@fro.bot/systematic 1.21.3 → 1.22.1
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/agents/research/learnings-researcher.md +1 -1
- package/commands/ce/brainstorm.md +145 -0
- package/commands/ce/compound.md +240 -0
- package/commands/ce/plan.md +636 -0
- package/commands/ce/review.md +525 -0
- package/commands/ce/work.md +456 -0
- package/commands/create-agent-skill.md +1 -3
- package/commands/deepen-plan.md +8 -8
- package/commands/heal-skill.md +1 -3
- package/commands/lfg.md +0 -1
- package/commands/slfg.md +0 -1
- package/commands/test-xcode.md +1 -2
- package/commands/workflows/brainstorm.md +23 -7
- package/commands/workflows/compound.md +5 -235
- package/commands/workflows/plan.md +4 -619
- package/commands/workflows/review.md +5 -524
- package/commands/workflows/work.md +5 -465
- package/package.json +2 -2
- package/skills/brainstorming/SKILL.md +0 -1
- package/skills/compound-docs/SKILL.md +4 -4
- package/skills/create-agent-skills/workflows/add-workflow.md +6 -0
- package/skills/create-agent-skills/workflows/create-new-skill.md +8 -2
- package/skills/create-agent-skills/workflows/get-guidance.md +1 -1
- package/skills/document-review/SKILL.md +0 -1
- package/skills/proof/SKILL.md +185 -0
- package/skills/setup/SKILL.md +10 -4
|
@@ -1,240 +1,10 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: workflows:compound
|
|
3
|
-
description:
|
|
4
|
-
argument-hint:
|
|
3
|
+
description: "[DEPRECATED] Use /ce:compound instead — renamed for clarity."
|
|
4
|
+
argument-hint: "[optional: brief context about the fix]"
|
|
5
|
+
disable-model-invocation: true
|
|
5
6
|
---
|
|
6
7
|
|
|
7
|
-
|
|
8
|
+
NOTE: /workflows:compound is deprecated. Please use /ce:compound instead. This alias will be removed in a future version.
|
|
8
9
|
|
|
9
|
-
|
|
10
|
-
|
|
11
|
-
## Purpose
|
|
12
|
-
|
|
13
|
-
Captures problem solutions while context is fresh, creating structured documentation in `docs/solutions/` with YAML frontmatter for searchability and future reference. Uses parallel subagents for maximum efficiency.
|
|
14
|
-
|
|
15
|
-
**Why "compound"?** Each documented solution compounds your team's knowledge. The first time you solve a problem takes research. Document it, and the next occurrence takes minutes. Knowledge compounds.
|
|
16
|
-
|
|
17
|
-
## Usage
|
|
18
|
-
|
|
19
|
-
```bash
|
|
20
|
-
/workflows:compound # Document the most recent fix
|
|
21
|
-
/workflows:compound [brief context] # Provide additional context hint
|
|
22
|
-
```
|
|
23
|
-
|
|
24
|
-
## Execution Strategy: Two-Phase Orchestration
|
|
25
|
-
|
|
26
|
-
<critical_requirement>
|
|
27
|
-
**Only ONE file gets written - the final documentation.**
|
|
28
|
-
|
|
29
|
-
Phase 1 subagents return TEXT DATA to the orchestrator. They must NOT use Write, Edit, or create any files. Only the orchestrator (Phase 2) writes the final documentation file.
|
|
30
|
-
</critical_requirement>
|
|
31
|
-
|
|
32
|
-
### Phase 1: Parallel Research
|
|
33
|
-
|
|
34
|
-
<parallel_tasks>
|
|
35
|
-
|
|
36
|
-
Launch these subagents IN PARALLEL. Each returns text data to the orchestrator.
|
|
37
|
-
|
|
38
|
-
#### 1. **Context Analyzer**
|
|
39
|
-
- Extracts conversation history
|
|
40
|
-
- Identifies problem type, component, symptoms
|
|
41
|
-
- Validates against schema
|
|
42
|
-
- Returns: YAML frontmatter skeleton
|
|
43
|
-
|
|
44
|
-
#### 2. **Solution Extractor**
|
|
45
|
-
- Analyzes all investigation steps
|
|
46
|
-
- Identifies root cause
|
|
47
|
-
- Extracts working solution with code examples
|
|
48
|
-
- Returns: Solution content block
|
|
49
|
-
|
|
50
|
-
#### 3. **Related Docs Finder**
|
|
51
|
-
- Searches `docs/solutions/` for related documentation
|
|
52
|
-
- Identifies cross-references and links
|
|
53
|
-
- Finds related GitHub issues
|
|
54
|
-
- Returns: Links and relationships
|
|
55
|
-
|
|
56
|
-
#### 4. **Prevention Strategist**
|
|
57
|
-
- Develops prevention strategies
|
|
58
|
-
- Creates best practices guidance
|
|
59
|
-
- Generates test cases if applicable
|
|
60
|
-
- Returns: Prevention/testing content
|
|
61
|
-
|
|
62
|
-
#### 5. **Category Classifier**
|
|
63
|
-
- Determines optimal `docs/solutions/` category
|
|
64
|
-
- Validates category against schema
|
|
65
|
-
- Suggests filename based on slug
|
|
66
|
-
- Returns: Final path and filename
|
|
67
|
-
|
|
68
|
-
</parallel_tasks>
|
|
69
|
-
|
|
70
|
-
### Phase 2: Assembly & Write
|
|
71
|
-
|
|
72
|
-
<sequential_tasks>
|
|
73
|
-
|
|
74
|
-
**WAIT for all Phase 1 subagents to complete before proceeding.**
|
|
75
|
-
|
|
76
|
-
The orchestrating agent (main conversation) performs these steps:
|
|
77
|
-
|
|
78
|
-
1. Collect all text results from Phase 1 subagents
|
|
79
|
-
2. Assemble complete markdown file from the collected pieces
|
|
80
|
-
3. Validate YAML frontmatter against schema
|
|
81
|
-
4. Create directory if needed: `mkdir -p docs/solutions/[category]/`
|
|
82
|
-
5. Write the SINGLE final file: `docs/solutions/[category]/[filename].md`
|
|
83
|
-
|
|
84
|
-
</sequential_tasks>
|
|
85
|
-
|
|
86
|
-
### Phase 3: Optional Enhancement
|
|
87
|
-
|
|
88
|
-
**WAIT for Phase 2 to complete before proceeding.**
|
|
89
|
-
|
|
90
|
-
<parallel_tasks>
|
|
91
|
-
|
|
92
|
-
Based on problem type, optionally invoke specialized agents to review the documentation:
|
|
93
|
-
|
|
94
|
-
- **performance_issue** → `performance-oracle`
|
|
95
|
-
- **security_issue** → `security-sentinel`
|
|
96
|
-
- **database_issue** → `data-integrity-guardian`
|
|
97
|
-
- **test_failure** → `cora-test-reviewer`
|
|
98
|
-
- Any code-heavy issue → `kieran-rails-reviewer` + `code-simplicity-reviewer`
|
|
99
|
-
|
|
100
|
-
</parallel_tasks>
|
|
101
|
-
|
|
102
|
-
## What It Captures
|
|
103
|
-
|
|
104
|
-
- **Problem symptom**: Exact error messages, observable behavior
|
|
105
|
-
- **Investigation steps tried**: What didn't work and why
|
|
106
|
-
- **Root cause analysis**: Technical explanation
|
|
107
|
-
- **Working solution**: Step-by-step fix with code examples
|
|
108
|
-
- **Prevention strategies**: How to avoid in future
|
|
109
|
-
- **Cross-references**: Links to related issues and docs
|
|
110
|
-
|
|
111
|
-
## Preconditions
|
|
112
|
-
|
|
113
|
-
<preconditions enforcement="advisory">
|
|
114
|
-
<check condition="problem_solved">
|
|
115
|
-
Problem has been solved (not in-progress)
|
|
116
|
-
</check>
|
|
117
|
-
<check condition="solution_verified">
|
|
118
|
-
Solution has been verified working
|
|
119
|
-
</check>
|
|
120
|
-
<check condition="non_trivial">
|
|
121
|
-
Non-trivial problem (not simple typo or obvious error)
|
|
122
|
-
</check>
|
|
123
|
-
</preconditions>
|
|
124
|
-
|
|
125
|
-
## What It Creates
|
|
126
|
-
|
|
127
|
-
**Organized documentation:**
|
|
128
|
-
|
|
129
|
-
- File: `docs/solutions/[category]/[filename].md`
|
|
130
|
-
|
|
131
|
-
**Categories auto-detected from problem:**
|
|
132
|
-
|
|
133
|
-
- build-errors/
|
|
134
|
-
- test-failures/
|
|
135
|
-
- runtime-errors/
|
|
136
|
-
- performance-issues/
|
|
137
|
-
- database-issues/
|
|
138
|
-
- security-issues/
|
|
139
|
-
- ui-bugs/
|
|
140
|
-
- integration-issues/
|
|
141
|
-
- logic-errors/
|
|
142
|
-
|
|
143
|
-
## Common Mistakes to Avoid
|
|
144
|
-
|
|
145
|
-
| ❌ Wrong | ✅ Correct |
|
|
146
|
-
|----------|-----------|
|
|
147
|
-
| Subagents write files like `context-analysis.md`, `solution-draft.md` | Subagents return text data; orchestrator writes one final file |
|
|
148
|
-
| Research and assembly run in parallel | Research completes → then assembly runs |
|
|
149
|
-
| Multiple files created during workflow | Single file: `docs/solutions/[category]/[filename].md` |
|
|
150
|
-
|
|
151
|
-
## Success Output
|
|
152
|
-
|
|
153
|
-
```
|
|
154
|
-
✓ Documentation complete
|
|
155
|
-
|
|
156
|
-
Subagent Results:
|
|
157
|
-
✓ Context Analyzer: Identified performance_issue in brief_system
|
|
158
|
-
✓ Solution Extractor: 3 code fixes
|
|
159
|
-
✓ Related Docs Finder: 2 related issues
|
|
160
|
-
✓ Prevention Strategist: Prevention strategies, test suggestions
|
|
161
|
-
✓ Category Classifier: `performance-issues`
|
|
162
|
-
|
|
163
|
-
Specialized Agent Reviews (Auto-Triggered):
|
|
164
|
-
✓ performance-oracle: Validated query optimization approach
|
|
165
|
-
✓ kieran-rails-reviewer: Code examples meet Rails standards
|
|
166
|
-
✓ code-simplicity-reviewer: Solution is appropriately minimal
|
|
167
|
-
✓ every-style-editor: Documentation style verified
|
|
168
|
-
|
|
169
|
-
File created:
|
|
170
|
-
- docs/solutions/performance-issues/n-plus-one-brief-generation.md
|
|
171
|
-
|
|
172
|
-
This documentation will be searchable for future reference when similar
|
|
173
|
-
issues occur in the Email Processing or Brief System modules.
|
|
174
|
-
|
|
175
|
-
What's next?
|
|
176
|
-
1. Continue workflow (recommended)
|
|
177
|
-
2. Link related documentation
|
|
178
|
-
3. Update other references
|
|
179
|
-
4. View documentation
|
|
180
|
-
5. Other
|
|
181
|
-
```
|
|
182
|
-
|
|
183
|
-
## The Compounding Philosophy
|
|
184
|
-
|
|
185
|
-
This creates a compounding knowledge system:
|
|
186
|
-
|
|
187
|
-
1. First time you solve "N+1 query in brief generation" → Research (30 min)
|
|
188
|
-
2. Document the solution → docs/solutions/performance-issues/n-plus-one-briefs.md (5 min)
|
|
189
|
-
3. Next time similar issue occurs → Quick lookup (2 min)
|
|
190
|
-
4. Knowledge compounds → Team gets smarter
|
|
191
|
-
|
|
192
|
-
The feedback loop:
|
|
193
|
-
|
|
194
|
-
```
|
|
195
|
-
Build → Test → Find Issue → Research → Improve → Document → Validate → Deploy
|
|
196
|
-
↑ ↓
|
|
197
|
-
└──────────────────────────────────────────────────────────────────────┘
|
|
198
|
-
```
|
|
199
|
-
|
|
200
|
-
**Each unit of engineering work should make subsequent units of work easier—not harder.**
|
|
201
|
-
|
|
202
|
-
## Auto-Invoke
|
|
203
|
-
|
|
204
|
-
<auto_invoke> <trigger_phrases> - "that worked" - "it's fixed" - "working now" - "problem solved" </trigger_phrases>
|
|
205
|
-
|
|
206
|
-
<manual_override> Use /workflows:compound [context] to document immediately without waiting for auto-detection. </manual_override> </auto_invoke>
|
|
207
|
-
|
|
208
|
-
## Routes To
|
|
209
|
-
|
|
210
|
-
`compound-docs` skill
|
|
211
|
-
|
|
212
|
-
## Applicable Specialized Agents
|
|
213
|
-
|
|
214
|
-
Based on problem type, these agents can enhance documentation:
|
|
215
|
-
|
|
216
|
-
### Code Quality & Review
|
|
217
|
-
- **kieran-rails-reviewer**: Reviews code examples for Rails best practices
|
|
218
|
-
- **code-simplicity-reviewer**: Ensures solution code is minimal and clear
|
|
219
|
-
- **pattern-recognition-specialist**: Identifies anti-patterns or repeating issues
|
|
220
|
-
|
|
221
|
-
### Specific Domain Experts
|
|
222
|
-
- **performance-oracle**: Analyzes performance_issue category solutions
|
|
223
|
-
- **security-sentinel**: Reviews security_issue solutions for vulnerabilities
|
|
224
|
-
- **cora-test-reviewer**: Creates test cases for prevention strategies
|
|
225
|
-
- **data-integrity-guardian**: Reviews database_issue migrations and queries
|
|
226
|
-
|
|
227
|
-
### Enhancement & Documentation
|
|
228
|
-
- **best-practices-researcher**: Enriches solution with industry best practices
|
|
229
|
-
- **every-style-editor**: Reviews documentation style and clarity
|
|
230
|
-
- **framework-docs-researcher**: Links to Rails/gem documentation references
|
|
231
|
-
|
|
232
|
-
### When to Invoke
|
|
233
|
-
- **Auto-triggered** (optional): Agents can run post-documentation for enhancement
|
|
234
|
-
- **Manual trigger**: User can invoke agents after /workflows:compound completes for deeper review
|
|
235
|
-
- **Customize agents**: Edit `systematic.local.md` or invoke the `setup` skill to configure which review agents are used across all workflows
|
|
236
|
-
|
|
237
|
-
## Related Commands
|
|
238
|
-
|
|
239
|
-
- `/research [topic]` - Deep investigation (searches docs/solutions/ for patterns)
|
|
240
|
-
- `/workflows:plan` - Planning workflow (references documented solutions)
|
|
10
|
+
/ce:compound $ARGUMENTS
|