package-all-plugins
Batch package every plugin in the workspace in a single release-prep operation
Best use case
package-all-plugins is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
It is a strong fit for teams already working in Codex.
Batch package every plugin in the workspace in a single release-prep operation
Teams using package-all-plugins should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/package-all-plugins/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How package-all-plugins Compares
| Feature / Agent | package-all-plugins | Standard Approach |
|---|---|---|
| Platform Support | Codex | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Batch package every plugin in the workspace in a single release-prep operation
Which AI agents support this skill?
This skill is designed for Codex.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
SKILL.md Source
# Package All Plugins You run `package-plugin` for every plugin in the workspace in a single batch operation. Used for release preparation to generate all plugin packages at once. ## Triggers Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description): - "package everything for the release" → batch package all plugins - "build all plugin archives" → batch package all plugins - "release prep — package the plugins" → batch package all plugins - "bundle all the plugins before tagging" → batch package all plugins ## Trigger Patterns Reference | Pattern | Example | Action | |---------|---------|--------| | Package all | "package all plugins" | Run `aiwg package-all-plugins` | | Bundle all | "bundle all plugins" | Run `aiwg package-all-plugins` | | Publish all | "publish all plugins" | Run `aiwg package-all-plugins --publish` | | Batch package | "batch package plugins" | Run `aiwg package-all-plugins` | | Dry run all | "validate all plugins before packaging" | Run `aiwg package-all-plugins --dry-run` | | Skip failures | "package all, skip broken ones" | Run `aiwg package-all-plugins --continue-on-error` | ## Behavior When triggered: 1. **Extract intent**: - Should packages be published after creation, or archived locally only? - Should the batch abort on first failure, or continue and report all failures? - Is this a dry run (validate only)? 2. **Run the appropriate command**: ```bash # Package all plugins (archive only, no publish) aiwg package-all-plugins # Validate all plugins — no archives created aiwg package-all-plugins --dry-run # Package and publish all to marketplace aiwg package-all-plugins --publish # Continue on individual failures, report all at end aiwg package-all-plugins --continue-on-error # Specify output directory for all archives aiwg package-all-plugins --output dist/plugins/ # Bump all versions before packaging aiwg package-all-plugins --bump patch ``` 3. **Report the result** — list each plugin with its status (packaged, failed, skipped), total count, and any errors. ## Output Format ``` Packaging all plugins (4)... sdlc ✓ packaged dist/plugins/sdlc-2026.4.0.aiwg-plugin.tar.gz voice ✓ packaged dist/plugins/voice-2026.4.0.aiwg-plugin.tar.gz marketing ✓ packaged dist/plugins/marketing-2026.4.0.aiwg-plugin.tar.gz utils ✗ failed validate-metadata: 1 error in soul-blend/SKILL.md Packaged: 3 / 4 Failed: 1 (utils) ``` ## Failure Behavior By default (`--abort-on-error`), the batch stops at the first failure and reports the error. Use `--continue-on-error` to package all plugins and collect all errors for a single remediation pass. ## Relationship to `package-plugin` `package-all-plugins` is a thin loop over `package-plugin`. Each plugin runs through the same validation and packaging logic as a single `package-plugin` call. Flags like `--dry-run`, `--publish`, and `--bump` are forwarded to each plugin invocation. ## Examples ### Example 1: Release preparation **User**: "Package all plugins for the release" **Extraction**: Full batch, no publish **Action**: ```bash aiwg package-all-plugins ``` **Response**: "Packaged 4/4 plugins. Archives in dist/plugins/: sdlc-2026.4.0, voice-2026.4.0, marketing-2026.4.0, utils-2026.4.0. All metadata validation passed." ### Example 2: Validate everything before tagging **User**: "Validate all plugins before I tag the release" **Extraction**: Dry-run requested **Action**: ```bash aiwg package-all-plugins --dry-run ``` **Response**: "Dry run: 4 plugins validated. 3 passed. 1 error: utils plugin — soul-blend/SKILL.md missing required field `id`. Fix and re-run." ### Example 3: Package and publish in one step **User**: "Package and publish everything for the release" **Extraction**: Batch package and publish **Action**: ```bash aiwg package-all-plugins --publish ``` **Response**: "Packaged and published 4/4 plugins to the AIWG marketplace. sdlc, voice, marketing, utils — all at v2026.4.0." ### Example 4: Continue through failures **User**: "Package all plugins but don't stop if one fails — I want to see all the errors at once" **Extraction**: Batch with `--continue-on-error` **Action**: ```bash aiwg package-all-plugins --continue-on-error ``` **Response**: "Packaged 3/4 plugins. 1 failure: utils — validate-metadata error in soul-blend/SKILL.md line 4 (missing `id`). All other packages created in dist/plugins/." ## References - @$AIWG_ROOT/src/cli/handlers/utilities.ts — Command handler - @$AIWG_ROOT/docs/cli-reference.md — CLI reference - @$AIWG_ROOT/agentic/code/addons/aiwg-utils/skills/package-plugin/SKILL.md — Single-plugin packaging
Related Skills
skill-packager
Package skills into uploadable ZIP files for Claude. Use after skill-builder/skill-enhancer to create final upload package.
packages
Manage remotely installed AIWG packages sourced from Git repositories via list, info, and remove subcommands
package-plugin
Bundle a single plugin into a distributable marketplace archive, validating metadata and optionally publishing
aiwg-orchestrate
Route structured artifact work to AIWG workflows via MCP with zero parent context cost
venv-manager
Create, manage, and validate Python virtual environments. Use for project isolation and dependency management.
pytest-runner
Execute Python tests with pytest, supporting fixtures, markers, coverage, and parallel execution. Use for Python test automation.
vitest-runner
Execute JavaScript/TypeScript tests with Vitest, supporting coverage, watch mode, and parallel execution. Use for JS/TS test automation.
eslint-checker
Run ESLint for JavaScript/TypeScript code quality and style enforcement. Use for static analysis and auto-fixing.
repo-analyzer
Analyze GitHub repositories for structure, documentation, dependencies, and contribution patterns. Use for codebase understanding and health assessment.
pr-reviewer
Review GitHub pull requests for code quality, security, and best practices. Use for automated PR feedback and approval workflows.
YouTube Acquisition
yt-dlp patterns for acquiring content from YouTube and video platforms
Quality Filtering
Accept/reject logic and quality scoring heuristics for media content