ssimhan/debugging
skills/debugging/SKILL.md
Use when encountering any bug, test failure, or unexpected behavior. Combines systematic root cause analysis with rigorous verification.
development
Updated Apr 14, 2026
$ install --global
skillsauthnpx skillsauth add ssimhan/meal-planner debuggingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 14, 2026, 2:33 AM17.4s1 file scanned
SKILL.md
- name:
- debugging
- description:
- Use when encountering any bug, test failure, or unexpected behavior. Combines systematic root cause analysis with rigorous verification.
Unified Debugging & Verification
Core Principle: Evidence Over Assertions
Never guess, never patch symptoms, and never claim a fix works without fresh, verifiable evidence.
Phase 1: Root Cause Investigation
NO FIXES WITHOUT INVESTIGATION.
- Reproduce Consistently: Find the exact steps to trigger the bug.
- Trace Data Flow: Trace the back value up the call stack to its origin.
- Gather Evidence: If multi-component, log data at boundaries (API ↔ Service ↔ DB).
- ** علمی Method**: State your hypothesis: "I think X is the root cause because Y."
Phase 2: Hypothesis & Minimal Testing
- Isolate Variables: Make the smallest possible change to test your hypothesis.
- Question Architecture: If 3+ fixes fail, the problem is likely architectural, not a simple bug. Stop and discuss.
Phase 3: The TDD Fix Cycle
- RED: Create a minimal failing test case that reproduces the bug.
- GREEN: Implement the minimal fix addressing the root cause.
- VERIFY: Run the test. It must pass. Run ALL tests to ensure no regressions.
Phase 4: Rigorous Verification
NO COMPLETION CLAIMS WITHOUT EVIDENCE.
- Identify: What command proves this is fixed?
- Run: Execute the FULL command.
- Read: Check exit codes and failure counts.
- Verify: Only claim success if the output explicitly confirms it.
Avoid "should work", "seems fixed", or "looks good". State the evidence.
Related Skills
ssimhan/writing-skills
testing
VerifiedTrustedCommunity
Use when creating new skills, editing existing skills, or verifying skills work before deployment
SKILL.mdUpdated Apr 14, 2026
ssimhan/skills/ui-development
development
VerifiedTrustedCommunity
<!-- This skill integrates patterns from: - Original source: https://github.com/Dammyjay93/interface-design - Author: Dammyjay93 - License: MIT - Integrated into claude-code-quickstart SDK by Sandhya Simhan --> --- name: ui-development description: Build premium, crafted interfaces with audience alignment and design system memory. Automatically invoked by workflows for UI/frontend work. --- # UI Development & Premium Aesthetics ## Scope **Use for:** All web interfaces, dashboards,
SKILL.mdUpdated Apr 14, 2026
ssimhan/test-driven-development
development
VerifiedTrustedCommunity
Use when implementing any feature or bugfix, before writing implementation code
SKILL.mdUpdated Apr 14, 2026
ssimhan/image-generator
development
VerifiedTrustedCommunity
Generate branded images using Google Gemini's image generation API. Supports multiple formats (LinkedIn headers, Medium headers, square concepts, vertical explainers). Reads brand guidelines from the project's BRAND.md file for consistent visual identity.
SKILL.mdUpdated Apr 14, 2026