@simplysm/sd-claude 13.0.78 → 13.0.80
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/claude/rules/sd-claude-rules.md +4 -63
- package/claude/rules/sd-simplysm-usage.md +7 -0
- package/claude/sd-session-start.sh +10 -0
- package/claude/skills/sd-api-review/SKILL.md +89 -0
- package/claude/skills/sd-check/SKILL.md +55 -57
- package/claude/skills/sd-commit/SKILL.md +37 -42
- package/claude/skills/sd-debug/SKILL.md +75 -265
- package/claude/skills/sd-document/SKILL.md +63 -53
- package/claude/skills/sd-document/_common.py +94 -0
- package/claude/skills/sd-document/extract_docx.py +19 -48
- package/claude/skills/sd-document/extract_pdf.py +22 -50
- package/claude/skills/sd-document/extract_pptx.py +17 -40
- package/claude/skills/sd-document/extract_xlsx.py +19 -40
- package/claude/skills/sd-email-analyze/SKILL.md +23 -31
- package/claude/skills/sd-email-analyze/email-analyzer.py +79 -65
- package/claude/skills/sd-init/SKILL.md +133 -0
- package/claude/skills/sd-plan/SKILL.md +69 -120
- package/claude/skills/sd-readme/SKILL.md +106 -131
- package/claude/skills/sd-review/SKILL.md +38 -155
- package/claude/skills/sd-simplify/SKILL.md +59 -0
- package/package.json +3 -2
- package/README.md +0 -297
- package/claude/refs/sd-angular.md +0 -127
- package/claude/refs/sd-code-conventions.md +0 -155
- package/claude/refs/sd-directories.md +0 -7
- package/claude/refs/sd-library-issue.md +0 -7
- package/claude/refs/sd-migration.md +0 -7
- package/claude/refs/sd-orm-v12.md +0 -81
- package/claude/refs/sd-orm.md +0 -23
- package/claude/refs/sd-service.md +0 -5
- package/claude/refs/sd-simplysm-docs.md +0 -52
- package/claude/refs/sd-solid.md +0 -68
- package/claude/refs/sd-workflow.md +0 -25
- package/claude/rules/sd-refs-linker.md +0 -52
- package/claude/sd-statusline.js +0 -296
- package/claude/skills/sd-api-name-review/SKILL.md +0 -154
- package/claude/skills/sd-brainstorm/SKILL.md +0 -215
- package/claude/skills/sd-debug/condition-based-waiting-example.ts +0 -158
- package/claude/skills/sd-debug/condition-based-waiting.md +0 -114
- package/claude/skills/sd-debug/defense-in-depth.md +0 -128
- package/claude/skills/sd-debug/find-polluter.sh +0 -64
- package/claude/skills/sd-debug/root-cause-tracing.md +0 -168
- package/claude/skills/sd-discuss/SKILL.md +0 -91
- package/claude/skills/sd-explore/SKILL.md +0 -118
- package/claude/skills/sd-plan-dev/SKILL.md +0 -294
- package/claude/skills/sd-plan-dev/code-quality-reviewer-prompt.md +0 -49
- package/claude/skills/sd-plan-dev/final-review-prompt.md +0 -50
- package/claude/skills/sd-plan-dev/implementer-prompt.md +0 -60
- package/claude/skills/sd-plan-dev/spec-reviewer-prompt.md +0 -45
- package/claude/skills/sd-review/api-reviewer-prompt.md +0 -75
- package/claude/skills/sd-review/code-reviewer-prompt.md +0 -82
- package/claude/skills/sd-review/convention-checker-prompt.md +0 -61
- package/claude/skills/sd-review/refactoring-analyzer-prompt.md +0 -92
- package/claude/skills/sd-skill/SKILL.md +0 -417
- package/claude/skills/sd-skill/anthropic-best-practices.md +0 -156
- package/claude/skills/sd-skill/cso-guide.md +0 -161
- package/claude/skills/sd-skill/examples/CLAUDE_MD_TESTING.md +0 -200
- package/claude/skills/sd-skill/persuasion-principles.md +0 -220
- package/claude/skills/sd-skill/testing-skills-with-subagents.md +0 -408
- package/claude/skills/sd-skill/writing-guide.md +0 -159
- package/claude/skills/sd-tdd/SKILL.md +0 -385
- package/claude/skills/sd-tdd/testing-anti-patterns.md +0 -317
- package/claude/skills/sd-use/SKILL.md +0 -67
- package/claude/skills/sd-worktree/SKILL.md +0 -78
|
@@ -1,67 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: sd-use
|
|
3
|
-
description: "Route requests to sd-* skills/agents (explicit invocation only)"
|
|
4
|
-
model: haiku
|
|
5
|
-
---
|
|
6
|
-
|
|
7
|
-
# sd-use - Auto Skill Router
|
|
8
|
-
|
|
9
|
-
Analyze user request from ARGUMENTS, select the best matching skill, explain why, then execute it.
|
|
10
|
-
|
|
11
|
-
## Execution Flow
|
|
12
|
-
|
|
13
|
-
1. Read ARGUMENTS
|
|
14
|
-
2. If user names a specific skill, route to that skill directly
|
|
15
|
-
3. Otherwise, match against catalog below
|
|
16
|
-
4. Report selection with reason
|
|
17
|
-
5. Execute immediately
|
|
18
|
-
|
|
19
|
-
## Catalog (execute via `Skill` tool)
|
|
20
|
-
|
|
21
|
-
| Skill | When to select |
|
|
22
|
-
|----------------------|-------------------------------------------------------------------------------------------------------------------------------------------------|
|
|
23
|
-
| `sd-brainstorm` | New feature, component, or behavior change — **creative work before implementation** |
|
|
24
|
-
| `sd-debug` | Bug, test failure, unexpected behavior — **systematic root cause investigation** |
|
|
25
|
-
| `sd-tdd` | Implementing a feature or fixing a bug — **before writing code** |
|
|
26
|
-
| `sd-plan` | Multi-step task with spec/requirements — **planning before code** |
|
|
27
|
-
| `sd-plan-dev` | Already have a plan — **executing implementation plan** |
|
|
28
|
-
| `sd-review` | Code review + refactoring analysis — defects, safety, API design, conventions, complexity, duplication, code structure |
|
|
29
|
-
| `sd-check` | Verify code — typecheck, lint, tests |
|
|
30
|
-
| `sd-commit` | Create a git commit |
|
|
31
|
-
| `sd-readme` | Update a package README.md |
|
|
32
|
-
| `sd-discuss` | Evaluate code design decisions against industry standards and project conventions |
|
|
33
|
-
| `sd-api-name-review` | Review public API naming consistency |
|
|
34
|
-
| `sd-worktree` | Start new work in branch isolation |
|
|
35
|
-
| `sd-skill` | Create or edit skills |
|
|
36
|
-
| `sd-email-analyze` | Analyze, read, or summarize email files (`.eml` or `.msg`) — parsing and attachment extraction |
|
|
37
|
-
| `sd-document` | Read or write document files (`.docx`, `.xlsx`, `.pptx`, `.pdf`) — content extraction, creation, data export |
|
|
38
|
-
|
|
39
|
-
## Selection Rules
|
|
40
|
-
|
|
41
|
-
1. **Explicit skill name** — If user mentions a specific skill name, route to that skill directly
|
|
42
|
-
2. Select **exactly one** skill — the most specific match wins
|
|
43
|
-
3. **Review & Refactor**: "find bugs", "review", "refactor", "improve structure", "remove duplication" → `sd-review`
|
|
44
|
-
4. **Sequential requests**: Route to the **first** skill only. After completion, user can invoke the next
|
|
45
|
-
5. If nothing matches, use **default LLM behavior** and handle the request directly
|
|
46
|
-
6. Pass ARGUMENTS through as the skill's input
|
|
47
|
-
|
|
48
|
-
## Report Format
|
|
49
|
-
|
|
50
|
-
Before executing, output:
|
|
51
|
-
|
|
52
|
-
```
|
|
53
|
-
**Selected**: `{skill-name}`
|
|
54
|
-
**Reason**: {one-line explanation}
|
|
55
|
-
**Tip**: Next time you can call `/{skill-name} {request}` directly.
|
|
56
|
-
```
|
|
57
|
-
|
|
58
|
-
Then execute immediately.
|
|
59
|
-
|
|
60
|
-
If no match:
|
|
61
|
-
|
|
62
|
-
```
|
|
63
|
-
**Selected**: Default LLM
|
|
64
|
-
**Reason**: {one-line explanation}
|
|
65
|
-
```
|
|
66
|
-
|
|
67
|
-
Then handle the request directly.
|
|
@@ -1,78 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: sd-worktree
|
|
3
|
-
description: "Git worktree branch isolation (explicit invocation only)"
|
|
4
|
-
model: haiku
|
|
5
|
-
---
|
|
6
|
-
|
|
7
|
-
# sd-worktree
|
|
8
|
-
|
|
9
|
-
Branch-isolated workflow using git worktrees.
|
|
10
|
-
|
|
11
|
-
## Flow
|
|
12
|
-
|
|
13
|
-
```mermaid
|
|
14
|
-
flowchart TD
|
|
15
|
-
START([sd-worktree invoked]) --> ADD
|
|
16
|
-
|
|
17
|
-
subgraph ADD [add]
|
|
18
|
-
A1["git worktree add .worktrees/NAME -b NAME"]
|
|
19
|
-
A1 -->|fail| HALT
|
|
20
|
-
A1 -->|ok| A2[detect package manager]
|
|
21
|
-
A2 --> A3["pm install (cwd: .worktrees/NAME)"]
|
|
22
|
-
A3 -->|fail| HALT
|
|
23
|
-
A3 -->|ok| A4["cd .worktrees/NAME"]
|
|
24
|
-
end
|
|
25
|
-
|
|
26
|
-
A4 --> WORK["work + commit inside worktree"]
|
|
27
|
-
WORK --> MERGE
|
|
28
|
-
|
|
29
|
-
subgraph MERGE [merge]
|
|
30
|
-
M0["cd PROJECT_ROOT"]
|
|
31
|
-
M0 --> M1["git merge NAME --no-ff (cwd: PROJECT_ROOT)"]
|
|
32
|
-
M1 -->|fail| HALT
|
|
33
|
-
M1 -->|ok| M2[merge complete]
|
|
34
|
-
end
|
|
35
|
-
|
|
36
|
-
M2 --> CLEAN
|
|
37
|
-
|
|
38
|
-
subgraph CLEAN [clean]
|
|
39
|
-
C1{"cwd inside worktree?"}
|
|
40
|
-
C1 -->|yes| HALT
|
|
41
|
-
C1 -->|no| C2["rm -rf .worktrees/NAME (bash)"]
|
|
42
|
-
C2 --> C3["git worktree prune"]
|
|
43
|
-
C3 --> C4["git branch -d NAME"]
|
|
44
|
-
C4 -->|fail| HALT
|
|
45
|
-
C4 -->|ok| C5[done]
|
|
46
|
-
end
|
|
47
|
-
|
|
48
|
-
HALT([HALT - AskUserQuestion])
|
|
49
|
-
```
|
|
50
|
-
|
|
51
|
-
## Rules
|
|
52
|
-
|
|
53
|
-
### HALT
|
|
54
|
-
|
|
55
|
-
When any step reaches **fail** or **HALT**:
|
|
56
|
-
|
|
57
|
-
1. Show the error message to the user as-is
|
|
58
|
-
2. Ask the user how to proceed via `AskUserQuestion`
|
|
59
|
-
3. Do **nothing** until the user responds
|
|
60
|
-
|
|
61
|
-
Manual git merge, git stash, git reset, git clean, or **any workaround is forbidden**. Yolo mode does NOT override HALT.
|
|
62
|
-
|
|
63
|
-
### Worktree location
|
|
64
|
-
|
|
65
|
-
All worktrees MUST be created under **`.worktrees/`** (project root).
|
|
66
|
-
|
|
67
|
-
### Package manager detection
|
|
68
|
-
|
|
69
|
-
| File | PM |
|
|
70
|
-
|---|---|
|
|
71
|
-
| `pnpm-lock.yaml` | pnpm |
|
|
72
|
-
| `yarn.lock` | yarn |
|
|
73
|
-
| `package-lock.json` | npm |
|
|
74
|
-
| `bun.lockb` / `bun.lock` | bun |
|
|
75
|
-
|
|
76
|
-
### clean: use rm -rf
|
|
77
|
-
|
|
78
|
-
`git worktree remove` almost always fails on Windows due to file locks. Use `rm -rf` (bash) + `git worktree prune` instead.
|