bms-speckit-plugin 3.2.0 → 3.4.0

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 (2) hide show
  1. package/package.json +1 -1
  2. package/skills/speckit/SKILL.md +16 -40
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "bms-speckit-plugin",
3
- "version": "3.2.0",
3
+ "version": "3.4.0",
4
4
  "description": "Single-command automated development pipeline: /bms-speckit takes requirements and runs constitution → specify → plan → tasks → analyze → implement → verify",
5
5
  "files": [
6
6
  ".claude-plugin/",
package/skills/speckit/SKILL.md CHANGED
@@ -8,58 +8,34 @@ allowed-tools: Read, Write, Edit, Bash, Glob, Grep, Skill, Agent, WebSearch, Web
8
8
 
9
9
  # BMS Speckit — Automated Development Pipeline
10
10
 
11
- Takes a single requirement and runs the complete engineering workflow by calling speckit skills. Do NOT ask for confirmation between steps.
11
+ Execute the following steps in exact order. Do NOT ask for confirmation between steps.
12
12
 
13
- ## Step 1: Constitution
13
+ ## Phase 1: Specification & Planning (run in subagent)
14
14
 
15
- Invoke `/speckit:constitution` with:
15
+ Dispatch a subagent to run Steps 1-7 serially. This keeps the main context window clean for implementation.
16
16
 
17
- Establish and enforce a comprehensive set of engineering principles that prioritize high code quality, strict adherence to Test-Driven Development (TDD) practices, and well-defined testing standards across unit, component, integration, and API levels to ensure system reliability and maintainability; maintain a consistent, user-friendly, and professional user interface aligned with strong user experience (UX) guidelines; optimize application performance through efficient architecture and resource management; enforce disciplined version control practices with frequent, atomic commits to minimize risk and improve traceability; promote the development and reuse of modular components and functions while centralizing business logic to avoid duplication and ensure consistency; provide clear, informative user feedback and progress reporting throughout system interactions; and leverage all available tools, frameworks, and domain-specific expertise to support developers in delivering robust, scalable, and high-quality applications.
17
+ The subagent should execute these steps in order:
18
18
 
19
- ## Step 2: Specify
19
+ 1. `/speckit.constitution` Establish and enforce a comprehensive set of engineering principles that prioritize high code quality, strict adherence to Test-Driven Development (TDD) practices, and well-defined testing standards across unit, component, integration, and API levels to ensure system reliability and maintainability; maintain a consistent, user-friendly, and professional user interface aligned with strong user experience (UX) guidelines; optimize application performance through efficient architecture and resource management; enforce disciplined version control practices with frequent, atomic commits to minimize risk and improve traceability; promote the development and reuse of modular components and functions while centralizing business logic to avoid duplication and ensure consistency; provide clear, informative user feedback and progress reporting throughout system interactions; and leverage all available tools, frameworks, and domain-specific expertise to support developers in delivering robust, scalable, and high-quality applications.
20
20
 
21
- Invoke `/speckit:specify` with: $ARGUMENTS
21
+ 2. Make sure that CLAUDE.md complies with the constitution above. Update CLAUDE.md if needed.
22
22
 
23
- ## Step 3: Plan
23
+ 3. `/speckit.specify` $ARGUMENTS
24
24
 
25
- Invoke `/speckit:plan`
25
+ 4. `/speckit.plan`
26
26
 
27
- ## Step 4: Compact
27
+ 5. `/speckit.tasks`
28
28
 
29
- Run `/compact` to free context window.
29
+ 6. `/speckit.analyze`
30
30
 
31
- ## Step 5: Tasks
31
+ 7. Commit and push code.
32
32
 
33
- Invoke `/speckit:tasks`
33
+ The subagent should return: feature name, number of tasks created, and the path to tasks.md.
34
34
 
35
- ## Step 6: Analyze
35
+ ## Phase 2: Implementation (run in main context)
36
36
 
37
- Invoke `/speckit:analyze`
37
+ After the subagent completes:
38
38
 
39
- ## Step 7: Commit and push
39
+ 8. `/compact`
40
40
 
41
- Commit all spec files and push to remote if configured.
42
-
43
- ## Step 8: Compact
44
-
45
- Run `/compact` to free context window before implementation.
46
-
47
- ## Step 9: Implement with ralph-loop
48
-
49
- ```
50
- /ralph-loop:ralph-loop "use skill /speckit:implement until all tasks in specs/*/tasks.md are finished; do not ask for any confirmation; once all tasks are done, use skill /speckit:analyze to recheck and update tasks, accept any recommendations, and output <promise>FINISHED</promise> only after all tasks are completed and revalidated" --completion-promise "FINISHED" --max-iterations 10
51
- ```
52
-
53
- ## After ralph-loop completes
54
-
55
- Output a final summary:
56
- - What was built
57
- - Total tests passing
58
- - Files created/modified
59
- - How to run the application
60
-
61
- ## CRITICAL RULES
62
- - Do NOT ask for confirmation between steps
63
- - Each step calls the speckit skill directly
64
- - Use MCP tools if available (bms-session for database access)
65
- - Push code if git remote is configured
41
+ 9. `/ralph-loop:ralph-loop "use skill speckit.implement until all tasks in specs/*/tasks.md are finished;do not ask for any confirmation; once all tasks are done, use skill speckit.analyze to recheck and update tasks, accept any recommendations, and output <promise>FINISHED</promise> only after all tasks are completed and revalidated" --completion-promise "FINISHED" --max-iterations 10