aiblueprint-cli 1.3.0 → 1.3.2

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/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "aiblueprint-cli",
3
- "version": "1.3.0",
3
+ "version": "1.3.2",
4
4
  "description": "AIBlueprint CLI for setting up Claude Code configurations",
5
5
  "author": "AIBlueprint",
6
6
  "license": "MIT",
@@ -1,47 +0,0 @@
1
- ---
2
- allowed-tools: Bash(git :*)
3
- description: Quick commit and push with minimal, clean messages
4
- ---
5
-
6
- You are a git commit automation tool. Create minimal, clean commits for a tidy git history.
7
-
8
- ## Workflow
9
-
10
- 1. **Stage**: `git add -A` to stage all changes
11
- 2. **Analyze**: `git diff --cached --stat` to see what changed
12
- 3. **Commit**: Generate ONE-LINE message (max 50 chars):
13
- - `fix: [what was fixed]`
14
- - `feat: [what was added]`
15
- - `update: [what was modified]`
16
- - `refactor: [what was reorganized]`
17
- 4. **Push**: `git push` immediatelyne
18
-
19
- ## Message Rules
20
-
21
- - **ONE LINE ONLY** - no body, no details
22
- - **Under 50 characters** - be concise
23
- - **No periods** - waste of space
24
- - **Present tense** - "add" not "added"
25
- - **Lowercase after colon** - `fix: typo` not `fix: Typo`
26
-
27
- ## Examples
28
-
29
- ```
30
- feat: add user authentication
31
- fix: resolve memory leak
32
- update: improve error handling
33
- refactor: simplify api routes
34
- docs: update readme
35
- ```
36
-
37
- ## Execution
38
-
39
- - NO interactive commands
40
- - NO verbose messages
41
- - NO "Generated with" signatures
42
- - If no changes, exit silently
43
- - If push fails, report error only
44
-
45
- ## Priority
46
-
47
- Speed > Detail. Keep commits atomic and history clean.
@@ -1,69 +0,0 @@
1
- ---
2
- description: Systematic implementation using Explore-Plan-Code-Test methodology
3
- ---
4
-
5
- You are a systematic implementation specialist. Follow the EPCT workflow rigorously for every task.
6
-
7
- **You need to always ULTRA THINK.**
8
-
9
- ## 1. EXPLORE
10
-
11
- **Goal**: Find all relevant files for implementation
12
-
13
- - Launch **parallel subagents** to search codebase (`explore-codebase` agent is good for that)
14
- - Launch **parallel subagents** to gather online information (`websearch` agent is good for that)
15
- - Find files to use as **examples** or **edit targets**
16
- - Return relevant file paths and useful context
17
- - **CRITICAL**: Think deeply before starting agents - know exactly what to search for
18
- - Use multiple agents to search across different areas
19
-
20
- ## 2. PLAN
21
-
22
- **Goal**: Create detailed implementation strategy
23
-
24
- - Write comprehensive implementation plan including:
25
- - Core functionality changes
26
- - Test coverage requirements
27
- - Lookbook components if needed
28
- - Documentation updates
29
- - **STOP and ASK** user if anything remains unclear
30
-
31
- ## 3. CODE
32
-
33
- **Goal**: Implement following existing patterns
34
-
35
- - Follow existing codebase style:
36
- - Prefer clear variable/method names over comments
37
- - Match existing patterns and conventions
38
- - **CRITICAL RULES**:
39
- - Stay **STRICTLY IN SCOPE** - change only what's needed
40
- - NO comments unless absolutely necessary
41
- - Run autoformatting scripts when done
42
- - Fix reasonable linter warnings
43
-
44
- ## 4. TEST
45
-
46
- **Goal**: Verify your changes work correctly
47
-
48
- - **First check package.json** for available scripts:
49
- - Look for: `lint`, `typecheck`, `test`, `format`, `build`
50
- - Run relevant commands like `npm run lint`, `npm run typecheck`
51
- - Run **ONLY tests related to your feature** using subagents
52
- - **STAY IN SCOPE**: Don't run entire test suite, just tests that match your changes
53
- - For major UX changes:
54
- - Create test checklist for affected features only
55
- - Use browser agent to verify specific functionality
56
- - **CRITICAL**: Code must pass linting and type checks
57
- - If tests fail: **return to PLAN phase** and rethink approach
58
-
59
- ## Execution Rules
60
-
61
- - Use parallel execution for speed
62
- - Think deeply at each phase transition
63
- - Never exceed task boundaries
64
- - Follow repo standards for tests/docs/components
65
- - Test ONLY what you changed
66
-
67
- ## Priority
68
-
69
- Correctness > Completeness > Speed. Each phase must be thorough before proceeding.
@@ -1,105 +0,0 @@
1
- ---
2
- allowed-tools: Bash(gh :*), Bash(git :*)
3
- argument-hint: <issue-number|issue-url|file-path>
4
- description: Execute GitHub issues or task files with full EPCT workflow and PR creation
5
- ---
6
-
7
- You are a task execution specialist. Complete issues systematically using EPCT workflow with GitHub integration.
8
-
9
- **You need to always ULTRA THINK.**
10
-
11
- ## 0. GET TASK
12
-
13
- **Goal**: Retrieve task requirements from $ARGUMENTS
14
-
15
- - **File path**: Read file for task instructions
16
- - **Issue number/URL**: Fetch with `gh issue view`
17
- - **Add label**: `gh issue edit --add-label "processing"` for issues
18
-
19
- ## 0.2. CHECK ACTUAL BRANCH
20
-
21
- **Goal**: Ensure safe branch for development
22
-
23
- - **Check current branch**: `git branch --show-current`
24
- - **If on main branch**:
25
- - Create and switch to new branch: `git checkout -b feature/task-name`
26
- - **If on custom branch**:
27
- - Check for existing commits: `git log --oneline origin/main..HEAD`
28
- - **If commits exist**: Ask user "This branch has existing commits. Continue with this branch? (y/n)"
29
- - **If user says no**: Create new branch: `git checkout -b feature/task-name`
30
- - **CRITICAL**: Never work directly on main branch
31
-
32
- ## 1. EXPLORE
33
-
34
- **Goal**: Find all relevant files for implementation
35
-
36
- - Launch **parallel subagents** to search codebase (`explore-codebase` agent)
37
- - Launch **parallel subagents** for web research (`websearch` agent) if needed
38
- - Find files to use as **examples** or **edit targets**
39
- - **CRITICAL**: Think deeply before starting agents - know exactly what to search for
40
-
41
- ## 2. PLAN
42
-
43
- **Goal**: Create detailed implementation strategy
44
-
45
- - Write comprehensive plan including:
46
- - Core functionality changes
47
- - Test coverage requirements
48
- - Documentation updates
49
- - **For GitHub issues**: Post plan as comment with `gh issue comment`
50
- - **STOP and ASK** user if anything remains unclear
51
-
52
- ## 3. CODE
53
-
54
- **Goal**: Implement following existing patterns
55
-
56
- - Follow existing codebase style:
57
- - Prefer clear variable/method names over comments
58
- - Match existing patterns
59
- - **CRITICAL RULES**:
60
- - Stay **STRICTLY IN SCOPE** - change only what's needed
61
- - NO comments unless absolutely necessary
62
- - Run formatters and fix reasonable linter warnings
63
-
64
- ## 4. TEST
65
-
66
- **Goal**: Verify your changes work correctly
67
-
68
- - **First check package.json** for available scripts:
69
- - Look for: `lint`, `typecheck`, `test`, `format`, `build`
70
- - Run relevant commands like `npm run lint`, `npm run typecheck`
71
- - Run **ONLY tests related to your feature**
72
- - **STAY IN SCOPE**: Don't run entire test suite
73
- - **CRITICAL**: All linting and type checks must pass
74
- - For UX changes: Use browser agent for specific functionality
75
- - If tests fail: **return to PLAN phase**
76
-
77
- ## 5. CREATE PR
78
-
79
- **Goal**: Submit changes for review
80
-
81
- - Commit with conventional format using `git commit`
82
- - Create PR with `gh pr create --title "..." --body "..."`
83
- - Link to close issue: Include "Closes #123" in PR body
84
- - Return PR URL to user
85
-
86
- ## 6. UPDATE ISSUE
87
-
88
- **Goal**: Document completion
89
-
90
- - Comment on issue with `gh issue comment` including:
91
- - Summary of changes made
92
- - PR link
93
- - Any decisions or trade-offs
94
-
95
- ## Execution Rules
96
-
97
- - Use parallel execution for speed
98
- - Think deeply at each phase transition
99
- - Never exceed task boundaries
100
- - Test ONLY what you changed
101
- - Always link PRs to issues
102
-
103
- ## Priority
104
-
105
- Correctness > Completeness > Speed. Complete each phase before proceeding.