@ngocsangairvds/vsaf 3.0.8 → 3.0.10

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.
Files changed (3) hide show
  1. package/.claude/skills/vsaf-plan/SKILL.md +14 -7
  2. package/README.md +83 -27
  3. package/package.json +1 -1
package/.claude/skills/vsaf-plan/SKILL.md CHANGED
@@ -9,12 +9,12 @@ description: Lên plan cho 1 feature/task mới. Dùng khi nhận được yêu
9
9
  Hiểu đầy đủ yêu cầu, phân tích impact, và xác định chiến lược implement trước khi viết bất kỳ dòng code nào.
10
10
 
11
11
  ## Input
12
- `<feature>` — mô tả feature/task cần làm (ví dụ: "tạo module quản lý dashboard")
12
+ `$ARGUMENTS` — mô tả feature/task cần làm (ví dụ: "tạo module quản lý dashboard")
13
13
 
14
14
  ## Các bước thực hiện
15
15
 
16
16
  ### Bước 1 — Search MemPalace (bắt buộc)
17
- - Gọi `mcp__mempalace__mempalace_search` với keyword từ `<feature>`
17
+ - Gọi `mcp__mempalace__mempalace_search` với keyword từ `$ARGUMENTS`
18
18
  - Tìm kiếm: past decisions, architectural patterns, previous attempts
19
19
  - Tóm tắt: có decision nào liên quan không?
20
20
 
@@ -29,15 +29,22 @@ Hiểu đầy đủ yêu cầu, phân tích impact, và xác định chiến lư
29
29
  - Báo cáo blast radius: bao nhiêu module bị ảnh hưởng, risk level
30
30
  - Nếu risk HIGH/CRITICAL: DỪNG, báo user trước khi tiếp tục
31
31
 
32
- ### Bước 4 — Architecture decision (BMAD architect)
32
+ ### Bước 4 — Trace dependencies (Graphify)
33
+ - Nếu cần trace path giữa 2 services: dùng `/graphify path ServiceA ServiceB`
34
+ - Xác định: integration points, shared dependencies
35
+
36
+ ### Bước 5 — Architecture decision (BMAD architect)
33
37
  - Dùng skill `bmad-agent-architect` để đề xuất architecture approach
34
38
  - So sánh alternatives, chọn approach phù hợp nhất
35
39
 
36
- ### Bước 5 — Brainstorm (Superpowers)
37
- - Dùng skill `superpowers:brainstorming` để explore alternatives
38
- - Đặt câu hỏi Socratic: "What if...", "What could go wrong..."
40
+ ### Bước 6 — Brainstorm (BMAD Brainstorming)
41
+ - Dùng skill `bmad-brainstorming` để explore alternatives và uncover hidden risks
42
+ - Facilitator sẽ dẫn dắt session với các kỹ thuật sáng tạo đa dạng
43
+ - Đặt câu hỏi: "What if...", "What could go wrong...", "What are we missing?"
44
+ - Mục tiêu: tối thiểu 20 ý tưởng/alternatives trước khi tổ chức lại
45
+ - bmad-brainstorming sẽ load config từ `_bmad/bmm/config.yaml`
39
46
 
40
- ### Bước 6 — Output cho user
47
+ ### Bước 7 — Output cho user
41
48
  Trình bày kết quả theo format:
42
49
 
43
50
  ```
package/README.md CHANGED
@@ -10,17 +10,17 @@ every decision. $20/month total.
10
10
 
11
11
  ```
12
12
  ┌──────────────────────────────────────────────────────────────────────┐
13
- │ PLANNING BMAD (agents) │
14
- │ Analyst, PM, Architect, Product Owner │
13
+ │ PLANNING BMAD (agents) │
14
+ │ Analyst · Architect · Brainstorming · QA │
15
15
  ├──────────────────────────────────────────────────────────────────────┤
16
- │ CODE INTEL GitNexus (MCP backbone) │
17
- │ call-graph, impact analysis, blast radius │
16
+ │ CODE INTEL GitNexus (MCP backbone) │
17
+ │ call-graph, impact analysis, blast radius │
18
18
  ├──────────────────────────────────────────────────────────────────────┤
19
- │ MEMORY MemPalace (knowledge base) │
20
- │ architecture decisions, temporal KG │
19
+ │ MEMORY MemPalace (knowledge base) │
20
+ │ architecture decisions, temporal KG │
21
21
  ├──────────────────────────────────────────────────────────────────────┤
22
- │ IMPLEMENTATION Claude Code + Superpowers │
23
- │ brainstorm, TDD execution, code review │
22
+ │ IMPLEMENTATION Claude Code + Superpowers │
23
+ │ TDD execution, code review │
24
24
  └──────────────────────────────────────────────────────────────────────┘
25
25
  ```
26
26
 
@@ -96,7 +96,8 @@ Run `npx @ngocsangairvds/vsaf@latest --help` for the full list. Highlights:
96
96
  Main skill commands inside Claude Code:
97
97
 
98
98
  - `/vsaf-onboard`
99
- - `/vsaf-plan` + `/vsaf-doc`
99
+ - `/vsaf-plan <feature>`
100
+ - `/vsaf-doc`
100
101
  - `/vsaf-test <path/to/srs>`
101
102
  - `/vsaf-build <path/to/srs> <path/to/testcases>`
102
103
  - `/vsaf-ship`
@@ -105,29 +106,84 @@ Main skill commands inside Claude Code:
105
106
 
106
107
  Every feature follows an **SRS-first cycle**:
107
108
 
108
- 1. `/vsaf-onboard` — understand project context (code graph + decisions)
109
- 2. `/vsaf-plan` + `/vsaf-doc` — turn requirement into approved SRS
110
- 3. `/vsaf-test <path/to/srs>` — generate testcase docs from SRS
111
- 4. `gitnexus_impact` + `mempalace_search` — mandatory impact/rationale gate
112
- 5. `/vsaf-build <path/to/srs> <path/to/testcases>` — implement with TDD guardrails
113
- 6. `/superpowers:code-review` + `vsaf index` + `/vsaf-ship` — review, sync graph, ship
109
+ ```
110
+ /vsaf-onboard → /vsaf-plan → /vsaf-doc → /vsaf-test → /vsaf-build → /vsaf-ship
111
+ ```
114
112
 
115
113
  Bug fixes (Quick Flow) may use mini-SRS + mini-testcases, but still require
116
114
  `gitnexus_impact` before editing symbols and `gitnexus_detect_changes` before commit.
117
115
 
118
- Generated docs path convention:
119
-
120
- - SRS: `docs/project/srs/<feature>.md`
121
- - Testcases: `docs/project/testcases/<feature>.md`
122
- - Planning artifacts: `docs/project/planning-artifacts/`
123
- - Implementation artifacts: `docs/project/implementation-artifacts/`
116
+ ### Flow breakdown
117
+
118
+ #### `/vsaf-onboard` — Understand the codebase
119
+ | Step | Tool | Does |
120
+ |------|------|------|
121
+ | 1 | **GitNexus** `mcp__gitnexus__query` + `group_list` | Maps modules, clusters, entry points, hot symbols |
122
+ | 2 | **MemPalace** `mempalace_search` × 3 | Surfaces past architecture decisions, patterns, rationale |
123
+ | → | Output | Project overview: architecture, patterns, key decisions, risk areas |
124
+
125
+ #### `/vsaf-plan <feature>` — Analyse and plan
126
+ | Step | Tool | Does |
127
+ |------|------|------|
128
+ | 1 | **MemPalace** `mempalace_search` | Checks for prior decisions that affect this feature |
129
+ | 2 | **BMAD** `bmad-agent-analyst` (Mary) | Elicits FRs, NFRs, edge cases, scope boundaries |
130
+ | 3 | **GitNexus** `mcp__gitnexus__impact` + `query` | Blast radius — how many modules touched, risk level |
131
+ | 4 | **Graphify** `/graphify path A B` *(if needed)* | Traces dependency path between two services |
132
+ | 5 | **BMAD** `bmad-agent-architect` (Winston) | Proposes architecture approach, compares alternatives |
133
+ | 6 | **BMAD** `bmad-brainstorming` | Creative exploration — min. 20 alternatives / risk angles |
134
+ | → | Output | Scope, impact report, chosen approach, rejected alternatives |
135
+
136
+ #### `/vsaf-doc` — Write the SRS
137
+ | Step | Tool | Does |
138
+ |------|------|------|
139
+ | 1 | **MemPalace** `mempalace_search` | Checks for old decisions to reference in SRS |
140
+ | 2 | *(Claude)* | Writes SRS with FRs/NFRs/acceptance criteria + traceability IDs → `docs/project/srs/` |
141
+ | 3 | *(Claude)* | Writes implement notes: affected modules, technical constraints |
142
+ | 4 | **MemPalace** `mempalace_add_drawer` | Persists chosen approach + rejected alternatives |
143
+ | → | Output | `docs/project/srs/[feature].md` ready for testcase generation |
144
+
145
+ #### `/vsaf-test <path/to/srs>` — Generate testcases
146
+ | Step | Tool | Does |
147
+ |------|------|------|
148
+ | 1 | **BMAD** `bmad-qa-generate-e2e-tests` | Derives unit / integration / edge-case tests from SRS FRs/NFRs |
149
+ | 2 | *(Claude)* | Validates every FR/NFR has ≥ 1 test, records gaps |
150
+ | 3 | *(Claude)* | Builds FR/NFR → Testcase ID traceability matrix |
151
+ | 4 | *(Claude)* | Saves to `docs/project/testcases/[feature].md` |
152
+ | → | Output | Testcase contract — used as implementation guardrails |
153
+
154
+ #### `/vsaf-build <path/to/srs> <path/to/testcases>` — Implement with TDD
155
+ | Step | Tool | Does |
156
+ |------|------|------|
157
+ | 1 | **MemPalace** `mempalace_search` | Last check — no old decisions conflict with implementation |
158
+ | 2 | *(Claude)* | Reads SRS + testcases, confirms FR/NFR → testcase mapping |
159
+ | 3 | **Claude Code** (TDD loop) | RED → GREEN → REFACTOR per testcase group |
160
+ | 3b | **GitNexus** `mcp__gitnexus__detect_changes` | Verifies only intended files changed before each commit |
161
+ | → | Output | Working code, all tests passing, 1 commit per task |
162
+
163
+ #### `/vsaf-ship` — Review, sync, and record
164
+ | Step | Tool | Does |
165
+ |------|------|------|
166
+ | 1 | **Superpowers** `superpowers:code-review` | Layer 1 — structure, naming, SOLID, patterns |
167
+ | 2 | **GitNexus** `gitnexus analyze` / `vsaf index` | Layer 2 — updates call graph to reflect new code |
168
+ | 3 | **MemPalace** `mempalace_add_drawer` + `diary_write` | Saves decisions + session summary for future sessions |
169
+ | 4 | *(git)* | Push branch, open PR with impact summary + test results |
170
+ | → | Output | Shipped feature, updated graph, persistent knowledge |
171
+
172
+ ### Generated docs path convention
173
+
174
+ | Artifact | Path |
175
+ |----------|------|
176
+ | SRS | `docs/project/srs/<feature>.md` |
177
+ | Testcases | `docs/project/testcases/<feature>.md` |
178
+ | Planning artifacts | `docs/project/planning-artifacts/` |
179
+ | Implementation artifacts | `docs/project/implementation-artifacts/` |
124
180
 
125
181
  ### Command naming map
126
182
 
127
- - `/vsaf-onboarding` -> `vsaf-onboard`
128
- - `/vsaf-planning + requirement` -> `vsaf-plan` + `vsaf-doc`
129
- - `/vsaf-testcase + path/to/srs` -> `vsaf-test <path/to/srs>`
130
- - `/vsaf-implement + path/to/srs + path/to/test_case` -> `vsaf-build <srs> <testcases>`
183
+ - `/vsaf-onboarding` → `vsaf-onboard`
184
+ - `/vsaf-planning <requirement>` → `vsaf-plan` + `vsaf-doc`
185
+ - `/vsaf-testcase <path/to/srs>` → `vsaf-test <path/to/srs>`
186
+ - `/vsaf-implement <srs> <testcases>` → `vsaf-build <srs> <testcases>`
131
187
 
132
188
  See [1-setup-guide.md § Your First Project](docs/onboarding/1-setup-guide.md#5-your-first-project--a-walkthrough)
133
189
  for a walkthrough, or [2-workflow-guide.md § JWT Demo](docs/onboarding/2-workflow-guide.md#4-full-sdlc-demo)
@@ -138,8 +194,8 @@ for a full command-by-command example.
138
194
  | Tool | What It Does | Cost |
139
195
  |---|---|---|
140
196
  | **Claude Code** | AI coding agent — everything else plugs into it | $20/mo |
141
- | **BMAD Method** | AI agents for planning: Analyst, PM, Architect, Product Owner | Free |
142
- | **Superpowers** | Methodology engine: brainstorm, plan, TDD execution, code review | Free |
197
+ | **BMAD Method** | AI agents for planning: Analyst, Architect, Brainstorming, QA | Free |
198
+ | **Superpowers** | Methodology engine: code review | Free |
143
199
  | **GitNexus** | Code knowledge graph via MCP — impact analysis, dependency queries | Free |
144
200
  | **MemPalace** | Knowledge base — verbatim storage of decisions, temporal knowledge graph | Free |
145
201
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@ngocsangairvds/vsaf",
3
- "version": "3.0.8",
3
+ "version": "3.0.10",
4
4
  "description": "VSAF — Agentic AI SDLC Framework. 4 integrated tools: BMAD, GitNexus, Superpowers, MemPalace. 2-layer review.",
5
5
  "keywords": ["claude", "claude-code", "ai", "sdlc", "framework", "bmad", "gitnexus", "mempalace"],
6
6
  "bin": {