Back to skills

publish-skill

ASecurity

> Use when turning a personal agent skill into an open-source, distributable one. Runs a PII audit, generalizes personal details, checks licence compatibility, reviews cross-platform adapters and walks through packaging. **Invoke:** `/publish-skill`

  • 327 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 3, 2026
ai-agentsbash

Works with

  • claude code

Security analysis

A100/100

Pro scans all 21 files and shows the line behind each finding

Scanned October 1, 2026

npx -y skills add Aperivue/medsci-skills --skill skills --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of publish-skill?

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

Security grade badge for publish-skill
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aperivue-publish-skill-medsci-skills/badge)](https://www.skillsdirectory.com/skills/aperivue-publish-skill-medsci-skills)

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
<!-- AUTO-GENERATED from skills/publish-skill/SKILL.md by scripts/gen_skill_docs.py. Do not edit by hand. -->

# publish-skill

> Use when turning a personal agent skill into an open-source, distributable one. Runs a PII audit, generalizes personal details, checks licence compatibility, reviews cross-platform adapters and walks through packaging.

**Invoke:** `/publish-skill`

## When to use

`publish-skill` activates on requests such as: publish skill, distribute skill, open-source skill, package skill, universalize skill.

## Quality Card

**Purpose** — Harden a personal skill for open-source release through a PII audit, generalization, and license/portability checks.

**Safety boundaries**

- Publication is gated on a passing PII audit; the blocklist is conservative and not weakened to pass.
- Personal paths, names, and document metadata are scrubbed before release.

**Known limitations**

- The audit catches known PII patterns; novel identifiers still need human review.
- Generalization preserves behavior but a maintainer should re-read the result.

**Validation**

- `bash scripts/audit_skill.sh <skill-dir>`
- `bash scripts/validate_skills.sh`

**Evidence** — `bundled_script`

## Bundled resources

**References** (`skills/publish-skill/references/`):

- `classroom-distribution.md`
- `license-compatibility-matrix.md`
- `pii-patterns.md`

**Scripts** (`skills/publish-skill/scripts/`):

- `audit_skill.sh`

## Source

Canonical definition: [`skills/publish-skill/SKILL.md`](../../skills/publish-skill/SKILL.md)

---

*Part of [MedSci Skills](../../README.md) — Claude Code skills for the medical research lifecycle. This page is generated from the skill's `SKILL.md`; edit that file and re-run `scripts/gen_skill_docs.py`.*

Files in this skill

  • AUDIT.md3.9 KB
  • README.md10.6 KB
  • academic-aio.md3.1 KB
  • add-journal.md1.7 KB
  • analyze-stats.md2.3 KB
  • architecture-zoo.md3.7 KB
  • author-strategy.md2 KB
  • batch-cohort.md1.8 KB
  • calc-sample-size.md2 KB
  • check-reporting.md3.9 KB
  • clean-data.md1.9 KB
  • contribute.md2.7 KB
  • cross-national.md1.6 KB
  • define-variables.md2 KB
  • deidentify.md2.1 KB
  • design-ai-benchmarking.md2.4 KB
  • design-study.md2 KB
  • explainability.md3.1 KB
  • fill-icmje-coi.md2.2 KB
  • fill-protocol.md2.1 KB

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.