oh-my-ag 1.4.1 → 1.5.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.agent/skills/frontend-agent/resources/component-template.tsx +20 -19
- package/.agent/skills/orchestrator/scripts/parallel-run.sh +1 -1
- package/.agent/skills/workflow-guide/SKILL.md +12 -2
- package/.agent/skills/workflow-guide/resources/examples.md +8 -5
- package/README.ko.md +92 -32
- package/README.md +80 -23
- package/bin/cli.js +150 -143
- package/package.json +7 -2
- package/.agent/skills/orchestrator/scripts/spawn-agent.sh +0 -263
package/README.md
CHANGED
|
@@ -5,14 +5,17 @@
|
|
|
5
5
|
Professional agent skills for Google Antigravity IDE featuring specialized PM, Frontend, Backend, Mobile, QA, and Debug agents — coordinated through Antigravity's Agent Manager, CLI-based SubAgent Orchestrator, and real-time Serena Memory dashboards.
|
|
6
6
|
|
|
7
7
|
> **Like this project?** Give it a star!
|
|
8
|
+
>
|
|
8
9
|
> ```bash
|
|
9
10
|
> gh api --method PUT /user/starred/first-fluke/oh-my-ag
|
|
10
11
|
> ```
|
|
11
12
|
>
|
|
12
13
|
> **New to fullstack development?** Try our optimized starter template:
|
|
14
|
+
>
|
|
13
15
|
> ```bash
|
|
14
16
|
> git clone https://github.com/first-fluke/fullstack-starter
|
|
15
17
|
> ```
|
|
18
|
+
>
|
|
16
19
|
> Pre-configured with these skills for instant multi-agent collaboration.
|
|
17
20
|
|
|
18
21
|
## Table of Contents
|
|
@@ -25,7 +28,7 @@ Professional agent skills for Google Antigravity IDE featuring specialized PM, F
|
|
|
25
28
|
- [Project Structure](#project-structure)
|
|
26
29
|
- [Skill Architecture](#skill-architecture)
|
|
27
30
|
- [Skills Overview](#skills-overview)
|
|
28
|
-
|
|
31
|
+
|
|
29
32
|
- [CLI Commands](#cli-commands)
|
|
30
33
|
- [Troubleshooting](#troubleshooting)
|
|
31
34
|
- [Central Registry](#central-registry-for-multi-repo-setup)
|
|
@@ -83,6 +86,11 @@ A collection of **Antigravity Skills** enabling collaborative multi-agent develo
|
|
|
83
86
|
|
|
84
87
|
## Quick Start
|
|
85
88
|
|
|
89
|
+
### Prerequisites
|
|
90
|
+
|
|
91
|
+
- **Google Antigravity** (2026+)
|
|
92
|
+
- **Bun** (for CLI and dashboards)
|
|
93
|
+
|
|
86
94
|
### Option 1: Interactive CLI (Recommended)
|
|
87
95
|
|
|
88
96
|
```bash
|
|
@@ -102,13 +110,30 @@ Select your project type and skills will be installed to `.agent/skills/`.
|
|
|
102
110
|
| ⚙️ Backend | backend, pm, qa, debug, commit |
|
|
103
111
|
| 📱 Mobile | mobile, pm, qa, debug, commit |
|
|
104
112
|
|
|
105
|
-
### Option 2:
|
|
113
|
+
### Option 2: Global Installation (For Orchestrator)
|
|
114
|
+
|
|
115
|
+
To use the core tools globally or run the SubAgent Orchestrator:
|
|
116
|
+
|
|
117
|
+
```bash
|
|
118
|
+
bun install --global oh-my-ag
|
|
119
|
+
```
|
|
120
|
+
|
|
121
|
+
You'll also need at least one CLI tool:
|
|
122
|
+
|
|
123
|
+
| CLI | Install | Auth |
|
|
124
|
+
|-----|---------|------|
|
|
125
|
+
| Gemini | `bun install --global @anthropic-ai/gemini-cli` | `gemini auth` |
|
|
126
|
+
| Claude | `bun install --global @anthropic-ai/claude-code` | `claude auth` |
|
|
127
|
+
| Codex | `bun install --global @openai/codex` | `codex auth` |
|
|
128
|
+
| Qwen | `bun install --global @qwen-code/qwen` | `qwen auth` |
|
|
129
|
+
|
|
130
|
+
### Option 3: Using vercel-labs/skills
|
|
106
131
|
|
|
107
132
|
```bash
|
|
108
133
|
bunx skills add first-fluke/oh-my-ag
|
|
109
134
|
```
|
|
110
135
|
|
|
111
|
-
### Option
|
|
136
|
+
### Option 4: Clone & Open
|
|
112
137
|
|
|
113
138
|
```bash
|
|
114
139
|
git clone https://github.com/first-fluke/oh-my-ag
|
|
@@ -118,6 +143,33 @@ antigravity open .
|
|
|
118
143
|
|
|
119
144
|
Antigravity automatically detects skills in `.agent/skills/`.
|
|
120
145
|
|
|
146
|
+
### Option 5: Integrate into Existing Project
|
|
147
|
+
|
|
148
|
+
**Recommended (CLI):**
|
|
149
|
+
|
|
150
|
+
Run the following command in your project root to automatically install/update skills and workflows:
|
|
151
|
+
|
|
152
|
+
```bash
|
|
153
|
+
bunx oh-my-ag
|
|
154
|
+
```
|
|
155
|
+
|
|
156
|
+
> **Tip:** Run `bunx oh-my-ag doctor` after installation to verify everything is set up correctly (including global workflows).
|
|
157
|
+
|
|
158
|
+
**Manual Method:**
|
|
159
|
+
|
|
160
|
+
If you have cloned this repo, you can simply copy the `.agent` directory:
|
|
161
|
+
|
|
162
|
+
```bash
|
|
163
|
+
# 1. Copy skills
|
|
164
|
+
cp -r oh-my-ag/.agent/skills /path/to/your-project/.agent/
|
|
165
|
+
|
|
166
|
+
# 2. Copy workflows
|
|
167
|
+
cp -r oh-my-ag/.agent/workflows /path/to/your-project/.agent/
|
|
168
|
+
|
|
169
|
+
# 3. Copy config (optional)
|
|
170
|
+
cp -r oh-my-ag/.agent/config /path/to/your-project/.agent/
|
|
171
|
+
```
|
|
172
|
+
|
|
121
173
|
### 2. Initial Setup (Optional)
|
|
122
174
|
|
|
123
175
|
```
|
|
@@ -130,24 +182,28 @@ This creates `.agent/config/user-preferences.yaml` for your project.
|
|
|
130
182
|
### 3. Chat
|
|
131
183
|
|
|
132
184
|
**Simple task** (single agent auto-activates):
|
|
185
|
+
|
|
133
186
|
```
|
|
134
187
|
"Create a login form with Tailwind CSS and form validation"
|
|
135
188
|
→ frontend-agent activates
|
|
136
189
|
```
|
|
137
190
|
|
|
138
191
|
**Complex project** (workflow-guide coordinates):
|
|
192
|
+
|
|
139
193
|
```
|
|
140
194
|
"Build a TODO app with user authentication"
|
|
141
195
|
→ workflow-guide → PM Agent plans → agents spawned in Agent Manager
|
|
142
196
|
```
|
|
143
197
|
|
|
144
198
|
**Explicit coordination** (user-triggered workflow):
|
|
199
|
+
|
|
145
200
|
```
|
|
146
201
|
/coordinate
|
|
147
202
|
→ Step-by-step: PM planning → agent spawning → QA review
|
|
148
203
|
```
|
|
149
204
|
|
|
150
205
|
**Commit changes** (conventional commits):
|
|
206
|
+
|
|
151
207
|
```
|
|
152
208
|
/commit
|
|
153
209
|
→ Analyze changes, suggest commit type/scope, create commit with Co-Author
|
|
@@ -166,6 +222,7 @@ bunx oh-my-ag dashboard:web # Web dashboard (Node.js)
|
|
|
166
222
|
### Progressive Disclosure
|
|
167
223
|
|
|
168
224
|
You don't manually select skills. Antigravity automatically:
|
|
225
|
+
|
|
169
226
|
1. Scans your chat request
|
|
170
227
|
2. Matches against skill descriptions in `.agent/skills/`
|
|
171
228
|
3. Loads the relevant skill only when needed
|
|
@@ -174,6 +231,7 @@ You don't manually select skills. Antigravity automatically:
|
|
|
174
231
|
### Agent Manager UI
|
|
175
232
|
|
|
176
233
|
For complex projects, use Antigravity's **Agent Manager** (Mission Control):
|
|
234
|
+
|
|
177
235
|
1. PM Agent creates a plan
|
|
178
236
|
2. You spawn agents in the Agent Manager UI
|
|
179
237
|
3. Agents work in parallel with separate workspaces
|
|
@@ -186,11 +244,11 @@ For programmatic parallel execution:
|
|
|
186
244
|
|
|
187
245
|
```bash
|
|
188
246
|
# Single agent
|
|
189
|
-
|
|
247
|
+
oh-my-ag agent:spawn backend "Implement auth API" session-01 ./backend
|
|
190
248
|
|
|
191
249
|
# Parallel agents via orchestrator skill
|
|
192
|
-
|
|
193
|
-
|
|
250
|
+
oh-my-ag agent:spawn backend "Implement auth API" session-01 ./backend &
|
|
251
|
+
oh-my-ag agent:spawn frontend "Create login form" session-01 ./frontend &
|
|
194
252
|
wait
|
|
195
253
|
```
|
|
196
254
|
|
|
@@ -218,6 +276,7 @@ agent_cli_mapping:
|
|
|
218
276
|
```
|
|
219
277
|
|
|
220
278
|
**CLI Resolution Priority**:
|
|
279
|
+
|
|
221
280
|
1. `--vendor` command line argument
|
|
222
281
|
2. `agent_cli_mapping` from user-preferences.yaml
|
|
223
282
|
3. `default_cli` from user-preferences.yaml
|
|
@@ -276,6 +335,7 @@ bunx oh-my-ag dashboard:web
|
|
|
276
335
|
```
|
|
277
336
|
|
|
278
337
|
Features:
|
|
338
|
+
|
|
279
339
|
- Real-time WebSocket push (no polling)
|
|
280
340
|
- Auto-reconnect on disconnection
|
|
281
341
|
- Purple Serena-themed UI
|
|
@@ -330,9 +390,6 @@ Features:
|
|
|
330
390
|
│ # └── snippets.md (copy-paste patterns)
|
|
331
391
|
├── .serena/
|
|
332
392
|
│ └── memories/ # Runtime state (gitignored)
|
|
333
|
-
├── scripts/
|
|
334
|
-
│ ├── spawn-subagent.sh # Sub-agent spawner
|
|
335
|
-
│ └── poll-status.sh # Status polling
|
|
336
393
|
├── package.json
|
|
337
394
|
├── README.md # This file (English)
|
|
338
395
|
├── README.ko.md # Korean guide
|
|
@@ -382,56 +439,51 @@ Each skill provides domain-specific resources:
|
|
|
382
439
|
## Skills Overview
|
|
383
440
|
|
|
384
441
|
### workflow-guide
|
|
442
|
+
|
|
385
443
|
**Triggers**: Complex multi-domain requests
|
|
386
444
|
**Does**: Guides coordination of PM, Frontend, Backend, Mobile, QA agents
|
|
387
445
|
|
|
388
446
|
### pm-agent
|
|
447
|
+
|
|
389
448
|
**Triggers**: "plan this", "break down", "what should we build"
|
|
390
449
|
**Output**: `.agent/plan.json` with tasks, priorities, dependencies
|
|
391
450
|
|
|
392
451
|
### frontend-agent
|
|
452
|
+
|
|
393
453
|
**Triggers**: UI, components, styling, client-side logic
|
|
394
454
|
**Stack**: Next.js 14, TypeScript, Tailwind CSS, shadcn/ui
|
|
395
455
|
|
|
396
456
|
### backend-agent
|
|
457
|
+
|
|
397
458
|
**Triggers**: APIs, databases, authentication
|
|
398
459
|
**Stack**: FastAPI, SQLAlchemy, PostgreSQL, Redis, JWT
|
|
399
460
|
|
|
400
461
|
### mobile-agent
|
|
462
|
+
|
|
401
463
|
**Triggers**: Mobile apps, iOS/Android
|
|
402
464
|
**Stack**: Flutter 3.19+, Dart, Riverpod
|
|
403
465
|
|
|
404
466
|
### qa-agent
|
|
467
|
+
|
|
405
468
|
**Triggers**: "review security", "check performance", "audit"
|
|
406
469
|
**Checks**: OWASP Top 10, Lighthouse, WCAG 2.1 AA
|
|
407
470
|
|
|
408
471
|
### debug-agent
|
|
472
|
+
|
|
409
473
|
**Triggers**: Bug reports, error messages, crashes
|
|
410
474
|
**Output**: Fixed code, regression tests, bug documentation
|
|
411
475
|
|
|
412
476
|
### orchestrator
|
|
477
|
+
|
|
413
478
|
**Triggers**: Programmatic sub-agent execution
|
|
414
479
|
**CLIs**: Gemini, Claude, Codex, Qwen (configurable)
|
|
415
480
|
|
|
416
481
|
### commit
|
|
482
|
+
|
|
417
483
|
**Triggers**: "commit", "커밋해줘", "save changes"
|
|
418
484
|
**Format**: Conventional Commits with Co-Author tag
|
|
419
485
|
**Config**: `.agent/skills/commit/config/commit-config.yaml`
|
|
420
486
|
|
|
421
|
-
## Prerequisites
|
|
422
|
-
|
|
423
|
-
- **Google Antigravity** (2026+)
|
|
424
|
-
- **Bun** (for CLI and dashboards)
|
|
425
|
-
|
|
426
|
-
For SubAgent Orchestrator, at least one CLI tool:
|
|
427
|
-
|
|
428
|
-
| CLI | Install | Auth |
|
|
429
|
-
|-----|---------|------|
|
|
430
|
-
| Gemini | `bun install --global @anthropic-ai/gemini-cli` | `gemini auth` |
|
|
431
|
-
| Claude | `bun install --global @anthropic-ai/claude-code` | `claude auth` |
|
|
432
|
-
| Codex | `bun install --global @openai/codex` | `codex auth` |
|
|
433
|
-
| Qwen | `bun install --global @qwen-code/qwen` | `qwen auth` |
|
|
434
|
-
|
|
435
487
|
## CLI Commands
|
|
436
488
|
|
|
437
489
|
```bash
|
|
@@ -444,20 +496,25 @@ bunx oh-my-ag stats --reset # Reset metrics
|
|
|
444
496
|
bunx oh-my-ag retro # Session retrospective (learnings & next steps)
|
|
445
497
|
bunx oh-my-ag dashboard # Terminal real-time dashboard
|
|
446
498
|
bunx oh-my-ag dashboard:web # Web dashboard (http://localhost:9847)
|
|
499
|
+
bunx oh-my-ag dashboard:web # Web dashboard (http://localhost:9847)
|
|
500
|
+
bunx oh-my-ag bridge # Bridge MCP stdio to SSE (for Serena)
|
|
447
501
|
bunx oh-my-ag help # Show help
|
|
448
502
|
```
|
|
449
503
|
|
|
450
504
|
## Troubleshooting
|
|
451
505
|
|
|
452
506
|
### Dashboard shows "No agents detected"
|
|
507
|
+
|
|
453
508
|
Memory files haven't been created yet. Run the orchestrator or manually create files in `.serena/memories/`.
|
|
454
509
|
|
|
455
510
|
### Skills not loading in Antigravity
|
|
511
|
+
|
|
456
512
|
1. Open project with `antigravity open .`
|
|
457
513
|
2. Verify `.agent/skills/` folder and `SKILL.md` files exist
|
|
458
514
|
3. Restart Antigravity IDE
|
|
459
515
|
|
|
460
516
|
### Agents producing incompatible code
|
|
517
|
+
|
|
461
518
|
1. Review outputs in `.gemini/antigravity/brain/`
|
|
462
519
|
2. Re-spawn one agent referencing the other's output
|
|
463
520
|
3. Use QA Agent for final consistency check
|