superkit-mcp-server 1.0.2 → 1.1.0

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 (116) hide show
  1. package/ARCHITECTURE.md +102 -102
  2. package/README.md +67 -63
  3. package/SUPERKIT.md +168 -168
  4. package/agents/code-archaeologist.md +106 -0
  5. package/agents/coder.md +90 -90
  6. package/agents/data-engineer.md +28 -28
  7. package/agents/devops-engineer.md +242 -0
  8. package/agents/git-manager.md +203 -203
  9. package/agents/orchestrator.md +4 -0
  10. package/agents/penetration-tester.md +188 -0
  11. package/agents/performance-optimizer.md +187 -0
  12. package/agents/planner.md +270 -270
  13. package/agents/qa-automation-engineer.md +103 -0
  14. package/agents/quant-developer.md +32 -28
  15. package/agents/reviewer.md +100 -100
  16. package/agents/scout.md +222 -222
  17. package/agents/tester.md +274 -274
  18. package/agents/ui-designer.md +208 -208
  19. package/build/index.js +53 -1
  20. package/build/tools/validators/__tests__/apiSchema.test.js +23 -23
  21. package/build/tools/validators/__tests__/convertRules.test.js +5 -5
  22. package/build/tools/validators/__tests__/frontendDesign.test.js +12 -12
  23. package/build/tools/validators/__tests__/geoChecker.test.js +19 -19
  24. package/build/tools/validators/__tests__/mobileAudit.test.js +12 -12
  25. package/build/tools/validators/__tests__/reactPerformanceChecker.test.js +17 -17
  26. package/build/tools/validators/__tests__/securityScan.test.js +6 -6
  27. package/build/tools/validators/__tests__/seoChecker.test.js +16 -16
  28. package/build/tools/validators/__tests__/typeCoverage.test.js +14 -14
  29. package/package.json +33 -33
  30. package/skills/meta/README.md +30 -30
  31. package/skills/meta/api-design/SKILL.md +134 -134
  32. package/skills/meta/code-review/SKILL.md +44 -37
  33. package/skills/meta/code-review/checklists/pre-merge.md +25 -25
  34. package/skills/meta/code-review/workflows/architecture-pass.md +26 -26
  35. package/skills/meta/code-review/workflows/performance-pass.md +27 -27
  36. package/skills/meta/code-review/workflows/security-pass.md +29 -29
  37. package/skills/meta/compound-docs/SKILL.md +133 -133
  38. package/skills/meta/debug/SKILL.md +40 -40
  39. package/skills/meta/debug/templates/bug-report.template.md +31 -31
  40. package/skills/meta/debug/workflows/reproduce-issue.md +20 -20
  41. package/skills/meta/docker/SKILL.md +126 -126
  42. package/skills/meta/examples/supabase/SKILL.md +46 -46
  43. package/skills/meta/examples/supabase/references/best-practices.md +319 -319
  44. package/skills/meta/examples/supabase/references/common-patterns.md +373 -373
  45. package/skills/meta/examples/supabase/templates/migration-template.sql +49 -49
  46. package/skills/meta/examples/supabase/templates/rls-policy-template.sql +77 -77
  47. package/skills/meta/examples/supabase/workflows/debugging.md +260 -260
  48. package/skills/meta/examples/supabase/workflows/migration-workflow.md +211 -211
  49. package/skills/meta/examples/supabase/workflows/rls-policies.md +244 -244
  50. package/skills/meta/examples/supabase/workflows/schema-design.md +321 -321
  51. package/skills/meta/file-todos/SKILL.md +88 -88
  52. package/skills/meta/mobile/SKILL.md +140 -140
  53. package/skills/meta/nextjs/SKILL.md +101 -101
  54. package/skills/meta/performance/SKILL.md +130 -130
  55. package/skills/meta/react-patterns/SKILL.md +83 -83
  56. package/skills/meta/security/SKILL.md +114 -114
  57. package/skills/meta/session-resume/SKILL.md +96 -96
  58. package/skills/meta/tailwind/SKILL.md +139 -139
  59. package/skills/meta/testing/SKILL.md +43 -43
  60. package/skills/meta/testing/references/vitest-patterns.md +45 -45
  61. package/skills/meta/testing/templates/component-test.template.tsx +37 -37
  62. package/skills/tech/alpha-vantage/SKILL.md +142 -0
  63. package/skills/tech/alpha-vantage/references/commodities.md +153 -0
  64. package/skills/tech/alpha-vantage/references/economic-indicators.md +158 -0
  65. package/skills/tech/alpha-vantage/references/forex-crypto.md +154 -0
  66. package/skills/tech/alpha-vantage/references/fundamentals.md +223 -0
  67. package/skills/tech/alpha-vantage/references/intelligence.md +138 -0
  68. package/skills/tech/alpha-vantage/references/options.md +93 -0
  69. package/skills/tech/alpha-vantage/references/technical-indicators.md +374 -0
  70. package/skills/tech/alpha-vantage/references/time-series.md +157 -0
  71. package/skills/tech/financial-modeling/SKILL.md +18 -0
  72. package/skills/tech/financial-modeling/skills/3-statements/SKILL.md +368 -0
  73. package/skills/tech/financial-modeling/skills/3-statements/references/formatting.md +118 -0
  74. package/skills/tech/financial-modeling/skills/3-statements/references/formulas.md +292 -0
  75. package/skills/tech/financial-modeling/skills/3-statements/references/sec-filings.md +125 -0
  76. package/skills/tech/financial-modeling/skills/dcf-model/SKILL.md +1211 -0
  77. package/skills/tech/financial-modeling/skills/dcf-model/TROUBLESHOOTING.md +40 -0
  78. package/skills/tech/financial-modeling/skills/dcf-model/requirements.txt +8 -0
  79. package/skills/tech/financial-modeling/skills/dcf-model/scripts/validate_dcf.py +292 -0
  80. package/skills/tech/financial-modeling/skills/lbo-model/SKILL.md +236 -0
  81. package/skills/tech/financial-modeling/skills/merger-model/SKILL.md +108 -0
  82. package/skills/tech/intelligent-routing/SKILL.md +5 -5
  83. package/workflows/README.md +191 -191
  84. package/workflows/adr.md +174 -174
  85. package/workflows/changelog.md +74 -74
  86. package/workflows/compound.md +323 -323
  87. package/workflows/compound_health.md +74 -74
  88. package/workflows/create-agent-skill.md +139 -139
  89. package/workflows/cycle.md +144 -144
  90. package/workflows/deploy-docs.md +84 -84
  91. package/workflows/development-rules.md +37 -37
  92. package/workflows/doc.md +95 -95
  93. package/workflows/documentation-management.md +29 -29
  94. package/workflows/explore.md +146 -146
  95. package/workflows/generate_command.md +106 -106
  96. package/workflows/heal-skill.md +97 -97
  97. package/workflows/housekeeping.md +229 -229
  98. package/workflows/kit-setup.md +102 -102
  99. package/workflows/map-codebase.md +78 -0
  100. package/workflows/orchestration-protocol.md +38 -38
  101. package/workflows/plan-compound.md +439 -433
  102. package/workflows/plan_review.md +269 -248
  103. package/workflows/primary-workflow.md +32 -32
  104. package/workflows/promote_pattern.md +86 -86
  105. package/workflows/release-docs.md +82 -82
  106. package/workflows/report-bug.md +135 -135
  107. package/workflows/reproduce-bug.md +118 -118
  108. package/workflows/resolve_pr.md +133 -133
  109. package/workflows/resolve_todo.md +128 -128
  110. package/workflows/review-compound.md +376 -359
  111. package/workflows/skill-review.md +127 -127
  112. package/workflows/specs.md +257 -257
  113. package/workflows/triage-sprint.md +102 -102
  114. package/workflows/triage.md +152 -152
  115. package/workflows/work.md +399 -399
  116. package/workflows/xcode-test.md +93 -93
package/workflows/doc.md CHANGED
@@ -1,95 +1,95 @@
1
- ---
2
- description: Update folder-level documentation and component changelogs. Use after modifying components or adding new ones.
3
- ---
4
-
5
- # /doc - Update Folder Documentation
6
-
7
- Maintain living, component-level documentation in folder README files.
8
-
9
- > **Why /doc?** Component-level context evaporates quickly. Documenting the "why" and "when" of changes ensures the codebase remains understandable as it grows.
10
-
11
- ## When To Use
12
-
13
- - After modifying a component's core logic
14
- - When adding a new file to a directory
15
- - As a handoff step in the `/review` workflow
16
- - When referencing a new ADR in a component
17
-
18
- ---
19
-
20
- ## Workflow
21
-
22
- ### Step 1: Identify Target Folder
23
-
24
- Identify which folder's `README.md` needs updating.
25
-
26
- ```bash
27
- # If not provided, list modified folders
28
- git diff main --name-only | xargs -n1 dirname | sort -u
29
- ```
30
-
31
- ### Step 2: Read Existing README
32
-
33
- Check if a `README.md` exists. If not, bootstrap it using the template.
34
-
35
- ```bash
36
- # Check for README
37
- ls {folder_path}/README.md
38
-
39
- # If missing, use bootstrap script
40
- ./scripts/bootstrap-folder-docs.sh {folder_path}
41
- ```
42
-
43
- ### Step 3: Update Components Table
44
-
45
- If a new component was added, ensure it's in the table.
46
-
47
- | Component | Purpose | Status |
48
- |-----------|---------|--------|
49
- | `NewComponent.tsx` | {Purpose} | `🏗️ Building` |
50
-
51
- ### Step 4: Add Tiered Component Details
52
-
53
- Update the `## Component Details` section with depth based on the component's [Tier](../../docs/templates/component-tier-guide.md).
54
-
55
- - **🔴 Critical**: Full detail (Purpose, Functionality, Tech, Error Handling, Usage).
56
- - **🟡 Supporting**: Brief purpose and key exports.
57
- - **🟢 Generated**: One-line description.
58
-
59
- ### Step 5: Add Changelog Entry
60
-
61
- Document the change, including the "why" and relevant references.
62
-
63
- ```markdown
64
- ### {YYYY-MM-DD}
65
- - {Change description} (Response to: {Link to TODO/Spec/ADR})
66
- ```
67
-
68
- ### Step 6: Verify Links
69
-
70
- Ensure any newly added links to ADRs or other documentation are valid.
71
-
72
- ### Step 7: Integration Audit (Sibling Parity)
73
-
74
- If you created a NEW folder, ensure it is covered by the validation system:
75
- 1. Run `./scripts/discover-undocumented-folders.sh` to verify discovery.
76
- 2. Run `./scripts/validate-folder-docs.sh` to verify structure.
77
- 3. If new patterns were established, update `docs/solutions/patterns/critical-patterns.md`.
78
-
79
- ---
80
-
81
- ## Quality Guidelines
82
-
83
- - ✅ Focus on the **Why**, not just the **What**.
84
- - ✅ Keep the components table updated and sorted.
85
- - ✅ Link to relevant ADRs for architectural decisions.
86
- - ✅ Ensure changelog entries are dated and specific.
87
-
88
- ---
89
-
90
- ## References
91
-
92
- - Template: `docs/templates/folder-readme-template.md`
93
- - Tier Guide: `docs/templates/component-tier-guide.md`
94
- - Documentation Map: `docs/architecture/codebase-map.md`
95
- - ADRs: `docs/decisions/`
1
+ ---
2
+ description: Update folder-level documentation and component changelogs. Use after modifying components or adding new ones.
3
+ ---
4
+
5
+ # /doc - Update Folder Documentation
6
+
7
+ Maintain living, component-level documentation in folder README files.
8
+
9
+ > **Why /doc?** Component-level context evaporates quickly. Documenting the "why" and "when" of changes ensures the codebase remains understandable as it grows.
10
+
11
+ ## When To Use
12
+
13
+ - After modifying a component's core logic
14
+ - When adding a new file to a directory
15
+ - As a handoff step in the `/review` workflow
16
+ - When referencing a new ADR in a component
17
+
18
+ ---
19
+
20
+ ## Workflow
21
+
22
+ ### Step 1: Identify Target Folder
23
+
24
+ Identify which folder's `README.md` needs updating.
25
+
26
+ ```bash
27
+ # If not provided, list modified folders
28
+ git diff main --name-only | xargs -n1 dirname | sort -u
29
+ ```
30
+
31
+ ### Step 2: Read Existing README
32
+
33
+ Check if a `README.md` exists. If not, bootstrap it using the template.
34
+
35
+ ```bash
36
+ # Check for README
37
+ ls {folder_path}/README.md
38
+
39
+ # If missing, use bootstrap script
40
+ ./scripts/bootstrap-folder-docs.sh {folder_path}
41
+ ```
42
+
43
+ ### Step 3: Update Components Table
44
+
45
+ If a new component was added, ensure it's in the table.
46
+
47
+ | Component | Purpose | Status |
48
+ |-----------|---------|--------|
49
+ | `NewComponent.tsx` | {Purpose} | `🏗️ Building` |
50
+
51
+ ### Step 4: Add Tiered Component Details
52
+
53
+ Update the `## Component Details` section with depth based on the component's [Tier](../../docs/templates/component-tier-guide.md).
54
+
55
+ - **🔴 Critical**: Full detail (Purpose, Functionality, Tech, Error Handling, Usage).
56
+ - **🟡 Supporting**: Brief purpose and key exports.
57
+ - **🟢 Generated**: One-line description.
58
+
59
+ ### Step 5: Add Changelog Entry
60
+
61
+ Document the change, including the "why" and relevant references.
62
+
63
+ ```markdown
64
+ ### {YYYY-MM-DD}
65
+ - {Change description} (Response to: {Link to TODO/Spec/ADR})
66
+ ```
67
+
68
+ ### Step 6: Verify Links
69
+
70
+ Ensure any newly added links to ADRs or other documentation are valid.
71
+
72
+ ### Step 7: Integration Audit (Sibling Parity)
73
+
74
+ If you created a NEW folder, ensure it is covered by the validation system:
75
+ 1. Run `./scripts/discover-undocumented-folders.sh` to verify discovery.
76
+ 2. Run `./scripts/validate-folder-docs.sh` to verify structure.
77
+ 3. If new patterns were established, update `docs/solutions/patterns/critical-patterns.md`.
78
+
79
+ ---
80
+
81
+ ## Quality Guidelines
82
+
83
+ - ✅ Focus on the **Why**, not just the **What**.
84
+ - ✅ Keep the components table updated and sorted.
85
+ - ✅ Link to relevant ADRs for architectural decisions.
86
+ - ✅ Ensure changelog entries are dated and specific.
87
+
88
+ ---
89
+
90
+ ## References
91
+
92
+ - Template: `docs/templates/folder-readme-template.md`
93
+ - Tier Guide: `docs/templates/component-tier-guide.md`
94
+ - Documentation Map: `docs/architecture/codebase-map.md`
95
+ - ADRs: `docs/decisions/`
@@ -1,29 +1,29 @@
1
- # Documentation Management
2
-
3
- ## When to Update Docs
4
-
5
- - New features added
6
- - API changes
7
- - Breaking changes
8
- - Configuration updates
9
-
10
- ## Documentation Locations
11
-
12
- | File | Purpose |
13
- |------|---------|
14
- | `README.md` | Project overview, install |
15
- | `CHANGELOG.md` | Version history |
16
- | `doc.md` | Gemini CLI reference |
17
- | `GEMINI.md` | AI context |
18
-
19
- ## Standards
20
-
21
- ### Code Comments
22
- - JSDoc for public functions
23
- - Inline comments for complex logic
24
- - TODO/FIXME with issue links
25
-
26
- ### API Documentation
27
- - Input/output types
28
- - Error cases
29
- - Examples
1
+ # Documentation Management
2
+
3
+ ## When to Update Docs
4
+
5
+ - New features added
6
+ - API changes
7
+ - Breaking changes
8
+ - Configuration updates
9
+
10
+ ## Documentation Locations
11
+
12
+ | File | Purpose |
13
+ |------|---------|
14
+ | `README.md` | Project overview, install |
15
+ | `CHANGELOG.md` | Version history |
16
+ | `doc.md` | Gemini CLI reference |
17
+ | `GEMINI.md` | AI context |
18
+
19
+ ## Standards
20
+
21
+ ### Code Comments
22
+ - JSDoc for public functions
23
+ - Inline comments for complex logic
24
+ - TODO/FIXME with issue links
25
+
26
+ ### API Documentation
27
+ - Input/output types
28
+ - Error cases
29
+ - Examples
@@ -1,146 +1,146 @@
1
- ---
2
- description: Deep investigation before planning. Use for best practices, implications, and systematic analysis.
3
- ---
4
-
5
- # /explore - Research and Deep Thinking
6
-
7
- Conduct a deep, systematic pre-planning investigation to gather industry best practices, analyze multi-order effects, and understand complex problems before committing to a formal plan.
8
-
9
- > **Why explore?** A plan built on assumptions is a liability. 30 minutes of deep exploration compounds into architectural excellence and prevents costly rework.
10
-
11
- ## When To Use
12
-
13
- - Before any `/plan` for complex features
14
- - When investigating unfamiliar technologies or patterns
15
- - For bugs requiring deep root-cause analysis
16
- - Anytime you think: "I need to understand this better before I decide."
17
-
18
- ---
19
-
20
- ## Workflow
21
-
22
- ### Step 0: Search & Log
23
-
24
- ```bash
25
- // turbo
26
- ./scripts/log-workflow.sh "/explore" "$$"
27
- ./scripts/compound-search.sh "exploration"
28
- ```
29
-
30
- ### Step 1: Search Existing Knowledge (MANDATORY)
31
-
32
- > [!CAUTION]
33
- > **BLOCKING STEP.** Search both solutions AND prior explorations.
34
-
35
- ```bash
36
- // turbo
37
- ./scripts/compound-search.sh "{keywords}"
38
- ls docs/explorations/*.md | grep "{keyword}"
39
- ```
40
-
41
- ### Step 1.5: Define the Question
42
-
43
- State exactly what we are trying to understand.
44
- *Example: "What is the most robust way to handle multi-session task orchestration in a stateless agentic system?"*
45
-
46
- ### Step 2: Scope & Time-box
47
-
48
- Set boundaries to avoid rabbit holes.
49
- - **Time-box:** How long will we explore? (e.g., 30m, 1h, 1 day)
50
- - **Success Criteria:** What specific answer or evidence do we need?
51
-
52
- ---
53
-
54
- ### Step 3: Internet Research (Recommended)
55
-
56
- > [!TIP]
57
- > **Best Practice.** Verification of industry standards is highly encouraged.
58
-
59
- ```bash
60
- // turbo
61
- search_web("{topic} best practices software engineering")
62
- search_web("{topic} common pitfalls and anti-patterns")
63
- search_web("{topic} design patterns comparison")
64
- ```
65
-
66
- **Summarize industry standards in the exploration artifact.**
67
-
68
- ---
69
-
70
- ### Step 4: Deep Systematic Analysis
71
-
72
- Apply multi-order thinking and holistic analysis.
73
-
74
- **Multi-Order Consequences ("And Then What?"):**
75
- - **1st order:** Immediate impact of the potential change.
76
- - **2nd order:** What depends on those changes?
77
- - **3rd order:** Cascading effects (drift, technical debt).
78
- - **4th order:** Long-term cultural or architectural shifts.
79
-
80
- **Stakeholder Impact Matrix:**
81
- Assess impact on End Users, Developers, Ops/Support, and Downstream Systems.
82
-
83
- ---
84
-
85
- ### Step 5: Document Findings
86
-
87
- Create the exploration file at `docs/explorations/{topic}-{YYYYMMDD}.md`.
88
- Use the template at `docs/explorations/templates/exploration-template.md`.
89
-
90
- ### Step 6: Long-Term Implications Check
91
-
92
- - **6 months/1 year:** How will this age?
93
- - **Reversibility:** Can we undo this? (Type 1 vs Type 2 decisions)
94
- - **Technical Debt:** Does this create or pay down debt?
95
-
96
- ---
97
-
98
- ### Step 7: Decision Gate
99
-
100
- Decide on the next logical action:
101
- 1. **Proceed to /plan:** We have enough understanding to build.
102
- 2. **Proceed to /specs:** This is a major iniciativa.
103
- 3. **Create Todo:** Defer based on findings.
104
- 4. **No Action:** Learning captured, no change needed.
105
- 5. **Escalate:** Needs human stakeholder input.
106
-
107
- ### Phase 5: Completion & Handoff
108
-
109
- #### Step 1: Establish Terminal UI State
110
-
111
- ```javascript
112
- await task_boundary({
113
- TaskName: "[COMPLETED] Exploration: {Topic}",
114
- TaskStatus: "Exploration complete. Offering next steps.",
115
- Mode: "VERIFICATION",
116
- TaskSummary: "Completed deep exploration of {topic}. Findings documented in docs/explorations/{filename}. Decision: {Gate Decision}."
117
- });
118
- ```
119
-
120
- #### Step 2: Mandatory Handoff
121
-
122
- ```bash
123
- ✓ Exploration complete
124
-
125
- Next steps:
126
- 1. /plan - Create plan based on findings (if proceed)
127
- 2. /specs - Create specification (if major initiative)
128
- 3. /triage - File found issues as todos
129
- ```
130
-
131
- ---
132
-
133
- ## Quality Guidelines
134
-
135
- - ✅ Internet search for industry standards is encouraged.
136
- - ✅ Document "And Then What?" at least to 3rd order.
137
- - ✅ Explicitly state when something is a "Type 1" (irreversible) decision.
138
- - ✅ Link findings back to codebase patterns.
139
-
140
- ---
141
-
142
- ## References
143
-
144
- - Explorations directory: `docs/explorations/`
145
- - Solutions: `docs/solutions/`
146
- - Pattern #11: Explore Before Plan
1
+ ---
2
+ description: Deep investigation before planning. Use for best practices, implications, and systematic analysis.
3
+ ---
4
+
5
+ # /explore - Research and Deep Thinking
6
+
7
+ Conduct a deep, systematic pre-planning investigation to gather industry best practices, analyze multi-order effects, and understand complex problems before committing to a formal plan.
8
+
9
+ > **Why explore?** A plan built on assumptions is a liability. 30 minutes of deep exploration compounds into architectural excellence and prevents costly rework.
10
+
11
+ ## When To Use
12
+
13
+ - Before any `/plan` for complex features
14
+ - When investigating unfamiliar technologies or patterns
15
+ - For bugs requiring deep root-cause analysis
16
+ - Anytime you think: "I need to understand this better before I decide."
17
+
18
+ ---
19
+
20
+ ## Workflow
21
+
22
+ ### Step 0: Search & Log
23
+
24
+ ```bash
25
+ // turbo
26
+ ./scripts/log-workflow.sh "/explore" "$$"
27
+ ./scripts/compound-search.sh "exploration"
28
+ ```
29
+
30
+ ### Step 1: Search Existing Knowledge (MANDATORY)
31
+
32
+ > [!CAUTION]
33
+ > **BLOCKING STEP.** Search both solutions AND prior explorations.
34
+
35
+ ```bash
36
+ // turbo
37
+ ./scripts/compound-search.sh "{keywords}"
38
+ ls docs/explorations/*.md | grep "{keyword}"
39
+ ```
40
+
41
+ ### Step 1.5: Define the Question
42
+
43
+ State exactly what we are trying to understand.
44
+ *Example: "What is the most robust way to handle multi-session task orchestration in a stateless agentic system?"*
45
+
46
+ ### Step 2: Scope & Time-box
47
+
48
+ Set boundaries to avoid rabbit holes.
49
+ - **Time-box:** How long will we explore? (e.g., 30m, 1h, 1 day)
50
+ - **Success Criteria:** What specific answer or evidence do we need?
51
+
52
+ ---
53
+
54
+ ### Step 3: Internet Research (Recommended)
55
+
56
+ > [!TIP]
57
+ > **Best Practice.** Verification of industry standards is highly encouraged.
58
+
59
+ ```bash
60
+ // turbo
61
+ search_web("{topic} best practices software engineering")
62
+ search_web("{topic} common pitfalls and anti-patterns")
63
+ search_web("{topic} design patterns comparison")
64
+ ```
65
+
66
+ **Summarize industry standards in the exploration artifact.**
67
+
68
+ ---
69
+
70
+ ### Step 4: Deep Systematic Analysis
71
+
72
+ Apply multi-order thinking and holistic analysis.
73
+
74
+ **Multi-Order Consequences ("And Then What?"):**
75
+ - **1st order:** Immediate impact of the potential change.
76
+ - **2nd order:** What depends on those changes?
77
+ - **3rd order:** Cascading effects (drift, technical debt).
78
+ - **4th order:** Long-term cultural or architectural shifts.
79
+
80
+ **Stakeholder Impact Matrix:**
81
+ Assess impact on End Users, Developers, Ops/Support, and Downstream Systems.
82
+
83
+ ---
84
+
85
+ ### Step 5: Document Findings
86
+
87
+ Create the exploration file at `docs/explorations/{topic}-{YYYYMMDD}.md`.
88
+ Use the template at `docs/explorations/templates/exploration-template.md`.
89
+
90
+ ### Step 6: Long-Term Implications Check
91
+
92
+ - **6 months/1 year:** How will this age?
93
+ - **Reversibility:** Can we undo this? (Type 1 vs Type 2 decisions)
94
+ - **Technical Debt:** Does this create or pay down debt?
95
+
96
+ ---
97
+
98
+ ### Step 7: Decision Gate
99
+
100
+ Decide on the next logical action:
101
+ 1. **Proceed to /plan:** We have enough understanding to build.
102
+ 2. **Proceed to /specs:** This is a major iniciativa.
103
+ 3. **Create Todo:** Defer based on findings.
104
+ 4. **No Action:** Learning captured, no change needed.
105
+ 5. **Escalate:** Needs human stakeholder input.
106
+
107
+ ### Phase 5: Completion & Handoff
108
+
109
+ #### Step 1: Establish Terminal UI State
110
+
111
+ ```javascript
112
+ await task_boundary({
113
+ TaskName: "[COMPLETED] Exploration: {Topic}",
114
+ TaskStatus: "Exploration complete. Offering next steps.",
115
+ Mode: "VERIFICATION",
116
+ TaskSummary: "Completed deep exploration of {topic}. Findings documented in docs/explorations/{filename}. Decision: {Gate Decision}."
117
+ });
118
+ ```
119
+
120
+ #### Step 2: Mandatory Handoff
121
+
122
+ ```bash
123
+ ✓ Exploration complete
124
+
125
+ Next steps:
126
+ 1. /plan - Create plan based on findings (if proceed)
127
+ 2. /specs - Create specification (if major initiative)
128
+ 3. /triage - File found issues as todos
129
+ ```
130
+
131
+ ---
132
+
133
+ ## Quality Guidelines
134
+
135
+ - ✅ Internet search for industry standards is encouraged.
136
+ - ✅ Document "And Then What?" at least to 3rd order.
137
+ - ✅ Explicitly state when something is a "Type 1" (irreversible) decision.
138
+ - ✅ Link findings back to codebase patterns.
139
+
140
+ ---
141
+
142
+ ## References
143
+
144
+ - Explorations directory: `docs/explorations/`
145
+ - Solutions: `docs/solutions/`
146
+ - Pattern #11: Explore Before Plan