Files
bi-agents/.claude/skills/bmad-quick-spec/steps/step-02-investigate.md
Cassel 647cbec54f docs: update all documentation and add AI tooling configs
- Rewrite README.md with current architecture, features and stack
- Update docs/API.md with all current endpoints (corporate, BI, client 360)
- Update docs/ARCHITECTURE.md with cache, modular queries, services, ETL
- Update docs/GUIA-USUARIO.md for all roles (admin, corporate, agente)
- Add docs/INDEX.md documentation index
- Add PROJETO.md comprehensive project reference
- Add BI-CCC-Implementation-Guide.md
- Include AI agent configs (.claude, .agents, .gemini, _bmad)
- Add netbird VPN configuration
- Add status report

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-19 13:29:03 -04:00

141 lines
4.4 KiB
Markdown

---
wipFile: '{implementation_artifacts}/tech-spec-wip.md'
---
# Step 2: Map Technical Constraints & Anchor Points
**Progress: Step 2 of 4** - Next: Generate Plan
## RULES:
- MUST NOT skip steps.
- MUST NOT optimize sequence.
- MUST follow exact instructions.
- MUST NOT generate the full spec yet (that's Step 3).
- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
## CONTEXT:
- Requires `{wipFile}` from Step 1 with the "Problem Statement" defined.
- Focus: Map the problem statement to specific anchor points in the codebase.
- Output: Exact files to touch, classes/patterns to extend, and technical constraints identified.
- Objective: Provide the implementation-ready ground truth for the plan.
## SEQUENCE OF INSTRUCTIONS
### 1. Load Current State
**Read `{wipFile}` and extract:**
- Problem statement and scope from Overview section
- Any context gathered in Step 1
### 2. Execute Investigation Path
**Universal Code Investigation:**
_Isolate deep exploration in sub-agents/tasks where available. Return distilled summaries only to prevent context snowballing._
a) **Build on Step 1's Quick Scan**
Review what was found in Step 1's orient scan. Then ask:
"Based on my quick look, I see [files/patterns found]. Are there other files or directories I should investigate deeply?"
b) **Read and Analyze Code**
For each file/directory provided:
- Read the complete file(s)
- Identify patterns, conventions, coding style
- Note dependencies and imports
- Find related test files
**If NO relevant code is found (Clean Slate):**
- Identify the target directory where the feature should live.
- Scan parent directories for architectural context.
- Identify standard project utilities or boilerplate that SHOULD be used.
- Document this as "Confirmed Clean Slate" - establishing that no legacy constraints exist.
c) **Document Technical Context**
Capture and confirm with user:
- **Tech Stack**: Languages, frameworks, libraries
- **Code Patterns**: Architecture patterns, naming conventions, file structure
- **Files to Modify/Create**: Specific files that will need changes or new files to be created
- **Test Patterns**: How tests are structured, test frameworks used
d) **Look for project-context.md**
If `**/project-context.md` exists and wasn't loaded in Step 1:
- Load it now
- Extract patterns and conventions
- Note any rules that must be followed
### 3. Update WIP File
**Update `{wipFile}` frontmatter:**
```yaml
---
# ... existing frontmatter ...
stepsCompleted: [1, 2]
tech_stack: ['{captured_tech_stack}']
files_to_modify: ['{captured_files}']
code_patterns: ['{captured_patterns}']
test_patterns: ['{captured_test_patterns}']
---
```
**Update the Context for Development section:**
Fill in:
- Codebase Patterns (from investigation)
- Files to Reference table (files reviewed)
- Technical Decisions (any decisions made during investigation)
**Report to user:**
"**Context Gathered:**
- Tech Stack: {tech_stack_summary}
- Files to Modify: {files_count} files identified
- Patterns: {patterns_summary}
- Tests: {test_patterns_summary}"
### 4. Present Checkpoint Menu
Display: "**Select:** [A] Advanced Elicitation [P] Party Mode [C] Continue to Generate Spec (Step 3 of 4)"
**HALT and wait for user selection.**
#### Menu Handling Logic:
- IF A: Invoke the `bmad-advanced-elicitation` skill with current tech-spec content, process enhanced insights, ask user "Accept improvements? (y/n)", if yes update WIP file then redisplay menu, if no keep original then redisplay menu
- IF P: Invoke the `bmad-party-mode` skill with current tech-spec content, process collaborative insights, ask user "Accept changes? (y/n)", if yes update WIP file then redisplay menu, if no keep original then redisplay menu
- IF C: Verify frontmatter updated with `stepsCompleted: [1, 2]`, then read fully and follow: `./step-03-generate.md`
- IF Any other comments or queries: respond helpfully then redisplay menu
#### EXECUTION RULES:
- ALWAYS halt and wait for user input after presenting menu
- ONLY proceed to next step when user selects 'C'
- After A or P execution, return to this menu
---
## REQUIRED OUTPUTS:
- MUST document technical context (stack, patterns, files identified).
- MUST update `{wipFile}` with functional context.
## VERIFICATION CHECKLIST:
- [ ] Technical mapping performed and documented.
- [ ] `stepsCompleted: [1, 2]` set in frontmatter.