Promote or graduate a project-local bundle to its upstream AIWG location or to a private corpus path.
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add jmagly/aiwg --skill promote --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Promote?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/jmagly-promote-aiwg)More formats (shields.io, HTML) on the badges page.
---
namespace: aiwg
name: promote
platforms: [all]
description: Promote or graduate a project-local bundle to its upstream AIWG location or to a private corpus path.
triggers:
- promote bundle
- promote project-local
- graduate project-local bundle
- graduate to upstream
- project-local bundle
---
# Promote Project-Local Bundle
Graduate a proven project-local bundle without losing its source provenance.
## Behavior
1. Identify the project-local bundle and its intended destination.
2. Preview the copy and registry transition:
```bash
aiwg promote <name> --dry-run
```
3. Promote to the declared upstream location or a private corpus:
```bash
aiwg promote <name> --to upstream
aiwg promote <name> --to corpus <path>
```
4. Use `--cleanup` only when the project-local source should be removed after
successful promotion. Use `--force` only after reviewing a destination
conflict.
## Safety
- Run `aiwg doctor` and a dry run before promotion.
- Promotion verifies the bundle manifest and destination before copying.
- Omit `--cleanup` to retain the project-local source.
## References
- @$AIWG_ROOT/src/cli/handlers/subcommands.ts — `promote` command handler
- @$AIWG_ROOT/src/extensions/project-local-promote.ts — promotion implementation
- @$AIWG_ROOT/agentic/code/addons/aiwg-utils/skills/steward-quickref/SKILL.md
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
