azclaude-copilot 0.1.4 → 0.1.5
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/README.md +3 -3
- package/package.json +1 -1
- package/templates/commands/evolve.md +31 -1
- package/templates/commands/setup.md +43 -1
package/README.md
CHANGED
|
@@ -424,7 +424,7 @@ azclaude-copilot/
|
|
|
424
424
|
├── DOCS.md <- full user guide
|
|
425
425
|
├── SECURITY.md <- security policy + architecture
|
|
426
426
|
├── tests/
|
|
427
|
-
│ └── test-features.sh ←
|
|
427
|
+
│ └── test-features.sh ← 1048 tests
|
|
428
428
|
```
|
|
429
429
|
|
|
430
430
|
---
|
|
@@ -450,11 +450,11 @@ The runner is stateless. These files ARE the state.
|
|
|
450
450
|
|
|
451
451
|
## Verified
|
|
452
452
|
|
|
453
|
-
|
|
453
|
+
1048 tests. Every template, command, capability, agent, and CLI feature verified.
|
|
454
454
|
|
|
455
455
|
```bash
|
|
456
456
|
bash tests/test-features.sh
|
|
457
|
-
# Results:
|
|
457
|
+
# Results: 1048 passed, 0 failed, 1048 total
|
|
458
458
|
```
|
|
459
459
|
|
|
460
460
|
---
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "azclaude-copilot",
|
|
3
|
-
"version": "0.1.
|
|
3
|
+
"version": "0.1.5",
|
|
4
4
|
"description": "Autonomous product builder. Describe once, AZCLAUDE builds it across sessions — planning, implementing, testing, evolving, deploying. Zero human input.",
|
|
5
5
|
"bin": {
|
|
6
6
|
"azclaude": "./bin/cli.js",
|
|
@@ -150,7 +150,37 @@ If the file doesn't exist, create it with this header:
|
|
|
150
150
|
|
|
151
151
|
---
|
|
152
152
|
|
|
153
|
-
## Step 7:
|
|
153
|
+
## Step 7: Generate Project-Specific Skills and Agents from Evidence
|
|
154
|
+
|
|
155
|
+
### Skills from git evidence
|
|
156
|
+
```bash
|
|
157
|
+
git log --name-only --format="" --diff-filter=AM | sort | uniq -c | sort -rn | head -20
|
|
158
|
+
```
|
|
159
|
+
If a file pattern appears 5+ times (e.g., `src/components/*.tsx`, `content/*.md`, `api/routes/*.py`):
|
|
160
|
+
1. Read `.claude/capabilities/level-builders/level3-skills.md`
|
|
161
|
+
2. Create a skill that encodes the workflow for that pattern
|
|
162
|
+
3. Save to `.claude/commands/{skill-name}.md`
|
|
163
|
+
4. Only create if no existing skill covers this workflow
|
|
164
|
+
|
|
165
|
+
### Agents from co-change clusters
|
|
166
|
+
```bash
|
|
167
|
+
git log --name-only --format="" --diff-filter=M | sort | uniq -c | sort -rn | head -30
|
|
168
|
+
```
|
|
169
|
+
If 3+ files in the same directory change together across 3+ commits:
|
|
170
|
+
1. Read `.claude/capabilities/level-builders/level5-agents.md`
|
|
171
|
+
2. Create an agent with all 5 layers in `.claude/agents/cc-{name}.md`
|
|
172
|
+
3. Use co-change data for scope boundaries
|
|
173
|
+
4. Only create if no existing agent covers this cluster
|
|
174
|
+
|
|
175
|
+
### Check existing before creating
|
|
176
|
+
```bash
|
|
177
|
+
ls .claude/commands/*.md .claude/agents/*.md 2>/dev/null
|
|
178
|
+
```
|
|
179
|
+
Skip creation if a skill/agent already covers the same workflow.
|
|
180
|
+
|
|
181
|
+
---
|
|
182
|
+
|
|
183
|
+
## Step 8: Promote GENERAL Skills
|
|
154
184
|
|
|
155
185
|
For any fix tagged GENERAL in EVALUATE:
|
|
156
186
|
1. Copy to `~/shared-skills/{name}.md`
|
|
@@ -70,7 +70,49 @@ The orchestrator-init agent:
|
|
|
70
70
|
|
|
71
71
|
---
|
|
72
72
|
|
|
73
|
-
## Step 5:
|
|
73
|
+
## Step 5: Generate Project-Specific Skills
|
|
74
|
+
|
|
75
|
+
Read `.claude/capabilities/level-builders/level3-skills.md` for the skill design guide.
|
|
76
|
+
|
|
77
|
+
Analyze the project's domain, stack, and recurring workflows:
|
|
78
|
+
1. Check what file types and patterns exist (endpoints, pages, components, schemas, tests)
|
|
79
|
+
2. Check git log for repeated commit patterns (what work is done most often)
|
|
80
|
+
3. Identify 2-4 project-specific skills that would encode the most common workflows
|
|
81
|
+
|
|
82
|
+
For each skill:
|
|
83
|
+
- Create `.claude/commands/{skill-name}.md` with pushy description (3+ trigger variants)
|
|
84
|
+
- Follow RECIPE pattern (steps to do something, not documentation)
|
|
85
|
+
- Include completion rule
|
|
86
|
+
- ≤ 500 lines (references/ subdir for overflow)
|
|
87
|
+
|
|
88
|
+
**Stack-specific defaults** (generate if stack detected):
|
|
89
|
+
| Stack | Generate |
|
|
90
|
+
|-------|---------|
|
|
91
|
+
| Next.js / React | `new-page.md`, `new-component.md` |
|
|
92
|
+
| Express / FastAPI | `new-endpoint.md` |
|
|
93
|
+
| Any DB | `migrate.md` |
|
|
94
|
+
| Any deploy config | `deploy.md` |
|
|
95
|
+
| Markdown content | `new-content.md`, `validate-content.md` |
|
|
96
|
+
| Exam / quiz | `new-exam.md`, `validate-exam.md` |
|
|
97
|
+
|
|
98
|
+
**TaskUpdate → completed** for Create skills.
|
|
99
|
+
|
|
100
|
+
---
|
|
101
|
+
|
|
102
|
+
## Step 6: Generate Project-Specific Agents (if project has 10+ files)
|
|
103
|
+
|
|
104
|
+
Read `.claude/capabilities/level-builders/level5-agents.md` for agent design guide.
|
|
105
|
+
|
|
106
|
+
1. Run co-change analysis: `git log --name-only --format="" --diff-filter=M | sort | uniq -c | sort -rn | head -30`
|
|
107
|
+
2. Identify file clusters that change independently → each cluster = potential agent
|
|
108
|
+
3. Create 1-3 agents in `.claude/agents/cc-{name}.md` with all 5 layers
|
|
109
|
+
4. Prefix all agents with `cc-` to avoid framework collisions
|
|
110
|
+
|
|
111
|
+
Skip if project has < 10 files or < 5 commits.
|
|
112
|
+
|
|
113
|
+
---
|
|
114
|
+
|
|
115
|
+
## Step 7: Quality Gate
|
|
74
116
|
|
|
75
117
|
Load `capabilities/shared/quality-check.md` and run the full environment check.
|
|
76
118
|
|