mirror of
https://github.com/affaan-m/ECC.git
synced 2026-08-20 22:42:22 +02:00
Gaurav Dubey
9d1ecb0754
The `.opencode/commands/*.md` frontmatter referenced agents with the Claude Code plugin namespace (`agent: everything-claude-code:<name>`), but ECC's opencode integration registers its agents unscoped in `opencode.json`'s `agent` map (`code-reviewer`, `planner`, ...), and that file's own `command` section already references them unscoped. The `everything-claude-code:` scope resolves under no opencode config (the opencode plugin package is `ecc-universal`, and inline-config agents are bare), so subtask commands like `/code-review` hard-fail with `Agent not found: everything-claude-code:code-reviewer`. Non-subtask commands fall back to the default agent and appear to work — which is why only some commands failed. Strip the `everything-claude-code:` prefix from all 30 command frontmatter agent ids so they match the registered agents, fix the MIGRATION.md example, and replace the test that enforced the broken scoped invariant with one that asserts each command agent id is a registered opencode agent (fails on the old scoped ids, passes on the fix). Fixes #2477
118 lines
2.0 KiB
Markdown
118 lines
2.0 KiB
Markdown
---
|
|
description: Generate skills from git history analysis
|
|
agent: build
|
|
---
|
|
|
|
# Skill Create Command
|
|
|
|
Analyze git history to generate Claude Code skills: $ARGUMENTS
|
|
|
|
## Your Task
|
|
|
|
1. **Analyze commits** - Pattern recognition from history
|
|
2. **Extract patterns** - Common practices and conventions
|
|
3. **Generate SKILL.md** - Structured skill documentation
|
|
4. **Create instincts** - For continuous-learning-v2
|
|
|
|
## Analysis Process
|
|
|
|
### Step 1: Gather Commit Data
|
|
```bash
|
|
# Recent commits
|
|
git log --oneline -100
|
|
|
|
# Commits by file type
|
|
git log --name-only --pretty=format: | sort | uniq -c | sort -rn
|
|
|
|
# Most changed files
|
|
git log --pretty=format: --name-only | sort | uniq -c | sort -rn | head -20
|
|
```
|
|
|
|
### Step 2: Identify Patterns
|
|
|
|
**Commit Message Patterns**:
|
|
- Common prefixes (feat, fix, refactor)
|
|
- Naming conventions
|
|
- Co-author patterns
|
|
|
|
**Code Patterns**:
|
|
- File structure conventions
|
|
- Import organization
|
|
- Error handling approaches
|
|
|
|
**Review Patterns**:
|
|
- Common review feedback
|
|
- Recurring fix types
|
|
- Quality gates
|
|
|
|
### Step 3: Generate SKILL.md
|
|
|
|
```markdown
|
|
# [Skill Name]
|
|
|
|
## Overview
|
|
[What this skill teaches]
|
|
|
|
## Patterns
|
|
|
|
### Pattern 1: [Name]
|
|
- When to use
|
|
- Implementation
|
|
- Example
|
|
|
|
### Pattern 2: [Name]
|
|
- When to use
|
|
- Implementation
|
|
- Example
|
|
|
|
## Best Practices
|
|
|
|
1. [Practice 1]
|
|
2. [Practice 2]
|
|
3. [Practice 3]
|
|
|
|
## Common Mistakes
|
|
|
|
1. [Mistake 1] - How to avoid
|
|
2. [Mistake 2] - How to avoid
|
|
|
|
## Examples
|
|
|
|
### Good Example
|
|
```[language]
|
|
// Code example
|
|
```
|
|
|
|
### Anti-pattern
|
|
```[language]
|
|
// What not to do
|
|
```
|
|
```
|
|
|
|
### Step 4: Generate Instincts
|
|
|
|
For continuous-learning-v2:
|
|
|
|
```json
|
|
{
|
|
"instincts": [
|
|
{
|
|
"trigger": "[situation]",
|
|
"action": "[response]",
|
|
"confidence": 0.8,
|
|
"source": "git-history-analysis"
|
|
}
|
|
]
|
|
}
|
|
```
|
|
|
|
## Output
|
|
|
|
Creates:
|
|
- `skills/[name]/SKILL.md` - Skill documentation
|
|
- `skills/[name]/instincts.json` - Instinct collection
|
|
|
|
---
|
|
|
|
**TIP**: Run `/skill-create --instincts` to also generate instincts for continuous learning.
|