devflow-kit 0.6.1 → 0.8.0
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/CHANGELOG.md +64 -0
- package/README.md +83 -16
- package/dist/commands/init.d.ts.map +1 -1
- package/dist/commands/init.js +5 -4
- package/dist/commands/init.js.map +1 -1
- package/package.json +1 -1
- package/src/claude/agents/devflow/audit-performance.md +1 -1
- package/src/claude/agents/devflow/audit-security.md +1 -1
- package/src/claude/agents/devflow/brainstorm.md +279 -0
- package/src/claude/agents/devflow/catch-up.md +3 -6
- package/src/claude/agents/devflow/code-review.md +307 -0
- package/src/claude/agents/devflow/commit.md +3 -5
- package/src/claude/agents/devflow/debug.md +2 -1
- package/src/claude/agents/devflow/design.md +491 -0
- package/src/claude/agents/devflow/pr-comments.md +285 -0
- package/src/claude/agents/devflow/tech-debt.md +338 -0
- package/src/claude/commands/devflow/brainstorm.md +68 -0
- package/src/claude/commands/devflow/breakdown.md +125 -0
- package/src/claude/commands/devflow/code-review.md +152 -346
- package/src/claude/commands/devflow/commit.md +8 -19
- package/src/claude/commands/devflow/design.md +82 -0
- package/src/claude/commands/devflow/devlog.md +2 -3
- package/src/claude/commands/devflow/implement.md +50 -457
- package/src/claude/commands/devflow/plan.md +133 -395
- package/src/claude/skills/devflow/research/SKILL.md +36 -33
- package/src/claude/agents/devflow/research.md +0 -609
- package/src/claude/commands/devflow/plan-next-steps.md +0 -212
- package/src/claude/commands/devflow/research.md +0 -51
|
@@ -0,0 +1,125 @@
|
|
|
1
|
+
---
|
|
2
|
+
allowed-tools: TodoWrite
|
|
3
|
+
description: Quickly break down discussion into actionable tasks without interactive triage
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
## Your task
|
|
7
|
+
|
|
8
|
+
Extract action items from the current conversation and immediately save them as todos. No interaction, no triage, no GitHub issues - just fast task decomposition.
|
|
9
|
+
|
|
10
|
+
**Goal**: Quick capture of actionable items from discussion.
|
|
11
|
+
|
|
12
|
+
---
|
|
13
|
+
|
|
14
|
+
## Step 1: Extract Action Items
|
|
15
|
+
|
|
16
|
+
Scan the conversation for concrete next steps:
|
|
17
|
+
|
|
18
|
+
**Look for**:
|
|
19
|
+
- Tasks mentioned or implied ("We should...", "I'll need to...", "Let me...")
|
|
20
|
+
- Code changes discussed or agreed upon
|
|
21
|
+
- Files to create, modify, or review
|
|
22
|
+
- Dependencies to install or configure
|
|
23
|
+
- Tests to write or update
|
|
24
|
+
- Documentation to update
|
|
25
|
+
- Decisions that need to be made
|
|
26
|
+
|
|
27
|
+
---
|
|
28
|
+
|
|
29
|
+
## Step 2: Convert to Specific Todos
|
|
30
|
+
|
|
31
|
+
Transform extracted items into actionable tasks:
|
|
32
|
+
|
|
33
|
+
**Good**:
|
|
34
|
+
- "Add authentication middleware to routes in `src/middleware/auth`"
|
|
35
|
+
- "Write unit tests for user registration in `tests/auth.test.ts`"
|
|
36
|
+
- "Install password hashing library dependency"
|
|
37
|
+
|
|
38
|
+
**Bad**:
|
|
39
|
+
- "Improve authentication" (vague)
|
|
40
|
+
- "Add better error handling" (not specific)
|
|
41
|
+
- "Make it more secure" (not actionable)
|
|
42
|
+
|
|
43
|
+
---
|
|
44
|
+
|
|
45
|
+
## Step 3: Prioritize by Dependencies
|
|
46
|
+
|
|
47
|
+
Order tasks logically:
|
|
48
|
+
1. **Dependencies first** - installations, setup
|
|
49
|
+
2. **Core implementation** - main functionality
|
|
50
|
+
3. **Tests** - verification
|
|
51
|
+
4. **Documentation** - updates
|
|
52
|
+
|
|
53
|
+
---
|
|
54
|
+
|
|
55
|
+
## Step 4: Save with TodoWrite
|
|
56
|
+
|
|
57
|
+
```json
|
|
58
|
+
[
|
|
59
|
+
{
|
|
60
|
+
"content": "${specific_task_description}",
|
|
61
|
+
"status": "pending",
|
|
62
|
+
"activeForm": "${task_in_progress_form}"
|
|
63
|
+
}
|
|
64
|
+
]
|
|
65
|
+
```
|
|
66
|
+
|
|
67
|
+
Each task should be:
|
|
68
|
+
- Completable in 15-60 minutes
|
|
69
|
+
- Specific with file paths when relevant
|
|
70
|
+
- Clear success criteria
|
|
71
|
+
- Pending status
|
|
72
|
+
|
|
73
|
+
---
|
|
74
|
+
|
|
75
|
+
## Step 5: Present Summary
|
|
76
|
+
|
|
77
|
+
```markdown
|
|
78
|
+
## BREAKDOWN COMPLETE
|
|
79
|
+
|
|
80
|
+
### Tasks Added (${count} items)
|
|
81
|
+
|
|
82
|
+
**Dependencies & Setup**
|
|
83
|
+
- ${task}
|
|
84
|
+
- ${task}
|
|
85
|
+
|
|
86
|
+
**Core Implementation**
|
|
87
|
+
- ${task}
|
|
88
|
+
- ${task}
|
|
89
|
+
|
|
90
|
+
**Testing**
|
|
91
|
+
- ${task}
|
|
92
|
+
|
|
93
|
+
**Documentation**
|
|
94
|
+
- ${task}
|
|
95
|
+
|
|
96
|
+
---
|
|
97
|
+
|
|
98
|
+
**Total: ${count} tasks saved to todo list**
|
|
99
|
+
|
|
100
|
+
💡 Run `/implement` to start working through these tasks
|
|
101
|
+
💡 Run `/plan` if you want to triage before committing to tasks
|
|
102
|
+
```
|
|
103
|
+
|
|
104
|
+
---
|
|
105
|
+
|
|
106
|
+
## Behavior Rules
|
|
107
|
+
|
|
108
|
+
### ALWAYS:
|
|
109
|
+
- Extract concrete action items immediately
|
|
110
|
+
- Use TodoWrite to save all items
|
|
111
|
+
- Break tasks into 15-60 minute chunks
|
|
112
|
+
- Include file paths and specific details
|
|
113
|
+
- Prioritize by dependencies
|
|
114
|
+
|
|
115
|
+
### NEVER:
|
|
116
|
+
- Ask user for selection (use `/plan` for that)
|
|
117
|
+
- Create vague or untestable tasks
|
|
118
|
+
- Skip obvious implementation steps
|
|
119
|
+
- Make tasks too large or complex
|
|
120
|
+
- Forget to use TodoWrite
|
|
121
|
+
|
|
122
|
+
### When to use `/breakdown` vs `/plan`:
|
|
123
|
+
|
|
124
|
+
- **`/breakdown`**: Fast capture, trust AI extraction, want all items
|
|
125
|
+
- **`/plan`**: Deliberate triage, want to defer some to GitHub issues, need understanding before committing
|