plugin-creator

von openai

Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, and baseline placeholders you can…

npx skills add https://github.com/openai/skills --skill plugin-creator

Plugin Creator

Quick Start

  1. Run the scaffold script:
  # Plugin names are normalized to lower-case hyphen-case and must be <= 64 chars.
  # The generated folder and plugin.json name are always the same.
# Run from repo root (or replace .agents/... with the absolute path to this SKILL).
# By default creates in <repo_root>/plugins/<plugin-name>.
python3 .agents/skills/plugin-creator/scripts/create_basic_plugin.py <plugin-name>
  1. Open <plugin-path>/.codex-plugin/plugin.json and replace [TODO: ...] placeholders.

  2. Generate or update the repo marketplace entry when the plugin should appear in Codex UI ordering:

# marketplace.json always lives at <repo-root>/.agents/plugins/marketplace.json
python3 .agents/skills/plugin-creator/scripts/create_basic_plugin.py my-plugin --with-marketplace

For a home-local plugin, treat <home> as the root and use:

python3 .agents/skills/plugin-creator/scripts/create_basic_plugin.py my-plugin \
  --path ~/plugins \
  --marketplace-path ~/.agents/plugins/marketplace.json \
  --with-marketplace
  1. Generate/adjust optional companion folders as needed:
python3 .agents/skills/plugin-creator/scripts/create_basic_plugin.py my-plugin --path <parent-plugin-directory> \
  --with-skills --with-hooks --with-scripts --with-assets --with-mcp --with-apps --with-marketplace

<parent-plugin-directory> is the directory where the plugin folder <plugin-name> will be created (for example ~/code/plugins).

What this skill creates

  • If the user has not made the plugin location explicit, ask whether they want a repo-local plugin or a home-local plugin before generating marketplace entries.
  • Creates plugin root at /<parent-plugin-directory>/<plugin-name>/.
  • Always creates /<parent-plugin-directory>/<plugin-name>/.codex-plugin/plugin.json.
  • Fills the manifest with the full schema shape, placeholder values, and the complete interface section.
  • Creates or updates <repo-root>/.agents/plugins/marketplace.json when --with-marketplace is set.
    • If the marketplace file does not exist yet, seed top-level name plus interface.displayName placeholders before adding the first plugin entry.
  • <plugin-name> is normalized using skill-creator naming rules:
    • My Pluginmy-plugin
    • My--Pluginmy-plugin
    • underscores, spaces, and punctuation are converted to -
    • result is lower-case hyphen-delimited with consecutive hyphens collapsed
  • Supports optional creation of:
    • skills/
    • hooks/
    • scripts/
    • assets/
    • .mcp.json
    • .app.json

Marketplace workflow

  • marketplace.json always lives at <repo-root>/.agents/plugins/marketplace.json.
  • For a home-local plugin, use the same convention with <home> as the root: ~/.agents/plugins/marketplace.json plus ./plugins/<plugin-name>.
  • Marketplace root metadata supports top-level name plus optional interface.displayName.
  • Treat plugin order in plugins[] as render order in Codex. Append new entries unless a user explicitly asks to reorder the list.
  • displayName belongs inside the marketplace interface object, not individual plugins[] entries.
  • Each generated marketplace entry must include all of:
    • policy.installation
    • policy.authentication
    • category
  • Default new entries to:
    • policy.installation: "AVAILABLE"
    • policy.authentication: "ON_INSTALL"
  • Override defaults only when the user explicitly specifies another allowed value.
  • Allowed policy.installation values:
    • NOT_AVAILABLE
    • AVAILABLE
    • INSTALLED_BY_DEFAULT
  • Allowed policy.authentication values:
    • ON_INSTALL
    • ON_USE
  • Treat policy.products as an override. Omit it unless the user explicitly requests product gating.
  • The generated plugin entry shape is:
{
  "name": "plugin-name",
  "source": {
    "source": "local",
    "path": "./plugins/plugin-name"
  },
  "policy": {
    "installation": "AVAILABLE",
    "authentication": "ON_INSTALL"
  },
  "category": "Productivity"
}
  • Use --force only when intentionally replacing an existing marketplace entry for the same plugin name.

  • If <repo-root>/.agents/plugins/marketplace.json does not exist yet, create it with top-level "name", an "interface" object containing "displayName", and a plugins array, then add the new entry.

  • For a brand-new marketplace file, the root object should look like:

{
  "name": "[TODO: marketplace-name]",
  "interface": {
    "displayName": "[TODO: Marketplace Display Name]"
  },
  "plugins": [
    {
      "name": "plugin-name",
      "source": {
        "source": "local",
        "path": "./plugins/plugin-name"
      },
      "policy": {
        "installation": "AVAILABLE",
        "authentication": "ON_INSTALL"
      },
      "category": "Productivity"
    }
  ]
}

Required behavior

  • Outer folder name and plugin.json "name" are always the same normalized plugin name.
  • Do not remove required structure; keep .codex-plugin/plugin.json present.
  • Keep manifest values as placeholders until a human or follow-up step explicitly fills them.
  • If creating files inside an existing plugin path, use --force only when overwrite is intentional.
  • Preserve any existing marketplace interface.displayName.
  • When generating marketplace entries, always write policy.installation, policy.authentication, and category even if their values are defaults.
  • Add policy.products only when the user explicitly asks for that override.
  • Keep marketplace source.path relative to repo root as ./plugins/<plugin-name>.

Reference to exact spec sample

For the exact canonical sample JSON for both plugin manifests and marketplace entries, use:

  • references/plugin-json-spec.md

Validation

After editing SKILL.md, run:

python3 <path-to-skill-creator>/scripts/quick_validate.py .agents/skills/plugin-creator

Mehr Skills von openai

user-context
openai
Laden oder verwalten Sie die dauerhaften Source-Routing-Einstellungen, die Onboarding-Logik, den Setup-Fortschritt und das Semantic-Layer-Register des Data Analytics-Plugins.
official
notion-research-documentation
openai
Notion-Inhalte recherchieren und in strukturierte Kurzberichte, Reports oder Vergleiche mit Quellenangaben synthetisieren. Notion-Seiten mit gezielten Suchanfragen durchsuchen und abrufen, dann Ergebnisse nach Themen ordnen mit Inline-Quellenangaben und einem Referenzabschnitt. Wählen Sie aus vier Ausgabeformaten (Kurzbericht, Forschungszusammenfassung, Vergleich, umfassender Report) basierend auf Umfang und Benutzerziel. Erstellen und aktualisieren Sie Notion-Seiten mit integrierten Vorlagen; verlinken Sie Quellen direkt und verfolgen Sie Änderungen, sobald neue Informationen eintreffen...
official
rcsb-pdb-skill
openai
Übermitteln Sie kompakte RCSB PDB-Anfragen für Kernmetadaten, Search API-Abfragen und FASTA-Downloads. Verwenden Sie dies, wenn ein Benutzer prägnante RCSB-Zusammenfassungen wünscht; speichern Sie rohes JSON oder…
official
pdf
openai
PDF-Lesen, -Erstellung und -Validierung mit visueller Darstellung und programmatischer Generierung. Rendern von PDF-Seiten in PNG zur visuellen Überprüfung von Layout, Abständen und Typografie vor der Auslieferung mit Poppler (pdftoppm). Programmatisches Erstellen von PDFs mit reportlab für zuverlässige Formatierung; Extrahieren von Text und Metadaten mit pdfplumber oder pypdf. Durchsetzung von Qualitätsstandards: kein abgeschnittener Text, überlappende Elemente, defekte Tabellen oder Rendering-Artefakte; nur ASCII-Bindestriche, menschenlesbare Zitate. Verwendung...
official
test-coverage-improver
openai
Improve test coverage in the OpenAI Agents JS monorepo: run `pnpm test:coverage`, inspect coverage artifacts, identify low-coverage files and branches, propose…
official
playwright
openai
Terminalgesteuerte Browserautomatisierung mit Element-Snapshots und interaktiven UI-Workflows. Funktioniert über ein playwright-cli-Wrapper-Skript (erfordert npx); unterstützt Headless- und Headed-Modi für visuelles Debugging. Kern-Workflow: Seite öffnen, Snapshot für stabile Elementreferenzen erstellen, mit Referenzen interagieren, nach Navigation oder DOM-Änderungen erneut snapshot erstellen. Beinhaltet Formularausfüllen, Klicken, Tippen, Multi-Tab-Verwaltung, Screenshot/PDF-Erfassung und Trace-Aufzeichnung für Flow-Debugging. Element-Referenzen (z. B. e3, e15)...
official
ukb-topmed-phewas-skill
openai
Rufe kompakte UKB-TOPMed-PheWAS-Zusammenfassungen für einzelne Varianten ab, indem du rsID, GRCh37 oder GRCh38 als Eingabe akzeptierst und zur erforderlichen GRCh38-Abfrage auflöst. Verwende, wenn ein…
official
code-review-context
openai
Für das Modell sichtbarer Kontext
official