Use when a review finding cannot be fixed in current PR - creates properly documented tracking issue with full context, linked to parent, following full issue-driven-development process
Creates a properly documented tracking issue when a review finding can't be fixed in the current PR. Use during code review when findings are out of scope, require external dependencies, or would cause breaking changes.
/plugin marketplace add troykelly/claude-skills/plugin install issue-driven-development@troykelly-skillsThis skill is limited to using the following tools:
Process for creating tracking issues when review findings cannot be addressed in the current PR.
Core principle: No finding disappears. Every deferral is tracked.
ABSOLUTE REQUIREMENT: Deferred findings MUST have tracking issues. There is no other option.
A finding may ONLY be deferred when:
| Valid Reason | Example |
|---|---|
| Out of scope | Finding requires architectural change beyond PR scope |
| External dependency | Requires infrastructure/config change |
| Breaking change | Would require major version bump |
| Separate concern | Logically independent from current work |
| Invalid Approach | Reality |
|---|---|
| "We'll fix it later" | Without tracking, later never comes |
| "It's minor" | Minor issues compound into major problems |
| "Not my problem" | You found it, you track it |
| "Good enough" | Good enough creates technical debt |
Ask yourself:
Document:
Use this template:
## [Finding] [Brief description] (from #[PARENT])
### Origin
This issue was created during code review of #[PARENT_ISSUE].
| Property | Value |
|----------|-------|
| Parent Issue | #[PARENT_ISSUE] |
| Parent PR | #[PARENT_PR] (if exists) |
| Finding ID | F-[PARENT]-[N] |
| Severity | [CRITICAL/HIGH/MEDIUM/LOW] |
| Review Criterion | [Which of 7 criteria OR OWASP category] |
| Depth | [N] |
### Finding Details
**What was found:**
[Detailed description of the issue - be specific]
**Location:**
- File: `[path/to/file.ts]`
- Line(s): [N-M]
- Function: `[functionName()]`
**Why it matters:**
[Impact if not addressed - be concrete]
**Evidence:**
```[language]
[Code snippet showing the issue]
[Explain why this cannot be fixed in the parent PR]
| Reason | Details |
|---|---|
| Category | [out-of-scope / external-dependency / breaking-change / separate-concern] |
| Justification | [Specific explanation] |
Labels: review-finding, spawned-from:#[PARENT], depth:[N], [severity]
This issue follows the full issue-driven-development process including its own code review.
### Step 4: Create Issue via CLI
```bash
gh issue create \
--title "[Finding] Rate limiting needed on auth endpoint (from #123)" \
--body "$(cat <<'EOF'
[Full template body here]
EOF
)" \
--label "review-finding" \
--label "depth:1" \
--label "high"
Note: Create the spawned-from:#N label if it doesn't exist:
gh label create "spawned-from:#123" --color "C2E0C6" --description "Spawned from issue #123" 2>/dev/null || true
gh issue edit [NEW_ISSUE] --add-label "spawned-from:#123"
Add the new issue to the "Findings Deferred" section:
### Findings Deferred (With Tracking Issues)
| # | Severity | Finding | Tracking Issue | Justification |
|---|----------|---------|----------------|---------------|
| 1 | HIGH | Rate limiting needed | #456 | Requires infrastructure changes |
If the deferred finding BLOCKS the parent PR (e.g., critical security issue):
# Add awaiting label
gh issue edit 123 --add-label "status:awaiting-dependencies"
# Post deviation comment
gh issue comment 123 --body "$(cat <<'EOF'
## Deviation: Awaiting Dependencies
This issue cannot proceed until deferred findings are resolved.
| Property | Value |
|----------|-------|
| Blocked At | Step 9 (Code Review) |
| Dependencies | #456 |
| Reason | Critical deferred finding blocks PR |
Work will resume when #456 is complete.
EOF
)"
Once created, the tracking issue:
| Depth | Meaning |
|---|---|
| 1 | Finding from original issue's review |
| 2 | Finding from a depth-1 issue's review |
| 3+ | Deeper nesting - flag for human attention |
At depth 3+:
**Deep Finding Chain Detected**
This issue is at depth [N]. Chain:
- #100 (original)
- #101 (depth 1)
- #102 (depth 2)
- #103 (depth 3) - Current
Consider: Is there a systemic issue requiring broader attention?
Required labels for tracking issues:
| Label | Purpose |
|---|---|
review-finding | Identifies as born from review |
spawned-from:#N | Links to parent issue |
depth:N | Tracks nesting level |
[severity] | critical/high/medium/low |
Optional labels:
security - Security-related findingstatus:pending - Ready for workBefore marking finding as deferred:
This skill is called by:
apply-all-findings - When finding cannot be fixedcomprehensive-review - When documenting deferralsThis skill creates:
issue-driven-development processThis skill references:
issue-lifecycle - Issue managementissue-driven-development - Process for new issuesThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.