analyze-bug
Analyzes a specific bug from the issue tracker (analysis only, no code changes)
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Menu
Analyzes a specific bug from the issue tracker (analysis only, no code changes)
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Validate Automation Config, MCP servers, and tokens
Creates backlog epics in issue tracker from a specification document
Multi-agent discussion -- brings 2-3 agent perspectives into one conversation
Run the fix pipeline on a single ticket OR a batch -- auto-resumes from checkpoint if state exists
Implements a feature from the issue tracker -- spec, design, fix, review, test, publish
Interactive wizard for generating Automation Config
| name | analyze-bug |
| description | Analyzes a specific bug from the issue tracker (analysis only, no code changes) |
| allowed-tools | mcp__*, Read, Glob, Grep, Task |
| argument-hint | <ISSUE-ID> |
Analyze bug $ARGUMENTS. Read Automation Config from CLAUDE.md.
Before any pipeline operation, verify MCP tool availability:
mcp__* tool matching the tracker type is accessible/agent-flow:check-setup for diagnostics."$ARGUMENTS is empty, display: "Usage: /agent-flow:analyze-bug " and stop.## Automation Config section with Issue Tracker. If not, report an error and stop.../../core/external-input-sanitizer.md: wrap each piece of external content in --- EXTERNAL INPUT START --- / --- EXTERNAL INPUT END --- markers.
Before dispatch, check Agent Overrides: follow ../../core/agent-override-injector.md for analyst overrides.
Run agent-flow:analyst --phase triage on bug $ARGUMENTS
After successful triage, instruct the agent to post a checkpoint comment to the issue tracker: [agent-flow] Triage completed. Severity: {severity}. Area: {area}.
3a. If triage output contains ## NEEDS_CLARIFICATION (interactive surface — no state.json, no pipeline pause):
question: line and the optional context: line from the triage output.[agent-flow] Triage needs clarification before analysis can proceed.
Question: {question text}
Context: {context text, if present}
Please provide the answer and re-run /agent-flow:analyze-bug with the additional information in the issue description, or answer interactively.
Quality gate: UNCLEAR:[agent-flow] 🔴 Pipeline Block
Agent: analyst
Step: triage
Reason: Issue is unclear — analyst returned Quality gate: UNCLEAR.
Detail: {analyst output explaining what is missing}
Recommendation: {analyst recommendation for what the reporter should clarify}
../../core/agent-override-injector.md for analyst overrides, then run agent-flow:analyst --phase impactNo code changes, no issue tracker state changes. Analysis only.