claude-symphony 0.7.0 → 0.8.1
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/README.md +14 -12
- package/dist/cli/index.js +673 -218
- package/dist/core/index.js +2 -11
- package/dist/hooks/output-validator.js +2 -1
- package/dist/hooks/pre-transition.js +2 -1
- package/dist/hooks/stage-checklist.js +2 -1
- package/package.json +1 -1
- package/template/.claude/commands/auto-pilot.md +33 -1
- package/template/config/pipeline.jsonc +14 -6
package/README.md
CHANGED
|
@@ -26,18 +26,20 @@ Unlike prototyping tools (Lovable, Bolt.new) that generate MVPs, claude-symphony
|
|
|
26
26
|
|
|
27
27
|
claude-symphony orchestrates a 10-stage pipeline where AI agents execute each stage automatically:
|
|
28
28
|
|
|
29
|
-
| # | Stage | What happens |
|
|
30
|
-
|
|
31
|
-
| 01 | **Brainstorm** | Generate features, user stories, requirements |
|
|
32
|
-
| 02 | **Research** | Evaluate tech options, analyze feasibility |
|
|
33
|
-
| 03 | **Planning** | Design architecture, data models, API |
|
|
34
|
-
| 04 | **UI/UX** | Create wireframes, component tree, design tokens |
|
|
35
|
-
| 05 | **Tasks** | Decompose into implementable tasks with priorities |
|
|
36
|
-
| 06 | **Implementation** | Write code using **TDD** (tests first, then code) |
|
|
37
|
-
| 07 | **Refactoring** | Improve code quality, maintain test coverage |
|
|
38
|
-
| 08 | **QA** | Security audit, accessibility, E2E test expansion |
|
|
39
|
-
| 09 | **Testing** | Edge-case tests, performance benchmarks |
|
|
40
|
-
| 10 | **Deployment** | CI/CD pipeline, hosting, production deploy |
|
|
29
|
+
| # | Stage | Model | What happens |
|
|
30
|
+
|---|-------|-------|-------------|
|
|
31
|
+
| 01 | **Brainstorm** | Gemini + Claude | Generate features, user stories, requirements |
|
|
32
|
+
| 02 | **Research** | Claude | Evaluate tech options, analyze feasibility |
|
|
33
|
+
| 03 | **Planning** | Gemini + Claude | Design architecture, data models, API |
|
|
34
|
+
| 04 | **UI/UX** | Gemini + Claude | Create wireframes, component tree, design tokens |
|
|
35
|
+
| 05 | **Tasks** | Claude | Decompose into implementable tasks with priorities |
|
|
36
|
+
| 06 | **Implementation** | Claude | Write code using **TDD** (tests first, then code) |
|
|
37
|
+
| 07 | **Refactoring** | Codex + Claude | Improve code quality, maintain test coverage |
|
|
38
|
+
| 08 | **QA** | Claude | Security audit, accessibility, E2E test expansion |
|
|
39
|
+
| 09 | **Testing** | Codex + Claude | Edge-case tests, performance benchmarks |
|
|
40
|
+
| 10 | **Deployment** | Claude | CI/CD pipeline, hosting, production deploy |
|
|
41
|
+
|
|
42
|
+
> **Multi-model fallback**: If Gemini/Codex CLI is not installed, the stage automatically falls back to Claude Code.
|
|
41
43
|
|
|
42
44
|
Each stage:
|
|
43
45
|
- Has a specialized AI persona (creative for brainstorming, precise for implementation)
|