Git commands for aitasks/aiplans directories — use ./ait git instead of plain git
Scanned 9/2/2026
Install to Claude Code
npx -y skills add majiayu000/claude-skill-registry --skill ait-git --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Ait Git?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/majiayu000-ait-git)More formats (shields.io, HTML) on the badges page.
---
name: ait-git
description: Git commands for aitasks/aiplans directories — use ./ait git instead of plain git
user-invocable: false
---
## Git Operations on Task/Plan Files
When running git commands that operate on files in `aitasks/` or `aiplans/` directories, **always use `./ait git` instead of plain `git`**. This ensures correct branch targeting when task data lives on a separate `aitask-data` branch.
### Usage
```bash
./ait git add aitasks/t42_foo.md
./ait git commit -m "ait: Update task t42"
./ait git push
./ait git status
```
### How it works
- If `.aitask-data/` worktree exists (branch mode): `ait git` routes to `git -C .aitask-data`
- If no worktree (legacy mode): `ait git` passes through to plain `git`
### When to use
- Any `git add`, `git commit`, `git push`, `git rm` involving files under `aitasks/` or `aiplans/`
- When committing task metadata changes (status, assignment, etc.)
- When archiving or creating task files
### When NOT to use
- For code-related git operations (implementation commits go on the main branch as normal)
- For `git log`, `git diff` on code files
- The aitask shell scripts already use `task_git()` internally — no need to wrap script calls
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.
**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.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.