debug
Deep root cause analysis with fix proposal. Use when the user says "/schovi:debug", "debug this issue", "find the root cause", or "investigate this bug", with a Jira ID, GitHub issue/PR, Datadog URL, error description, or stack trace file. Returns problem summary, root cause, fix proposal, testing strategy, and rollout plan.
What this skill does
# Debug Skill
Structured debugging: parse a problem reference, run root cause analysis in isolated context via the debug-executor subagent, present the fix proposal.
Conversational observability questions ("what's the error rate of X?", a pasted Datadog URL with no debug request) belong to the `datadog-auto-detector` skill, not this one.
## Codex Compatibility
If a Claude-style custom subagent is unavailable, execute the workflow directly with available Codex tools. Use `plugins/schovi/agents/debug-executor/AGENT.md`, `plugins/schovi/agents/datadog-analyzer/AGENT.md`, and `plugins/schovi/agents/jira-analyzer/AGENT.md` as reference instructions. For codebase exploration, use Codex's available exploration tools or built-in subagents.
## Trigger
- User invokes `/schovi:debug <arg>`
- User says "debug this issue", "find the root cause", "investigate this bug"
---
## Workflow
### Phase 1: Argument Parsing
Parse single positional argument (or none). Detect input type in this order:
1. **Jira pattern**: Matches `[A-Z]{2,10}-\d{1,6}` (e.g., EC-1234, PROJ-567)
2. **Datadog URL**: Contains `datadoghq.com` (logs, traces, metrics, etc.)
3. **GitHub PR**: URL, `owner/repo#123`, or `#123` containing "pull"
4. **GitHub Issue**: URL or `owner/repo#123` containing "issues"
5. **File path**: Path exists and is a file (error log, stack trace)
6. **Plain text**: Everything else (error description)
Store: `INPUT_TYPE` and `INPUT_VALUE`
**At least one input source required.** If none provided, ask for a Jira ID, GitHub URL, Datadog URL, or error description.
### Phase 2: Execute Debug (Isolated Context)
Spawn debug-executor subagent to perform ALL debugging work in isolated context.
```
Task tool configuration:
subagent_type: "schovi:debug-executor:debug-executor"
description: "Execute debug workflow"
prompt: |
PROBLEM REFERENCE: [INPUT_VALUE]
CONFIGURATION:
- identifier: [auto-detect from INPUT_VALUE or generate slug]
- severity: [auto-detect or "Medium"]
- input_type: [INPUT_TYPE]
Execute complete debugging workflow:
1. Fetch external context (Jira/GitHub/Datadog if applicable)
2. Deep debugging & root cause analysis (Explore subagent, very thorough mode)
3. Generate fix proposal (location, code changes, testing, rollout)
Return structured fix proposal (~1500-2500 tokens).
```
**Expected output**: Complete structured fix proposal markdown (~1500-2500 tokens) with problem summary, root cause with execution flow, fix proposal with code changes, testing strategy, rollout plan. All file references in file:line format.
### Phase 3: Terminal Output
Display the fix proposal directly in terminal:
```markdown
# Debug Complete: [identifier]
Root cause analysis and fix proposal ready.
## Root Cause
[Extract root cause summary - 2-3 sentences]
## Fix Location
[Extract fix location - file:line]
## Fix Proposal
[Full fix proposal from executor output]
## Next Steps
Ready to implement the fix.
```
---
## Error Handling
- **No input provided**: Ask user for Jira ID, GitHub URL, Datadog URL, or error description
- **Invalid format**: Report error, show format examples
- **File not found**: Report error, ask for correct path
- **Executor failed**: Report error with details from subagent
- **External fetch failed** (Jira/GitHub/Datadog inside executor): Report error, suggest checking auth or MCP server config
## Quality Gates
Before completing, verify:
- [ ] Input processed successfully with clear problem reference
- [ ] debug-executor invoked with full three-part subagent type
- [ ] Output received within token budget
- [ ] All file references use file:line format
- [ ] Terminal output displayed
## Example Usage
```bash
/schovi:debug EC-1234 # from Jira issue
/schovi:debug https://app.datadoghq.com/apm/trace/abc123 # from Datadog trace
/schovi:debug https://github.com/owner/repo/issues/456 # from GitHub issue
/schovi:debug "NullPointerException in UserService.authenticate at line 123"
/schovi:debug ./error.log # from stack trace file
```
Related in Code Review
gstack
IncludedFast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)
startup-due-diligence
IncludedLegal due diligence review for seed-stage and Series A startups (US, Delaware C-Corp focus). Supports both investor and founder perspectives. Capabilities include: (1) Interactive document review and issue spotting; (2) Document request list generation; (3) Cap table and SAFE/convertible note analysis; (4) Red flag identification with severity ratings; (5) Diligence report generation. TRIGGERS: due diligence, DD, startup investment, cap table review, Series A, seed round, investor diligence, legal review startup, SAFE analysis, convertible note, 409A, founder vesting.
interview-master
IncludedThis skill should be used when the user asks to "generate interview questions", "prepare for interview", "optimize resume", "conduct mock interview", "analyze git commits for resume", "generate resume from code", "review my resume", or mentions interview preparation, career assistance, or extracting project experience from git history. Provides comprehensive interview and career development guidance for both job seekers and interviewers.
fix-issue
IncludedFixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to avoid recurrence. Use when debugging errors, resolving regressions, fixing bugs, or triaging issues.
sf-apex
IncludedGenerates and reviews Salesforce Apex code with 150-point scoring. TRIGGER when: user writes, reviews, or fixes Apex classes, triggers, test classes, batch/queueable/schedulable jobs, or touches .cls/.trigger files. DO NOT TRIGGER when: LWC JavaScript (use sf-lwc), Flow XML (use sf-flow), SOQL-only queries (use sf-soql), or non-Salesforce code.
swift-development
IncludedComprehensive Swift development for building, testing, and deploying iOS/macOS applications. Use when Claude needs to: (1) Build Swift packages or Xcode projects from command line, (2) Run tests with XCTest or Swift Testing framework, (3) Manage iOS simulators with simctl, (4) Handle code signing, provisioning profiles, and app distribution, (5) Format or lint Swift code with SwiftFormat/SwiftLint, (6) Work with Swift Package Manager (SPM), (7) Implement Swift 6 concurrency patterns (async/await, actors, Sendable), (8) Create SwiftUI views with MVVM architecture, (9) Set up Core Data or SwiftData persistence, or any other Swift/iOS/macOS development tasks.