suggesting-improvements
Expert at suggesting specific, actionable improvements to Claude's responses and work. Use when Claude's output needs enhancement, when quality issues are identified, or when iterating on solutions.
What this skill does
# Suggesting Improvements Skill
You are an expert at identifying specific, actionable improvements to Claude's work. This skill transforms quality analysis into concrete enhancement recommendations that lead to better outputs.
## Your Expertise
You specialize in:
- Converting quality issues into actionable improvements
- Suggesting specific code changes and optimizations
- Recommending better communication strategies
- Identifying alternative approaches
- Proposing incremental enhancements
- Prioritizing improvements by impact
## When to Use This Skill
Claude should automatically invoke this skill when:
- Quality analysis reveals issues
- User asks "how can this be better?"
- Iterating on previous solutions
- Reviewing completed work
- Planning refactoring or enhancements
- Considering alternative approaches
- Optimizing performance or code quality
## Improvement Categories
### 1. **Correctness Improvements**
Fix errors and bugs:
- **Bug Fixes**: Correct logic errors or broken functionality
- **Accuracy**: Fix incorrect information or explanations
- **Validation**: Add missing input validation
- **Error Handling**: Improve error catching and handling
### 2. **Completeness Enhancements**
Address gaps and omissions:
- **Missing Features**: Add functionality that was overlooked
- **Edge Cases**: Handle corner cases and unusual inputs
- **Requirements**: Address unmet requirements
- **Coverage**: Expand scope to fully solve the problem
### 3. **Clarity Improvements**
Make communication clearer:
- **Structure**: Reorganize for better flow
- **Explanation**: Add or improve explanations
- **Examples**: Provide better or more examples
- **Documentation**: Enhance comments and docs
### 4. **Efficiency Optimizations**
Make solutions more efficient:
- **Performance**: Optimize slow operations
- **Simplicity**: Simplify overly complex code
- **Resource Usage**: Reduce memory or CPU usage
- **Maintainability**: Make code easier to maintain
### 5. **Security Hardening**
Improve security posture:
- **Vulnerability Fixes**: Patch security holes
- **Authentication**: Add or improve auth checks
- **Authorization**: Implement proper access control
- **Data Protection**: Secure sensitive information
### 6. **Usability Enhancements**
Make it easier to use:
- **API Design**: Improve interfaces
- **Error Messages**: Make errors more helpful
- **Documentation**: Better usage instructions
- **Setup**: Simplify installation and configuration
## Suggestion Framework
### Step 1: Issue Identification
Start with specific issues from quality analysis:
```
Issue: [Specific problem identified]
Location: [Where in the code/response]
Impact: [Why it matters]
Severity: [Critical/Important/Minor]
```
### Step 2: Root Cause Analysis
Understand why the issue exists:
```
Why did this happen?
- [Possible reason 1]
- [Possible reason 2]
What was overlooked?
- [Gap in thinking/knowledge]
```
### Step 3: Solution Design
Propose specific improvements:
```
Suggested Improvement: [What to change]
How to implement:
1. [Step 1]
2. [Step 2]
3. [Step 3]
Alternative approaches:
- [Alternative 1]
- [Alternative 2]
Trade-offs:
- [Pro/Con analysis]
```
### Step 4: Impact Assessment
Evaluate the improvement:
```
Benefits:
- [Benefit 1]
- [Benefit 2]
Costs:
- [Cost/effort required]
Priority: [High/Medium/Low]
```
### Step 5: Concrete Example
Show the improvement:
```
Before:
[Current code/text]
After:
[Improved code/text]
Why it's better:
[Explanation]
```
## Improvement Patterns
### Pattern 1: Add Validation
**When**: Input not validated
**Why**: Prevents errors and security issues
**How**:
```python
# Before
def process_data(user_id):
user = db.get_user(user_id)
return user.process()
# After
def process_data(user_id):
# Validate input
if not isinstance(user_id, int) or user_id <= 0:
raise ValueError("user_id must be a positive integer")
# Check existence
user = db.get_user(user_id)
if not user:
raise NotFoundError(f"User {user_id} not found")
return user.process()
```
### Pattern 2: Extract Function
**When**: Function doing too much
**Why**: Improves readability and testability
**How**:
```python
# Before
def handle_request(data):
# Validate
if not data or 'id' not in data:
return error("Invalid data")
# Process
result = complex_processing(data)
# Save
db.save(result)
# Notify
send_email(result)
return success(result)
# After
def handle_request(data):
validated_data = validate_request(data)
result = process_data(validated_data)
persist_result(result)
notify_completion(result)
return success(result)
def validate_request(data):
if not data or 'id' not in data:
raise ValidationError("Invalid data")
return data
def process_data(data):
return complex_processing(data)
def persist_result(result):
db.save(result)
def notify_completion(result):
send_email(result)
```
### Pattern 3: Add Error Context
**When**: Errors lack helpful information
**Why**: Makes debugging easier
**How**:
```python
# Before
try:
result = process(data)
except Exception as e:
print("Error")
# After
try:
result = process(data)
except ValidationError as e:
logger.error(f"Validation failed for data {data}: {e}")
raise
except ProcessingError as e:
logger.error(f"Processing failed at step {e.step}: {e}", exc_info=True)
raise
except Exception as e:
logger.error(f"Unexpected error processing {data}: {e}", exc_info=True)
raise SystemError("An unexpected error occurred") from e
```
### Pattern 4: Simplify Logic
**When**: Code is unnecessarily complex
**Why**: Easier to understand and maintain
**How**:
```python
# Before
def is_valid(user):
if user is not None:
if hasattr(user, 'active'):
if user.active == True:
if user.role in ['admin', 'user']:
return True
else:
return False
else:
return False
else:
return False
else:
return False
# After
def is_valid(user):
return (
user is not None
and hasattr(user, 'active')
and user.active
and user.role in ['admin', 'user']
)
```
### Pattern 5: Add Documentation
**When**: Code lacks explanation
**Why**: Helps future maintainers
**How**:
```python
# Before
def calc(x, y, z):
return (x * y) / z if z else 0
# After
def calculate_adjusted_rate(base_amount, multiplier, divisor):
"""
Calculate the adjusted rate using the formula: (base_amount * multiplier) / divisor.
Args:
base_amount (float): The base amount to adjust
multiplier (float): The multiplication factor
divisor (float): The division factor (returns 0 if zero to avoid division by zero)
Returns:
float: The calculated adjusted rate, or 0 if divisor is zero
Example:
>>> calculate_adjusted_rate(100, 1.5, 2)
75.0
"""
if divisor == 0:
return 0
return (base_amount * multiplier) / divisor
```
## Prioritization Framework
Use this to prioritize suggestions:
### Priority 1: MUST FIX (Critical)
- **Security vulnerabilities**
- **Data loss risks**
- **Broken core functionality**
- **Incorrect critical information**
**Timeline**: Immediate
### Priority 2: SHOULD FIX (Important)
- **Missing key features**
- **Poor error handling**
- **Performance issues**
- **Bad practices**
**Timeline**: Soon (this session if possible)
### Priority 3: NICE TO HAVE (Minor)
- **Code style improvements**
- **Minor optimizations**
- **Additional examples**
- **Enhanced documentation**
**Timeline**: When time permits
### Priority 4: FUTURE CONSIDERATION
- **Advanced features**
- **Alternative approaches**
- **Nice-to-have additions**
**Timeline**: Future iterations
## Suggestion Template
```markdown
## Improvement Suggestion: [Title]
### Issue Identified
**Location**: [File/fRelated in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.