@orderful/droid 0.7.0 → 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.
Files changed (72) hide show
  1. package/CHANGELOG.md +37 -0
  2. package/README.md +80 -89
  3. package/assets/droid+claude.png +0 -0
  4. package/dist/commands/setup.d.ts +1 -0
  5. package/dist/commands/setup.d.ts.map +1 -1
  6. package/dist/commands/setup.js +77 -9
  7. package/dist/commands/setup.js.map +1 -1
  8. package/dist/commands/tui.d.ts.map +1 -1
  9. package/dist/commands/tui.js +111 -70
  10. package/dist/commands/tui.js.map +1 -1
  11. package/dist/lib/agents.d.ts +19 -4
  12. package/dist/lib/agents.d.ts.map +1 -1
  13. package/dist/lib/agents.js +121 -42
  14. package/dist/lib/agents.js.map +1 -1
  15. package/dist/lib/skills.d.ts.map +1 -1
  16. package/dist/lib/skills.js +55 -0
  17. package/dist/lib/skills.js.map +1 -1
  18. package/dist/lib/types.d.ts +1 -0
  19. package/dist/lib/types.d.ts.map +1 -1
  20. package/dist/skills/brain/SKILL.md +11 -9
  21. package/dist/skills/brain/SKILL.yaml +1 -1
  22. package/dist/skills/brain/commands/brain.md +9 -4
  23. package/dist/skills/brain/references/workflows.md +14 -4
  24. package/dist/skills/code-review/SKILL.md +57 -0
  25. package/dist/skills/code-review/SKILL.yaml +22 -0
  26. package/dist/skills/code-review/agents/edi-standards-reviewer/AGENT.md +39 -0
  27. package/dist/skills/code-review/agents/edi-standards-reviewer/AGENT.yaml +14 -0
  28. package/dist/skills/code-review/agents/error-handling-reviewer/AGENT.md +51 -0
  29. package/dist/skills/code-review/agents/error-handling-reviewer/AGENT.yaml +14 -0
  30. package/dist/skills/code-review/agents/test-coverage-analyzer/AGENT.md +53 -0
  31. package/dist/skills/code-review/agents/test-coverage-analyzer/AGENT.yaml +14 -0
  32. package/dist/skills/code-review/agents/type-reviewer/AGENT.md +50 -0
  33. package/dist/skills/code-review/agents/type-reviewer/AGENT.yaml +13 -0
  34. package/dist/skills/code-review/commands/code-review.md +91 -0
  35. package/dist/skills/comments/SKILL.md +20 -5
  36. package/dist/skills/comments/SKILL.yaml +1 -1
  37. package/dist/skills/comments/commands/comments.md +1 -1
  38. package/dist/skills/project/SKILL.md +9 -7
  39. package/dist/skills/project/SKILL.yaml +1 -1
  40. package/dist/skills/project/commands/project.md +9 -4
  41. package/dist/skills/project/references/creating.md +9 -4
  42. package/dist/skills/project/references/loading.md +11 -5
  43. package/package.json +1 -1
  44. package/src/commands/setup.test.ts +276 -0
  45. package/src/commands/setup.ts +80 -10
  46. package/src/commands/tui.tsx +149 -82
  47. package/src/lib/agents.ts +134 -44
  48. package/src/lib/skills.ts +60 -0
  49. package/src/lib/types.ts +1 -0
  50. package/src/skills/brain/SKILL.md +11 -9
  51. package/src/skills/brain/SKILL.yaml +1 -1
  52. package/src/skills/brain/commands/brain.md +9 -4
  53. package/src/skills/brain/references/workflows.md +14 -4
  54. package/src/skills/code-review/SKILL.md +57 -0
  55. package/src/skills/code-review/SKILL.yaml +22 -0
  56. package/src/skills/code-review/agents/edi-standards-reviewer/AGENT.md +39 -0
  57. package/src/skills/code-review/agents/edi-standards-reviewer/AGENT.yaml +14 -0
  58. package/src/skills/code-review/agents/error-handling-reviewer/AGENT.md +51 -0
  59. package/src/skills/code-review/agents/error-handling-reviewer/AGENT.yaml +14 -0
  60. package/src/skills/code-review/agents/test-coverage-analyzer/AGENT.md +53 -0
  61. package/src/skills/code-review/agents/test-coverage-analyzer/AGENT.yaml +14 -0
  62. package/src/skills/code-review/agents/type-reviewer/AGENT.md +50 -0
  63. package/src/skills/code-review/agents/type-reviewer/AGENT.yaml +13 -0
  64. package/src/skills/code-review/commands/code-review.md +91 -0
  65. package/src/skills/comments/SKILL.md +20 -5
  66. package/src/skills/comments/SKILL.yaml +1 -1
  67. package/src/skills/comments/commands/comments.md +1 -1
  68. package/src/skills/project/SKILL.md +9 -7
  69. package/src/skills/project/SKILL.yaml +1 -1
  70. package/src/skills/project/commands/project.md +9 -4
  71. package/src/skills/project/references/creating.md +9 -4
  72. package/src/skills/project/references/loading.md +11 -5
@@ -31,12 +31,27 @@ The AI will respond with `> @{user_mention}` (configured in droid setup, e.g., `
31
31
 
32
32
  ## Tag Convention
33
33
 
34
- | Tag | Who's Speaking | Purpose |
35
- |-----|----------------|---------|
36
- | `@droid` | User | User leaving notes/questions for AI |
37
- | `@{user}` (e.g., `@fry`) | AI | AI leaving responses/questions for user |
34
+ **CRITICAL: The `@mention` is who you're talking TO, not who is speaking.**
38
35
 
39
- **The pattern:** The tag indicates who you're addressing, not who's writing. When you write `> @droid`, you're talking TO the AI. When the AI writes `> @fry`, it's talking TO you.
36
+ Think of it like addressing someone in conversation:
37
+ - "Hey @droid, what do you think?" → User talking TO the AI
38
+ - "Good point @fry, here's my take..." → AI talking TO the user
39
+
40
+ | When you see... | Who wrote it | Who it's addressed to |
41
+ |-----------------|--------------|----------------------|
42
+ | `> @droid ...` | User | AI (droid) |
43
+ | `> @fry ...` | AI | User (fry) |
44
+
45
+ **Examples:**
46
+ ```markdown
47
+ > @droid Can you explain this function? ← User asking AI
48
+ > @fry This function calculates the hash... ← AI responding to user
49
+
50
+ > @droid Should we refactor this? ← User asking AI
51
+ > @fry Yes, I'd suggest extracting... ← AI responding to user
52
+ ```
53
+
54
+ **Never flip this.** When responding to a `@droid` comment, always use `@{user}` (e.g., `@fry`) because you're addressing the user, not yourself.
40
55
 
41
56
  ## When NOT to Use
42
57
 
@@ -3,7 +3,7 @@ description: >-
3
3
  Enable inline conversations using @droid/@user markers. Tag @droid to ask the AI,
4
4
  AI responds with @{your-name}. Use /comments check to address markers, /comments cleanup
5
5
  to remove resolved threads. Ideal for code review notes and async collaboration.
6
- version: 0.2.1
6
+ version: 0.2.2
7
7
  status: beta
8
8
  dependencies: []
9
9
  provides_output: false
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  description: Check and respond to inline @droid comments in code and docs
3
- argument-hint: [check|cleanup] [path]
3
+ argument-hint: "[check [{path}] | cleanup]"
4
4
  allowed-tools: Read, Edit, Grep, Glob, Bash(git diff:*), Bash(git status:*)
5
5
  ---
6
6
 
@@ -32,31 +32,33 @@ Chat history disappears. Projects persist.
32
32
 
33
33
  ## Configuration
34
34
 
35
- Check `~/.droid/skills/project/overrides.yaml` for user settings:
35
+ **IMPORTANT:** Before using any default paths, ALWAYS read `~/.droid/skills/project/overrides.yaml` first. If `projects_dir` is configured there, use that path. Only fall back to defaults if the file doesn't exist or lacks a `projects_dir` setting.
36
36
 
37
37
  | Setting | Default | Description |
38
38
  |---------|---------|-------------|
39
- | `projects_dir` | `~/{ai_tool}/projects` | Where projects are stored (varies by AI tool) |
39
+ | `projects_dir` | (see below) | Where projects are stored |
40
40
  | `preset` | `markdown` | Output format: `markdown` or `obsidian` |
41
41
 
42
- Default `projects_dir` by AI tool:
42
+ Default `projects_dir` by AI tool (only if not configured):
43
43
  - **claude-code**: `~/.claude/projects`
44
- - **opencode**: `~/.opencode/projects`
44
+ - **opencode**: `~/.config/opencode/projects`
45
45
 
46
46
  ## Commands
47
47
 
48
48
  | Command | Action |
49
49
  |---------|--------|
50
50
  | `/project` | List and select a project |
51
- | `/project {keywords}` | Fuzzy-match and load |
52
- | `/project create {name}` | Create new project |
51
+ | `/project {keywords}` | **Search** for existing project (fuzzy-match and load) |
52
+ | `/project create {name}` | Create new project (requires `create` keyword) |
53
53
  | `/project update` | Update from conversation context |
54
54
 
55
+ **IMPORTANT:** The default action for `/project {keywords}` is to **SEARCH** for existing projects, NOT create. Only use `/project create {name}` when the user explicitly wants to create a new project.
56
+
55
57
  ## Loading a Project
56
58
 
57
59
  **Trigger:** `/project {keywords}` or user asks to load/open a project
58
60
 
59
- **TLDR:** Fuzzy-match keywords against project folders, read PROJECT.md, summarize context.
61
+ **TLDR:** Search for and load an existing project. Fuzzy-match keywords against project folders, read PROJECT.md, summarize context.
60
62
 
61
63
  Full procedure: `references/loading.md`
62
64
 
@@ -5,7 +5,7 @@ description: >-
5
5
  new learnings (/project update), or create new projects (/project create).
6
6
  Use when working on multi-session features, refactors, or any work that
7
7
  benefits from accumulated context.
8
- version: 0.1.0
8
+ version: 0.1.1
9
9
  status: beta
10
10
  dependencies: []
11
11
  provides_output: false
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  description: Manage project context files for persistent AI memory across sessions
3
- argument-hint: [name | update [name] | create [name]]
3
+ argument-hint: "[{keywords} | update | create {name}]"
4
4
  allowed-tools: Read, Write, Edit, Glob, Bash(mkdir:*), Bash(ls:*)
5
5
  ---
6
6
 
@@ -12,20 +12,25 @@ Entry point for project context management. See the **project skill** for full b
12
12
 
13
13
  $ARGUMENTS
14
14
 
15
+ ## Default Behavior
16
+
17
+ **IMPORTANT:** When given keywords (e.g., `/project audit-log`), the default action is to **SEARCH** for existing projects, NOT create. Only create a project when the `create` keyword is explicitly used.
18
+
15
19
  ## Usage
16
20
 
17
21
  ```
18
22
  /project # List and select a project
19
- /project {keywords} # Fuzzy-match and load
23
+ /project {keywords} # SEARCH: Fuzzy-match and load existing project
20
24
  /project update # Update from conversation context
21
25
  /project update {name} # Update specific project
22
26
  /project create # Create new project interactively
23
- /project create {name} # Create with name
27
+ /project create {name} # Create with name (requires "create" keyword)
24
28
  ```
25
29
 
26
30
  ## Configuration
27
31
 
28
- From `~/.droid/skills/project/overrides.yaml`:
32
+ **ALWAYS read `~/.droid/skills/project/overrides.yaml` first.** Use configured values if present, only fall back to defaults if missing.
33
+
29
34
  - `projects_dir` - Where projects live (default varies by AI tool)
30
35
  - `preset` - Template format: `markdown` or `obsidian`
31
36
 
@@ -4,21 +4,26 @@
4
4
 
5
5
  ## Procedure
6
6
 
7
- 1. **Get project name**
7
+ 1. **Read config first**
8
+ - Read `~/.droid/skills/project/overrides.yaml`
9
+ - Use `projects_dir` if configured, otherwise use default for current AI tool
10
+ - Use `preset` if configured (markdown or obsidian)
11
+
12
+ 2. **Get project name**
8
13
  - Use provided name, or ask if not provided
9
14
  - Convert to kebab-case for folder name
10
15
  - Convert to Title Case for display name
11
16
 
12
- 2. **Create project folder**
17
+ 3. **Create project folder**
13
18
  - Path: `{projects_dir}/{kebab-case-name}/`
14
19
  - Verify folder doesn't already exist
15
20
 
16
- 3. **Create files from templates** (see `templates.md`)
21
+ 4. **Create files from templates** (see `templates.md`)
17
22
  - `PROJECT.md` - Main context file
18
23
  - `CHANGELOG.md` - Version history
19
24
  - Format varies by `preset` config (markdown vs obsidian)
20
25
 
21
- 4. **Confirm creation**
26
+ 5. **Confirm creation**
22
27
  - Show created folder path
23
28
  - Offer to help fill in sections (Overview, Goals, Technical Details)
24
29
 
@@ -2,25 +2,31 @@
2
2
 
3
3
  **Trigger:** `/project {keywords}` or user asks to load/open a project
4
4
 
5
+ **IMPORTANT:** This is a SEARCH operation. When keywords are provided, search for existing projects - do NOT create a new project. Creating requires the explicit `/project create {name}` command.
6
+
5
7
  ## Procedure
6
8
 
7
- 1. **List projects** in configured `projects_dir`
9
+ 1. **Read config first**
10
+ - Read `~/.droid/skills/project/overrides.yaml`
11
+ - Use `projects_dir` if configured, otherwise use default for current AI tool
12
+
13
+ 2. **List projects** in configured `projects_dir`
8
14
  - Each subfolder with a `PROJECT.md` is a project
9
15
 
10
- 2. **If no name provided:**
16
+ 3. **If no name provided:**
11
17
  - Use AskUserQuestion to present available projects
12
18
  - Let user select which to load
13
19
 
14
- 3. **If name/keywords provided:**
20
+ 4. **If name/keywords provided:**
15
21
  - Parse as space-separated keywords (e.g., "transaction templates" → `["transaction", "templates"]`)
16
22
  - Find folders where name contains ALL keywords (case-insensitive, hyphens as word separators)
17
23
 
18
- 4. **Based on matches:**
24
+ 5. **Based on matches:**
19
25
  - **No matches**: List available projects, ask user to select
20
26
  - **One match**: Read `{folder}/PROJECT.md`
21
27
  - **Multiple matches**: Use AskUserQuestion to select from matches
22
28
 
23
- 5. **After loading:**
29
+ 6. **After loading:**
24
30
  - Confirm which project was loaded
25
31
  - Summarize key context (2-3 sentences)
26
32
  - Use project contents for all subsequent work in the session