first commit

This commit is contained in:
2026-06-11 03:33:14 +08:00
commit 5f555bf342
599 changed files with 142347 additions and 0 deletions

View File

@@ -0,0 +1,251 @@
---
name: skill-improver
description: This skill should be used when the user asks to "apply skill improvements", "update skill from plan", "execute improvement plan", "fix skill issues", "implement skill recommendations", or mentions applying improvements from quality review reports. Reads improvement-plan-{name}.md files generated by skill-quality-reviewer and intelligently merges and executes the suggested changes to improve Claude Skills quality.
version: 1.0.0
---
# Skill Improver
Execute improvement plans generated by `skill-quality-reviewer` to automatically update and fix issues in Claude Skills.
## Core Workflow
```
Read improvement-plan-{name}.md
Parse improvement items (High/Medium/Low priority)
Group changes by file
Detect and resolve conflicts
Backup original files
Execute updates (Edit or Write tools)
Verify results
Generate update-report
```
## When to Use
**Trigger phrases:**
- "Apply improvements from improvement-plan-git-workflow.md"
- "Update my skill based on the quality report"
- "Execute the improvement plan for api-helper"
- "Fix the issues identified in quality review"
**Use this skill when:**
- Applying improvements from an improvement plan
- Updating a skill based on quality review feedback
- Executing recommended fixes from `skill-quality-reviewer`
- Implementing structured improvements to skill documentation
## Step-by-Step Guide
### Step 1: Load the Improvement Plan
Read the `improvement-plan-{skill-name}.md` file generated by `skill-quality-reviewer`.
```bash
# Plan is typically in current directory
ls improvement-plan-*.md
# Or specify full path
read /path/to/improvement-plan-my-skill.md
```
**Validate the plan:**
- File exists and is readable
- Contains priority sections (High/Medium/Low)
- Has structured improvement items
- Includes file paths and suggested changes
See `references/plan-format.md` for detailed plan structure.
### Step 2: Parse and Group Changes
Extract all improvement suggestions and organize by target file.
**Extract from each item:**
- File path (e.g., `SKILL.md:line:line` or `references/file.md`)
- Dimension (Description Quality, Content Organization, etc.)
- Impact (+X points)
- Current content
- Suggested content
- Reason for change
**Build update queue:**
```
by_file = {
"SKILL.md": [change1, change2, ...],
"references/guide.md": [change3, ...],
"examples/demo.md": [change4, ...],
}
```
### Step 3: Detect and Resolve Conflicts
Check for conflicts when multiple changes affect the same content.
**Resolution strategy:**
1. High priority takes precedence over medium/low
2. If same priority, preserve first change
3. Flag conflicts for manual review
4. Document resolution in update report
See `references/merge-strategies.md` for detailed merge logic.
### Step 4: Sort by Priority
Order changes by priority within each file.
**Priority order:**
1. High Priority (execute first)
2. Medium Priority (execute second)
3. Low Priority (execute last)
### Step 5: Backup and Execute
**Backup location:** `~/.claude/skills/backup/{skill-name}-{timestamp}/`
```bash
# Use backup script
~/.claude/skills/skill-improver/scripts/backup-skill.sh <skill-path>
```
**Apply changes:**
- Use Edit tool for existing content
- Use Write tool for new files
- Verify each change was applied
### Step 6: Verify and Report
**Verification checks:**
1. YAML syntax valid
2. All modified files exist and are valid
3. New files were created successfully
4. No unintended changes occurred
```bash
# Use verify script
~/.claude/skills/skill-improver/scripts/verify-update.sh <skill-path>
```
**Generate update-report-{skill-name}-{timestamp}.md** documenting:
- Summary (files modified, files created, total changes)
- Changes Applied (per-file breakdown)
- Quality Improvement (before/after scores)
- Verification Results
- Backup Location
See `examples/update-report-example.md` for report template.
## Priority Handling
### High Priority
Execute first. These typically address:
- Critical description issues
- Major writing style problems
- Missing structural elements
- Security-related concerns
### Medium Priority
Execute after High. These typically address:
- Content organization improvements
- Additional examples
- Documentation enhancements
### Low Priority
Execute last. These typically address:
- Minor clarifications
- Nice-to-have improvements
- Polish and refinement
## Integration with Skill Quality Reviewer
This skill works seamlessly with `skill-quality-reviewer`:
```
Current Skill (67/100 D+)
↓ [skill-quality-reviewer]
Improvement Plan
↓ [skill-improver]
Improved Skill (87/100 B+)
↓ [skill-quality-reviewer]
Quality Report (validation)
```
**Iterate until desired quality level reached.**
## Additional Resources
### Reference Files
- **`references/plan-format.md`** - Improvement plan file structure and format
- **`references/merge-strategies.md`** - Detailed merge algorithms and conflict resolution
- **`references/error-handling.md`** - Error handling strategies
- **`references/supported-updates.md`** - Supported update types with examples
### Example Files
- **`examples/improvement-plan-example.md`** - Sample improvement plan
- **`examples/update-report-example.md`** - Sample update report
### Scripts
- **`scripts/backup-skill.sh`** - Create backup of skill before updates
- **`scripts/verify-update.sh`** - Verify skill integrity after updates
## Best Practices
### Before Applying Updates
1. **Review the improvement plan** - Understand what will change
2. **Verify backup location** - Ensure backups can be restored
3. **Check for manual changes** - Note any uncommitted local modifications
4. **Estimate impact** - Review expected quality improvement
### During Update Execution
1. **Process in priority order** - High → Medium → Low
2. **Verify after each file** - Check updates were applied correctly
3. **Log all changes** - Document what was modified
4. **Handle conflicts gracefully** - Flag for review if needed
### After Applying Updates
1. **Review the update report** - Confirm all changes were intended
2. **Test the skill** - Verify it still works correctly
3. **Compare scores** - Check quality improvement matches expectations
4. **Keep backup** - Retain backup until confident in changes
## Usage Examples
**Example 1: Apply improvements to local skill**
```
User: "Apply improvements from improvement-plan-git-workflow.md"
[Claude executes the workflow:]
1. Reads improvement-plan-git-workflow.md
2. Parses all improvement items
3. Groups changes by file
4. Detects and resolves conflicts
5. Sorts by priority
6. Backs up git-workflow skill
7. Executes updates
8. Verifies results
9. Generates update-report-git-workflow-timestamp.md
```
**Example 2: Update skill from quality review**
```
User: "Update my api-helper skill based on quality report"
[Claude:]
1. Locates improvement-plan-api-helper.md
2. Applies all recommended changes
3. Verifies skill structure
4. Reports quality improvement: 72/100 → 91/100
```

View File

@@ -0,0 +1,85 @@
# Skill Improvement Plan: example-skill
## Priority Summary
- **High Priority**: 2 items
- **Medium Priority**: 1 item
- **Low Priority**: 1 item
## High Priority Improvements
### 1. Fix Description Trigger Phrases
**File**: SKILL.md:3:4
**Dimension**: Description Quality
**Impact**: +20 points
**Current**:
```yaml
---
name: example-skill
description: A helpful skill for various tasks
---
```
**Suggested**:
```yaml
---
name: api-contract-manager
description: This skill should be used when the user asks to "validate API contract", "check API compatibility", or "detect breaking changes"
---
```
**Reason**: The current description lacks specific trigger phrases and uses first-person format. The suggested version follows third-person format with clear trigger phrases.
### 2. Convert to Imperative Form
**File**: SKILL.md:50:55
**Dimension**: Writing Style
**Impact**: +15 points
**Current**:
```markdown
You should create the file first.
You need to validate the input.
```
**Suggested**:
```markdown
Create the file first.
Validate the input.
```
**Reason**: Skills must use imperative form without second-person language.
## Medium Priority Improvements
### 3. Add Progressive Disclosure
**File**: SKILL.md
**Dimension**: Content Organization
**Impact**: +10 points
**Current**: All content in SKILL.md (3000+ words)
**Suggested**: Move detailed content to references/ directory, keep SKILL.md under 2000 words
**Reason**: SKILL.md should follow progressive disclosure principles with lean main content and detailed references.
## Low Priority Improvements
### 4. Add Examples
**File**: examples/demo.md (new file)
**Dimension**: Structural Integrity
**Impact**: +5 points
**Suggested**: Create examples/demo.md with working demonstration
**Reason**: Examples help users understand how to use the skill effectively.
## Estimated Time to Complete
- High Priority: 1 hour
- Medium Priority: 2 hours
- Low Priority: 30 minutes
- **Total**: 3.5 hours
## Expected Score Improvement
- Current: 67/100 (D+)
- After High Priority: 82/100 (B-)
- After All: 87/100 (B+)

View File

@@ -0,0 +1,45 @@
# Skill Update Report: example-skill
## Summary
- **Update Date**: 2025-01-25 14:30:00
- **Improvement Plan**: improvement-plan-example-skill.md
- **Files Modified**: 1
- **Files Created**: 1
- **Total Changes Applied**: 4
## Changes Applied
### SKILL.md
- ✅ Fixed description trigger phrases (line 3-4)
- ✅ Changed to imperative form (line 50, 52, 55)
- ✅ Reorganized content for progressive disclosure
### examples/demo.md (new)
- ✅ Created example demonstration file
## Quality Improvement
| Dimension | Before | After | Change |
|-----------|--------|-------|--------|
| Description Quality | 55/100 | 90/100 | +35 |
| Content Organization | 70/100 | 85/100 | +15 |
| Writing Style | 60/100 | 95/100 | +35 |
| Structural Integrity | 80/100 | 90/100 | +10 |
| **Overall** | **67/100** | **87/100** | **+20** |
**Grade**: D+ → B+
## Verification Results
- ✅ YAML syntax valid
- ✅ All files updated successfully
- ✅ No unintended changes
- ✅ Skill structure intact
## Backup
Original files backed up to: `~/.claude/skills/backup/example-skill-20250125-143000/`
## Notes
- All high priority changes applied successfully
- Medium priority reorganization completed
- Low priority example file created
- Skill is now ready for use

View File

@@ -0,0 +1,39 @@
# Error Handling
## Parse Errors
**Symptom:** Cannot read improvement plan
**Solutions:**
- Verify file exists and is readable
- Check file follows expected format
- Ensure proper markdown structure
## Conflict Errors
**Symptom:** Multiple changes to same content
**Solutions:**
- Apply highest priority change
- Flag conflict for manual review
- Document decision in report
## Edit Failures
**Symptom:** Cannot find current content to replace
**Solutions:**
- Verify current content matches exactly
- Check line numbers are correct
- File may have been modified externally
- Skip change and document in report
## Verification Failures
**Symptom:** Update broke skill structure
**Solutions:**
- Restore from backup
- Review conflicting changes
- Apply changes individually
- Skip problematic changes

View File

@@ -0,0 +1,570 @@
# Merge Strategies for Skill Updates
Detailed strategies for intelligently merging multiple improvements to the same skill files.
## Overview
When applying improvements from an improvement plan, multiple changes may affect the same file or even the same lines. This document defines strategies for detecting conflicts, resolving them, and applying updates in the correct order.
## Priority-Based Merging
### Priority Order
Changes are applied in strict priority order:
1. **High Priority** - Critical issues that must be fixed
2. **Medium Priority** - Important improvements
3. **Low Priority** - Nice-to-have enhancements
### Rationale
- High priority changes often fix fundamental issues
- Applying them first ensures a solid foundation
- Lower priority changes may depend on high priority fixes
- Prevents wasted effort on changes that might be reverted
## Per-File Merge Strategy
### Single File, Multiple Changes
When multiple changes affect the same file:
1. **Group by file**
```
SKILL.md: [
{ line: 10, priority: high, ... },
{ line: 50, priority: high, ... },
{ line: 100, priority: medium, ... },
{ line: 200, priority: low, ... }
]
```
2. **Sort by line number (descending)**
- Process from bottom to top
- Prevents line offset issues
- Earlier changes don't affect later line numbers
```
SKILL.md: [
{ line: 200, priority: low, ... }, # First
{ line: 100, priority: medium, ... }, # Second
{ line: 50, priority: high, ... }, # Third
{ line: 10, priority: high, ... } # Fourth
]
```
3. **Apply within same line range by priority**
- If multiple changes affect same lines
- Higher priority wins
- Document conflict in report
### Algorithm
```python
def merge_per_file(changes):
"""Merge changes for a single file."""
# Group by line range
by_range = {}
for change in changes:
key = (change['start'], change['end'])
if key not in by_range:
by_range[key] = []
by_range[key].append(change)
# Resolve conflicts within ranges
resolved = []
for range_key, range_changes in by_range.items():
if len(range_changes) == 1:
resolved.append(range_changes[0])
else:
# Conflict: pick highest priority
priority_order = {'high': 0, 'medium': 1, 'low': 2}
sorted_changes = sorted(
range_changes,
key=lambda c: priority_order[c['priority']]
)
winner = sorted_changes[0]
winner['conflicts_with'] = sorted_changes[1:]
resolved.append(winner)
# Sort by line number descending
resolved.sort(key=lambda c: c['start'], reverse=True)
return resolved
```
## Cross-File Merge Strategy
### Multiple Files, Multiple Changes
When changes span multiple files:
1. **Execute all High Priority changes first**
- Across all files
- Ensures critical fixes everywhere
2. **Then execute all Medium Priority changes**
- Build on High Priority foundation
3. **Finally execute all Low Priority changes**
- Polish and refine
### Execution Order
```
Round 1: High Priority
├── SKILL.md (High changes)
├── references/guide.md (High changes)
└── examples/demo.md (High changes)
Round 2: Medium Priority
├── SKILL.md (Medium changes)
├── references/guide.md (Medium changes)
└── examples/new.md (Medium, new file)
Round 3: Low Priority
└── SKILL.md (Low changes)
```
### Algorithm
```python
def merge_cross_files(all_changes):
"""Merge changes across all files."""
# Group by priority
by_priority = {
'high': [],
'medium': [],
'low': []
}
for change in all_changes:
by_priority[change['priority']].append(change)
# Process each priority level
execution_order = []
for priority in ['high', 'medium', 'low']:
# Group by file within priority
by_file = {}
for change in by_priority[priority]:
file = change['file']
if file not in by_file:
by_file[file] = []
by_file[file].append(change)
# Merge within each file
for file, file_changes in by_file.items():
merged = merge_per_file(file_changes)
execution_order.extend(merged)
return execution_order
```
## Conflict Detection
### Types of Conflicts
#### 1. Same Line, Different Content
```
Change A: SKILL.md:10:10
Current: "You should create file"
Suggested: "Create the file"
Change B: SKILL.md:10:10
Current: "You should create file"
Suggested: "Create file now"
```
**Resolution:** Higher priority wins, document conflict
#### 2. Overlapping Line Ranges
```
Change A: SKILL.md:10:15
Current: lines 10-15 content
Suggested: new content for 10-15
Change B: SKILL.md:12:20
Current: lines 12-20 content
Suggested: new content for 12-20
```
**Resolution:** Higher priority wins, lower priority is skipped
#### 3. Same Priority Conflicts
```
Change A: SKILL.md:10:10 (High)
Suggested: "Option A"
Change B: SKILL.md:10:10 (High)
Suggested: "Option B"
```
**Resolution:** First in list wins, flag for manual review
### Conflict Detection Algorithm
```python
def detect_conflicts(changes):
"""Detect conflicting changes."""
conflicts = []
# Sort by line range
sorted_changes = sorted(changes, key=lambda c: (c['start'], c['end']))
for i in range(len(sorted_changes)):
for j in range(i + 1, len(sorted_changes)):
a = sorted_changes[i]
b = sorted_changes[j]
# Check for overlap
if ranges_overlap(a, b):
# Check if suggestions differ
if a['suggested'] != b['suggested']:
conflicts.append({
'changes': [a, b],
'type': 'overlap',
'resolution': 'priority'
})
return conflicts
def ranges_overlap(a, b):
"""Check if two line ranges overlap."""
a_start, a_end = a['start'], a['end']
b_start, b_end = b['start'], b['end']
return not (a_end < b_start or b_end < a_start)
```
## Conflict Resolution
### Resolution Strategies
#### 1. Priority-Based Resolution
**Apply highest priority change:**
```
Conflicting changes:
- High: Fix description
- Low: Clarify text
Resolution: Apply High, skip Low
```
#### 2. First-Win Resolution
**For same priority conflicts:**
```
Conflicting changes (both High):
- #1: Fix description option A
- #2: Fix description option B
Resolution: Apply #1, skip #2, flag for review
```
#### 3. Manual Review Flag
**Document conflicts requiring human review:**
```markdown
## Conflicts Requiring Manual Review
### SKILL.md:10:10
**Applied:** High Priority - Fix description (Option A)
**Skipped:** High Priority - Alternative fix (Option B)
**Reason:** Same priority, first change applied
Review suggested alternative and manually apply if preferred.
```
### Resolution Algorithm
```python
def resolve_conflicts(changes):
"""Resolve conflicts using priority-based strategy."""
priority_value = {'high': 3, 'medium': 2, 'low': 1}
# Track applied line ranges
applied_ranges = []
# Filter changes
resolved = []
skipped = []
for change in sorted(changes, key=lambda c: (
-priority_value[c['priority']], # Higher priority first
c['start']
)):
# Check if range already applied
conflict = False
for applied in applied_ranges:
if ranges_overlap(change, applied):
conflict = True
skipped.append({
'change': change,
'reason': 'overlap_with_higher_priority',
'conflicts_with': applied
})
break
if not conflict:
resolved.append(change)
applied_ranges.append({
'start': change['start'],
'end': change['end']
})
return resolved, skipped
```
## Special Cases
### New File Creation
When creating new files (no line numbers):
1. **Check if file already exists**
2. **If exists:** Verify content matches or skip
3. **If not exists:** Create with suggested content
```python
def handle_new_file(change, skill_path):
"""Handle new file creation."""
file_path = os.path.join(skill_path, change['file'])
if os.path.exists(file_path):
# File exists, verify content
existing = read_file(file_path)
if existing.strip() == change['suggested'].strip():
return {'status': 'already_exists', 'action': 'skip'}
else:
return {
'status': 'conflict',
'action': 'skip',
'reason': 'File exists with different content'
}
else:
# Create new file
write_file(file_path, change['suggested'])
return {'status': 'created', 'action': 'created'}
```
### Append Operations
When no line numbers and file exists:
```python
def handle_append(change, skill_path):
"""Handle append to existing file."""
file_path = os.path.join(skill_path, change['file'])
if os.path.exists(file_path):
# Append to end
existing = read_file(file_path)
updated = existing + '\n\n' + change['suggested']
write_file(file_path, updated)
return {'status': 'appended', 'action': 'appended'}
else:
# Treat as new file
write_file(file_path, change['suggested'])
return {'status': 'created', 'action': 'created'}
```
### YAML Frontmatter Updates
Special handling for YAML frontmatter:
1. **Parse existing frontmatter**
2. **Update specific fields**
3. **Preserve other fields**
4. **Validate YAML syntax**
```python
def update_frontmatter(file_path, updates):
"""Update YAML frontmatter fields."""
# Read file
content = read_file(file_path)
# Extract frontmatter
frontmatter, body = extract_frontmatter(content)
# Parse YAML
import yaml
data = yaml.safe_load(frontmatter)
# Apply updates
for key, value in updates.items():
data[key] = value
# Serialize back
new_frontmatter = yaml.dump(data, default_flow_style=False)
# Reconstruct file
updated = f"---\n{new_frontmatter}---\n{body}"
write_file(file_path, updated)
```
## Verification After Merge
### Post-Merge Checks
After applying all changes:
1. **Verify file existence**
```python
for change in applied_changes:
file_path = os.path.join(skill_path, change['file'])
assert os.path.exists(file_path), f"File not found: {file_path}"
```
2. **Verify YAML syntax**
```bash
~/.claude/skills/skill-quality-reviewer/scripts/extract-yaml.sh <skill-path>
```
3. **Verify content was applied**
```python
for change in applied_changes:
content = read_file(change['file'])
assert change['suggested'] in content, "Change not found in file"
```
4. **Verify no unintended changes**
```python
# Compare backup with current
# Only expected changes should be present
```
## Complete Merge Workflow
```python
def execute_merge(improvement_plan, skill_path):
"""Complete merge workflow."""
# 1. Parse improvement plan
changes = parse_improvement_plan(improvement_plan)
# 2. Detect conflicts
conflicts = detect_conflicts(changes)
# 3. Resolve conflicts
resolved, skipped = resolve_conflicts(changes)
# 4. Sort by execution order
execution_order = merge_cross_files(resolved)
# 5. Backup original files
backup_skill(skill_path)
# 6. Execute changes
applied = []
failed = []
for change in execution_order:
try:
if change['start'] is None:
# New file or append
result = handle_new_file(change, skill_path)
else:
# Edit existing content
result = edit_file(
change['file'],
change['start'],
change['end'],
change['current'],
change['suggested']
)
applied.append({
'change': change,
'result': result
})
except Exception as e:
failed.append({
'change': change,
'error': str(e)
})
# 7. Verify results
verification = verify_merge(skill_path, applied)
# 8. Generate report
report = generate_merge_report(
applied=applied,
failed=failed,
skipped=skipped,
conflicts=conflicts,
verification=verification
)
return report
```
## Best Practices
### When Merging
1. **Always backup first** - Restore if things go wrong
2. **Apply high priority first** - Critical fixes first
3. **Process bottom to top** - Avoid line offset issues
4. **Verify after each file** - Catch errors early
5. **Document all decisions** - Clear update report
### When Conflicts Occur
1. **Prioritize by importance** - Critical over nice-to-have
2. **Flag for review** - Let user decide when unsure
3. **Don't silently skip** - Document everything
4. **Preserve originals** - Backup enables recovery
### After Merging
1. **Run verification** - Ensure skill still works
2. **Review report** - Confirm changes match intent
3. **Test the skill** - Verify functionality
4. **Keep backup** - Until confident in changes
## Error Recovery
### If Merge Fails
1. **Stop immediately** - Don't continue with errors
2. **Identify failure point** - Which change caused issue
3. **Restore from backup** - Return to original state
4. **Analyze failure** - Understand why it failed
5. **Retry selectively** - Skip problematic changes
### Partial Recovery
If some changes applied before failure:
```python
def partial_recovery(applied, backup_path):
"""Restore only failed changes."""
# Get list of applied files
applied_files = set(c['file'] for c in applied)
# Restore only files that failed
for file_path in failed_files:
restore_from_backup(file_path, backup_path)
return {
'restored': failed_files,
'preserved': applied_files
}
```
This ensures successful changes are preserved while failed ones are reverted.

View File

@@ -0,0 +1,518 @@
# Improvement Plan Format
Detailed specification of the `improvement-plan-{skill-name}.md` file format generated by `skill-quality-reviewer` and consumed by `skill-improver`.
## File Structure
```markdown
# Skill Improvement Plan: {skill-name}
## Priority Summary
- **High Priority**: {count} items
- **Medium Priority**: {count} items
- **Low Priority**: {count} items
## High Priority Improvements
### 1. [Issue Title]
**File**: SKILL.md:line:line
**Dimension**: {Dimension Name}
**Impact**: +X points
**Current**:
```yaml or markdown
{current content}
```
**Suggested**:
```yaml or markdown
{suggested content}
```
**Reason**: {why this improves quality}
[Repeat for all high priority items...]
## Medium Priority Improvements
[Same format as High Priority...]
## Low Priority Improvements
[Same format as High Priority...]
## Quick Wins (Easy Fixes)
1. {quick fix description}
2. {quick fix description}
## Estimated Time to Complete
- High Priority: X hours
- Medium Priority: X hours
- Low Priority: X hours
- **Total**: X hours
## Expected Score Improvement
- Current: X/100 ({Grade})
- After High Priority: X/100 ({Grade})
- After All: X/100 ({Grade})
```
## Parsing Rules
### Priority Section Detection
**Identify sections by heading:**
```markdown
## High Priority Improvements
## Medium Priority Improvements
## Low Priority Improvements
```
**Case insensitive but exact match preferred:**
- "High Priority Improvements" ✓
- "high priority improvements" ✓ (acceptable)
- "High Priority" ✗ (incomplete)
### Item Extraction
**Each improvement item starts with:**
```markdown
### N. [Issue Title]
```
Where N is a sequential number (1, 2, 3, ...)
**Required fields within each item:**
1. **File** (required)
```
**File**: SKILL.md:line:line
**File**: references/filename.md
**File**: examples/filename.md
```
- Format: `filepath:line:line` or just `filepath`
- Line numbers are specific for edits
- File only indicates new file creation or append
2. **Dimension** (required)
```
**Dimension**: Description Quality
**Dimension**: Content Organization
**Dimension**: Writing Style
**Dimension**: Structural Integrity
```
3. **Impact** (required)
```
**Impact**: +X points
```
- Points indicate expected score improvement
- Used for calculating expected final score
4. **Current** (required for edits)
```
**Current**:
```yaml or markdown
{exact current content}
```
- Must match exactly for Edit operations
- Code fence specifies format (yaml, markdown, etc.)
5. **Suggested** (required)
```
**Suggested**:
```yaml or markdown
{suggested replacement content}
```
- Content to replace current or create
6. **Reason** (optional but recommended)
```
**Reason**: {explanation}
```
- Human-readable explanation
- Included in update report
### Code Fence Formats
**Supported formats:**
```yaml
```yaml
---
name: skill-name
---
```
```
```markdown
```markdown
## Section Header
Content here...
```
```
```bash
```bash
#!/bin/bash
echo "script"
```
```
**Format determines:**
- Syntax highlighting
- Validation rules
- Parser expectations
## File Path Patterns
### SKILL.md References
**With line numbers:**
```
**File**: SKILL.md:5:10
```
- Lines 5-10 will be replaced
- Used for Edit operations
**Without line numbers:**
```
**File**: SKILL.md
```
- Typically indicates new file or append
### References/ Files
**Specific file:**
```
**File**: references/api-guide.md
**File**: references/examples-bad.md
```
**With line numbers:**
```
**File**: references/patterns.md:50:100
```
### Examples/ Files
**New file creation:**
```
**File**: examples/demo.md
```
- No line numbers
- Suggested content becomes entire file
**Modification:**
```
**File**: examples/basic-usage.sh:20:30
```
### Scripts/ Files
**Script updates:**
```
**File**: scripts/validate.sh:15:25
```
## Parsing Pseudocode
```python
def parse_improvement_plan(plan_path):
"""Parse improvement plan file into structured data."""
plan = read_file(plan_path)
sections = {
'high': [],
'medium': [],
'low': []
}
current_section = None
current_item = None
for line in plan.split('\n'):
# Detect section headers
if line.startswith('## High Priority'):
current_section = 'high'
elif line.startswith('## Medium Priority'):
current_section = 'medium'
elif line.startswith('## Low Priority'):
current_section = 'low'
# Detect item start
elif line.startswith('### '):
if current_item:
sections[current_section].append(current_item)
current_item = {'title': line[4:].strip()}
# Parse fields within item
elif current_item:
if line.startswith('**File**'):
current_item['file'] = parse_file_path(line)
elif line.startswith('**Dimension**'):
current_item['dimension'] = line.split(':', 1)[1].strip()
elif line.startswith('**Impact**'):
current_item['impact'] = parse_impact(line)
elif line.startswith('**Current**'):
current_item['current'] = extract_code_fence(plan, line)
elif line.startswith('**Suggested**'):
current_item['suggested'] = extract_code_fence(plan, line)
elif line.startswith('**Reason**'):
current_item['reason'] = line.split(':', 1)[1].strip()
# Add last item
if current_item:
sections[current_section].append(current_item)
return sections
```
## Line Number Handling
### Single Line
```
**File**: SKILL.md:10:10
```
- Only line 10 is replaced
### Line Range
```
**File**: SKILL.md:10:15
```
- Lines 10-15 are replaced
- Current content should span these lines
### No Line Numbers
```
**File**: references/new-file.md
```
- New file creation
- Or append to existing file
### Line Number Extraction
```python
def parse_file_path(line):
"""Extract file path and line numbers from File field."""
# Remove "**File**:" prefix
value = line.split(':', 1)[1].strip()
# Check for line numbers
if ':' in value:
parts = value.split(':')
file_path = ':'.join(parts[:-2])
start_line = int(parts[-2])
end_line = int(parts[-1])
return {
'path': file_path,
'start': start_line,
'end': end_line
}
else:
return {
'path': value,
'start': None,
'end': None
}
```
## Impact Extraction
```python
def parse_impact(line):
"""Extract impact value from Impact field."""
# Format: **Impact**: +X points
value = line.split(':', 1)[1].strip()
# Extract number
import re
match = re.search(r'\+(\d+)', value)
if match:
return int(match.group(1))
return 0
```
## Code Fence Extraction
```python
def extract_code_fence(content, start_line):
"""Extract code block starting after current line."""
lines = content.split('\n')
start_idx = lines.index(start_line)
# Find opening fence
for i in range(start_idx, len(lines)):
if lines[i].strip().startswith('```'):
fence_start = i
lang = lines[i].strip()[3:]
break
# Find closing fence
for i in range(fence_start + 1, len(lines)):
if lines[i].strip() == '```':
fence_end = i
break
# Extract content
code_lines = lines[fence_start + 1:fence_end]
return '\n'.join(code_lines)
```
## Validation Rules
### Required Sections
- [ ] High Priority Improvements (may be empty)
- [ ] Medium Priority Improvements (may be empty)
- [ ] Low Priority Improvements (may be empty)
### Required Item Fields
For each improvement item:
- [ ] **File** field present
- [ ] **Dimension** field present
- [ ] **Impact** field present
- [ ] **Current** field present (for edits)
- [ ] **Suggested** field present
### File Path Validity
- [ ] File path is valid format
- [ ] Line numbers are integers (if present)
- [ ] File extension matches content type
### Code Fence Validity
- [ ] Opening fence present
- [ ] Closing fence present
- [ ] Language identifier valid
- [ ] Content non-empty (for suggested)
## Example Improvement Plan
```markdown
# Skill Improvement Plan: example-skill
## Priority Summary
- **High Priority**: 2 items
- **Medium Priority**: 1 item
- **Low Priority**: 1 item
## High Priority Improvements
### 1. Fix Description Trigger Phrases
**File**: SKILL.md:3:5
**Dimension**: Description Quality
**Impact**: +20 points
**Current**:
```yaml
---
name: example-skill
description: Use this for helpful tasks.
---
```
**Suggested**:
```yaml
---
name: example-skill
description: This skill should be used when the user asks to "validate data",
"check schemas", or "verify formats". Perform data validation and schema
checking for JSON and YAML files.
---
```
**Reason**: Add specific trigger phrases and use third-person format.
### 2. Fix Writing Style
**File**: SKILL.md:25:30
**Dimension**: Writing Style
**Impact**: +15 points
**Current**:
```markdown
## Overview
You should use this skill to validate data files. You can choose from
JSON or XML formats.
```
**Suggested**:
```markdown
## Overview
Validate data files in JSON or XML formats with configurable schemas.
```
**Reason**: Change to imperative form, remove second person.
## Medium Priority Improvements
### 1. Add Reference Documentation
**File**: references/validation-rules.md
**Dimension**: Content Organization
**Impact**: +10 points
**Suggested**:
```markdown
# Validation Rules
## JSON Schema Rules
- Required fields validation
- Type checking
- Format validation
## YAML Schema Rules
- Structure validation
- Type coercion rules
```
**Reason**: Move detailed rules to references for progressive disclosure.
## Low Priority Improvements
### 1. Clarify Description
**File**: SKILL.md:50:52
**Dimension**: Writing Style
**Impact**: +5 points
**Current**:
```markdown
## Usage
Use the skill when you need to validate files.
```
**Suggested**:
```markdown
## Usage
Invoke skill for file validation tasks.
```
**Reason**: Use imperative form for consistency.
## Quick Wins (Easy Fixes)
1. Add space after comma in description (+2 points)
2. Fix indentation in examples section (+3 points)
## Estimated Time to Complete
- High Priority: 0.5 hours
- Medium Priority: 0.5 hours
- Low Priority: 0.25 hours
- **Total**: 1.25 hours
## Expected Score Improvement
- Current: 65/100 (D)
- After High Priority: 82/100 (B-)
- After All: 88/100 (B+)
```
## Integration Notes
**Generated by:** `skill-quality-reviewer`
**Consumed by:** `skill-improver`
**Format version:** 1.0
**Compatibility:** Must maintain backward compatibility

View File

@@ -0,0 +1,53 @@
# Supported Update Types
## YAML Frontmatter Updates
Update name or description:
```yaml
# Current
---
name: my-skill
description: A helpful skill for various tasks.
---
# Suggested
---
name: api-contract-manager
description: This skill should be used when the user asks to "validate API contract", "check API compatibility", or "detect breaking changes"
---
```
## SKILL.md Content Updates
Fix writing style (imperative form):
```
# Current
You should create the file first.
You need to validate the input.
# Suggested
Create the file first.
Validate the input.
```
## References/ File Updates
Add new section:
```markdown
## New Section
Content to be added...
```
## New File Creation
Create new example file:
```markdown
# examples/demo.md
Complete example content...
```

View File

@@ -0,0 +1,56 @@
#!/bin/bash
# backup-skill.sh - Backup skill files before applying updates
# Part of skill-improver
# Usage: ./backup-skill.sh <skill-path>
# Example: ./backup-skill.sh ~/.claude/skills/git-workflow
set -euo pipefail
# Check if path provided
if [ $# -eq 0 ]; then
echo "Usage: $0 <skill-path>"
echo "Example: $0 ~/.claude/skills/git-workflow"
exit 1
fi
SKILL_PATH="$1"
SKILL_NAME=$(basename "$SKILL_PATH")
TIMESTAMP=$(date +%Y%m%d-%H%M%S)
BACKUP_DIR="$HOME/.claude/skills/backup/${SKILL_NAME}-${TIMESTAMP}"
# Check if skill path exists
if [ ! -d "$SKILL_PATH" ]; then
echo "Error: Skill path not found: ${SKILL_PATH}"
exit 1
fi
# Create backup directory
echo "Creating backup directory: ${BACKUP_DIR}"
mkdir -p "$BACKUP_DIR"
# Copy entire skill directory
echo "Backing up skill: ${SKILL_NAME}"
cp -R "$SKILL_PATH"/* "$BACKUP_DIR/"
# Create backup manifest
cat > "$BACKUP_DIR/backup-manifest.txt" <<EOF
Backup Manifest
==============
Skill Name: ${SKILL_NAME}
Source Path: ${SKILL_PATH}
Backup Date: $(date)
Timestamp: ${TIMESTAMP}
Files Backed Up:
$(find "$BACKUP_DIR" -type f ! -name "backup-manifest.txt" | sed "s|$BACKUP_DIR/||")
Restore Instructions:
-------------------
To restore this backup, run:
cp -R ${BACKUP_DIR}/* ${SKILL_PATH}/
EOF
echo "Backup complete!"
echo "Backup location: ${BACKUP_DIR}"
echo "Files backed up: $(find "$BACKUP_DIR" -type f ! -name "backup-manifest.txt" | wc -l)"

View File

@@ -0,0 +1,251 @@
#!/bin/bash
# verify-update.sh - Verify skill integrity after applying updates
# Part of skill-improver
# Usage: ./verify-update.sh <skill-path>
# Example: ./verify-update.sh ~/.claude/skills/git-workflow
set -euo pipefail
# Check if path provided
if [ $# -eq 0 ]; then
echo "Usage: $0 <skill-path>"
echo "Example: $0 ~/.claude/skills/git-workflow"
exit 1
fi
SKILL_PATH="$1"
SKILL_NAME=$(basename "$SKILL_PATH")
SKILL_FILE="${SKILL_PATH}/SKILL.md"
# Verification results
PASS=0
FAIL=0
WARN=0
echo "================================"
echo "Skill Update Verification"
echo "================================"
echo "Skill: ${SKILL_NAME}"
echo "Path: ${SKILL_PATH}"
echo ""
# Check 1: SKILL.md exists
echo "Check 1: SKILL.md exists"
if [ -f "$SKILL_FILE" ]; then
echo "✅ PASS: SKILL.md found"
((PASS++))
else
echo "❌ FAIL: SKILL.md not found"
((FAIL++))
echo ""
echo "Verification Summary:"
echo " Passed: ${PASS}"
echo " Failed: ${FAIL}"
echo " Warnings: ${WARN}"
exit 1
fi
echo ""
# Check 2: YAML frontmatter valid
echo "Check 2: YAML frontmatter valid"
if command -v yq &> /dev/null; then
# Use yq if available for proper YAML validation
FRONTMAFTER=$(sed -n '/^---$/,/^---$/{ /^---$/d; p; }' "$SKILL_FILE")
if echo "$FRONTMAFTER" | yq eval '.' > /dev/null 2>&1; then
echo "✅ PASS: YAML frontmatter is valid"
((PASS++))
else
echo "❌ FAIL: Invalid YAML frontmatter"
((FAIL++))
fi
else
# Fallback: basic check for name and description fields
if grep -q "^name:" "$SKILL_FILE" && grep -q "^description:" "$SKILL_FILE"; then
echo "✅ PASS: YAML frontmatter has required fields (name, description)"
((PASS++))
else
echo "❌ FAIL: YAML frontmatter missing required fields"
((FAIL++))
fi
fi
echo ""
# Check 3: Directory structure
echo "Check 3: Directory structure"
DIRS_OK=true
if [ -d "${SKILL_PATH}/references" ]; then
echo " ✅ references/ exists"
else
echo " references/ not found (optional)"
((WARN++))
fi
if [ -d "${SKILL_PATH}/examples" ]; then
echo " ✅ examples/ exists"
else
echo " examples/ not found (optional)"
((WARN++))
fi
if [ -d "${SKILL_PATH}/scripts" ]; then
echo " ✅ scripts/ exists"
# Check if scripts are executable (macOS compatible)
SCRIPT_COUNT=$(find "${SKILL_PATH}/scripts" -type f | wc -l | tr -d ' ')
EXEC_COUNT=0
for script in "${SKILL_PATH}/scripts"/*; do
if [ -f "$script" ] && [ -x "$script" ]; then
((EXEC_COUNT++))
fi
done
if [ "$SCRIPT_COUNT" -gt 0 ] && [ "$EXEC_COUNT" -eq "$SCRIPT_COUNT" ]; then
echo " ✅ All scripts are executable"
elif [ "$SCRIPT_COUNT" -gt 0 ]; then
echo " ⚠️ Some scripts are not executable (${EXEC_COUNT}/${SCRIPT_COUNT} executable)"
((WARN++))
fi
else
echo " scripts/ not found (optional)"
fi
if [ "$DIRS_OK" = true ] || [ ! -d "${SKILL_PATH}/references" ] && [ ! -d "${SKILL_PATH}/examples" ]; then
echo "✅ PASS: Directory structure is valid"
((PASS++))
else
echo "⚠️ WARN: Optional directories missing"
fi
echo ""
# Check 4: SKILL.md size (progressive disclosure check)
echo "Check 4: SKILL.md size (progressive disclosure)"
WORD_COUNT=$(wc -w < "$SKILL_FILE" | tr -d ' ')
if [ "$WORD_COUNT" -lt 3000 ]; then
echo "✅ PASS: SKILL.md is ${WORD_COUNT} words (good progressive disclosure)"
((PASS++))
elif [ "$WORD_COUNT" -lt 5000 ]; then
echo "⚠️ WARN: SKILL.md is ${WORD_COUNT} words (could be more concise)"
((WARN++))
else
echo "❌ FAIL: SKILL.md is ${WORD_COUNT} words (too long, should use references/)"
((FAIL++))
fi
echo ""
# Check 5: No broken references (basic check)
echo "Check 5: Referenced files exist"
BROKEN_REFS=0
# Extract references from SKILL.md
# Look for patterns like "See `references/file.md`" or "**`references/pattern.md`**"
REF_FILES=$(grep -oE 'references/[-_a-zA-Z0-9\.]+' "$SKILL_FILE" | sort -u || true)
if [ -n "$REF_FILES" ]; then
for ref in $REF_FILES; do
REF_PATH="${SKILL_PATH}/${ref}"
if [ -f "$REF_PATH" ]; then
echo "${ref} exists"
else
echo "${ref} referenced but not found"
((BROKEN_REFS++))
fi
done
if [ "$BROKEN_REFS" -eq 0 ]; then
echo "✅ PASS: All referenced files exist"
((PASS++))
else
echo "❌ FAIL: ${BROKEN_REFS} referenced file(s) not found"
((FAIL++))
fi
else
echo " No references found in SKILL.md"
echo "✅ PASS: No broken references"
((PASS++))
fi
echo ""
# Check 6: Writing style (imperative form check)
echo "Check 6: Writing style (imperative form check)"
SECOND_PERSON=$(grep -iE "you should|you need|you can|you must|you'll|your" "$SKILL_FILE" | wc -l | tr -d ' ')
if [ "$SECOND_PERSON" -eq 0 ]; then
echo "✅ PASS: No second-person language found"
((PASS++))
elif [ "$SECOND_PERSON" -lt 5 ]; then
echo "⚠️ WARN: ${SECOND_PERSON} instance(s) of second-person language"
((WARN++))
# Still count as pass for now
((PASS++))
else
echo "❌ FAIL: ${SECOND_PERSON} instances of second-person language"
echo " (should use imperative form)"
((FAIL++))
fi
echo ""
# Check 7: Description quality (basic check)
echo "Check 7: Description quality"
DESCRIPTION=$(grep "^description:" "$SKILL_FILE" | head -1)
if [ -n "$DESCRIPTION" ]; then
# Check for third person
if echo "$DESCRIPTION" | grep -qi "this skill should be used when"; then
echo " ✅ Uses third-person format"
DESC_OK=true
else
echo " ❌ Does not use third-person format"
DESC_OK=false
fi
# Check length (100-300 characters ideal)
DESC_LEN=$(echo "$DESCRIPTION" | cut -d: -f2- | wc -c | tr -d ' ')
if [ "$DESC_LEN" -ge 100 ] && [ "$DESC_LEN" -le 300 ]; then
echo " ✅ Description length is ${DESC_LEN} characters (good)"
elif [ "$DESC_LEN" -lt 100 ]; then
echo " ⚠️ Description is ${DESC_LEN} characters (too short)"
DESC_OK=false
else
echo " ⚠️ Description is ${DESC_LEN} characters (too long)"
DESC_OK=false
fi
if [ "$DESC_OK" = true ]; then
echo "✅ PASS: Description quality is good"
((PASS++))
else
echo "⚠️ WARN: Description could be improved"
((WARN++))
# Still count as pass for basic check
((PASS++))
fi
else
echo "❌ FAIL: No description found in frontmatter"
((FAIL++))
fi
echo ""
echo "================================"
echo "Verification Summary"
echo "================================"
echo " Passed: ${PASS}"
echo " Failed: ${FAIL}"
echo " Warnings: ${WARN}"
echo ""
if [ "$FAIL" -eq 0 ]; then
echo "✅ Verification PASSED"
echo " Skill structure is valid."
exit 0
else
echo "❌ Verification FAILED"
echo " Please review and fix the failed checks."
exit 1
fi