SDLC: Intake → Triage → Explore → Plan → Code → Test → Review → Commit → Deploy → Improve
MCP Tools by Phase
| Phase |
Tools |
| Intake |
mcp__linear__get_issue, mcp__notion__notion-search |
| Explore |
mcp__memory__search_nodes, mcp__github__search_code, mcp__context7__query-docs |
| Plan |
mcp__linear__create_issue (subtasks), mcp__notion__notion-create-pages, mcp__github__create_branch |
| Code |
mcp__context7__query-docs, Read, Write, Edit |
| Test |
Bash (make test, npm test), /quick-test |
| Deploy |
mcp__github__create_pull_request, /smoke-test |
| Improve |
mcp__memory__create_entities, mcp__linear__create_issue |
Triage Decision
| Change Type |
Path |
| New feature, breaking change, architecture |
OpenSpec → /openspec:proposal |
| Bug fix, config, tests, typo |
Quick → TodoWrite |
Phase Actions
Intake: Fetch Linear issue, search Notion for context
Explore: Search Memory for learnings, explore codebase, check related PRs
Plan: OpenSpec proposal OR TodoWrite, create branch
Code: Follow tasks, use platform rules, mark todos complete
Test: /quick-test, add tests for new logic
Review: /code-review, /security-scan if auth/data
Commit: /commit with type: description
Deploy: Create PR, run smoke tests after merge
Improve: Store learnings in Memory, create improvement tasks if needed
Quick Reference
# Backend
cd backend && make test
cd backend && make build
# Web
cd web && npm test
cd web && npm run build
# iOS
cd mobile/ios && make test
# Android
cd mobile/android && ./gradlew test
Anti-Patterns
- Coding without exploring → miss patterns
- Skipping Linear context → untracked work
- No Memory capture → repeat learnings
- Big commits → hard to review
1---2name: dev-workflow3description: SDLC workflow with MCP tools. Triggers on "start", "implement", "work on", or unclear workflow.4---5
6# SDLC: Intake → Triage → Explore → Plan → Code → Test → Review → Commit → Deploy → Improve
7
8## MCP Tools by Phase
9
10| Phase | Tools |
11|-------|-------|
12| Intake | `mcp__linear__get_issue`, `mcp__notion__notion-search` |
13| Explore | `mcp__memory__search_nodes`, `mcp__github__search_code`, `mcp__context7__query-docs` |
14| Plan | `mcp__linear__create_issue` (subtasks), `mcp__notion__notion-create-pages`, `mcp__github__create_branch` |
15| Code | `mcp__context7__query-docs`, Read, Write, Edit |
16| Test | Bash (make test, npm test), `/quick-test` |
17| Deploy | `mcp__github__create_pull_request`, `/smoke-test` |
18| Improve | `mcp__memory__create_entities`, `mcp__linear__create_issue` |
19
20## Triage Decision
21
22| Change Type | Path |
23|-------------|------|
24| New feature, breaking change, architecture | OpenSpec → `/openspec:proposal` |
25| Bug fix, config, tests, typo | Quick → `TodoWrite` |
26
27## Phase Actions
28
29**Intake**: Fetch Linear issue, search Notion for context
30**Explore**: Search Memory for learnings, explore codebase, check related PRs
31**Plan**: OpenSpec proposal OR TodoWrite, create branch
32**Code**: Follow tasks, use platform rules, mark todos complete
33**Test**: `/quick-test`, add tests for new logic
34**Review**: `/code-review`, `/security-scan` if auth/data
35**Commit**: `/commit` with `type: description`
36**Deploy**: Create PR, run smoke tests after merge
37**Improve**: Store learnings in Memory, create improvement tasks if needed
38
39## Quick Reference
40
41```bash
42# Backend
43cd backend && make test
44cd backend && make build
45
46# Web
47cd web && npm test
48cd web && npm run build
49
50# iOS
51cd mobile/ios && make test
52
53# Android
54cd mobile/android && ./gradlew test
55```
56
57## Anti-Patterns
58
59- Coding without exploring → miss patterns
60- Skipping Linear context → untracked work
61- No Memory capture → repeat learnings
62- Big commits → hard to review
majiayu000