kaizen-bug-router
Identify the correct project repository for bugs and file issues automatically.
Install
mkdir -p .claude/skills/kaizen-bug-router && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11815" && unzip -o skill.zip -d .claude/skills/kaizen-bug-router && rm skill.zipInstalls to .claude/skills/kaizen-bug-router
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Investigate bugs in kaizen-agents-org, identify which project owns the failing behavior, and file a GitHub issue in the correct repository. Use when a user reports a Kaizen Agents bug, regression, broken workflow, unexpected issue-to-PR behavior, agent orchestration failure, verifier failure, builder failure, or org-level skill/documentation bug; if ownership is unclear after investigation, file the bug in kaizen-loop by default.Key capabilities
- →Investigate Kaizen Agents bug reports
- →Identify the owning project for failing behavior
- →File a GitHub issue in the correct repository
- →Check for existing issues before creating new ones
- →Create issues with clear titles, evidence, and routing rationale
- →Report created issue URL, repository, and labels
How it works
The skill investigates Kaizen Agents bug reports to determine the originating project and files a GitHub issue in the appropriate repository, using `kaizen-loop` as a fallback.
Inputs & outputs
When to use kaizen-bug-router
- →Report a kaizen agent bug
- →File issue in correct repo
- →Debug agent orchestration failures
About this skill
Kaizen Bug Router
Rule
When a Kaizen Agents bug is reported, investigate where the bug originates before filing an issue. File exactly one primary issue in the owning repository. If the owner cannot be determined with reasonable evidence, file the issue in kaizen-agents-org/kaizen-loop.
Repository Routing
kaizen-agents-org/builder-agent: builder execution, build request/result contracts, Codex/Claude backend invocation, self-review, implementation output, builder artifacts, or generated change quality before verifier review.kaizen-agents-org/verifier: verifier execution, verdict schemas, MVP verdict statuses (open_pr,open_pr_with_warning,block_pr,needs_context),must_fix/should_fixsemantics, approval/rejection logic, verification prompts, risk evaluation, or verifier result artifacts.kaizen-agents-org/kaizen-loop: issue selection, labels, scheduling, registry/config loading, orchestration, retry loops, workspace/git handling, GitHub issue/PR operations, reflection policy, protected path handling, comments, or cross-agent handoff.kaizen-agents-org/coderabbit: CodeRabbit configuration, review policy, automated review rules, or review feedback behavior owned by the shared CodeRabbit setup.kaizen-agents-org/renovate-config: Renovate presets, dependency update policy, package rule behavior, or shared dependency automation configuration.kaizen-agents-org/.github: org-level shared docs, issue templates, reusable skills, PR/issue linking guidance, or org configuration.
Use kaizen-loop as the fallback when symptoms span multiple projects or the available evidence does not isolate a clearer owner.
Workflow
-
Gather evidence from the user's report, local logs, failing commands, linked issues/PRs, and relevant code.
-
Reproduce or narrow the failure when practical. Keep the investigation focused on ownership; do not implement the fix in this workflow unless the user asks.
-
Check for an existing issue before creating a new one:
gh issue list --repo kaizen-agents-org/<repo> --search "<short error or behavior>" -
Choose the target repository using the routing rules above. If uncertain, choose
kaizen-agents-org/kaizen-loopand say why ownership is unclear. -
Create the issue with a clear title, evidence, and routing rationale. Prefer labels that exist in the target repository:
gh label list --repo kaizen-agents-org/<repo> --limit 200 gh issue create --repo kaizen-agents-org/<repo> --title "<title>" --body-file <body-file>
Only pass --label values that exist. Prefer bug for ordinary bug reports and add the base kaizen label by default when it exists. Treat kaizen as a visibility/routing label, not execution authorization. If no useful labels exist, create the issue without labels rather than blocking.
Issue creation and execution authorization are separate:
- Add
kaizenby default when the label exists, but do not addkaizen:authorized,kaizen:ready, or any other authorization or selection label by default. - When the user asks to queue, approve, run, execute, or put the issue on the Kaizen Loop, add both the repository's execution authorization label and its configured
issues.selection.includeLabelwhen those labels exist. - In the managed opt-in fleet, this means adding both
kaizen:authorizedandkaizen:ready; either label alone leaves the issue ineligible. - If the user asks for immediate execution, file the issue, add both labels when available, then report the explicit command that should run next, such as
kaizen fix <issue>. - If the issue needs human clarification before automation, do not add an authorization or selection label; state what clarification is needed.
Issue Body
Use this structure:
## Bug
<What failed or behaved unexpectedly.>
## Evidence
- <Exact command, log excerpt, PR/issue link, file path, or observed behavior.>
## Expected
<What should happen instead.>
## Routing
Filed in `<repo>` because <short ownership rationale>.
## PR linkage requirement
The implementation PR for this issue must target the repository default branch,
include `Closes #<issue-number>` for same-repository work or `Closes
kaizen-agents-org/<repo>#<issue-number>` for cross-repository work in the PR
body, and verify `gh pr view <pr> --json baseRefName,closingIssuesReferences,isDraft`
before reporting the PR ready. Do not rely on a PR title, branch name, or issue
comment as proof that GitHub will close the issue on merge.
## Notes
- If ownership is uncertain, state what was checked and why this issue falls back to `kaizen-loop`.
Output
After filing, report:
- created issue URL
- selected repository
- labels applied
- one-sentence routing rationale
If a duplicate issue exists, do not create another issue. Return the existing issue URL and the reason it matches.
When not to use it
- →Implementing the fix for a bug
- →When ownership cannot be determined with reasonable evidence and kaizen-loop is not the fallback
- →Creating duplicate issues when one already exists
Limitations
- →Does not implement the fix for the bug
- →Files exactly one primary issue per bug
- →Requires reasonable evidence to determine ownership
How it compares
This skill provides a deterministic routing table for bug reports across multiple repositories, ensuring issues are filed in the correct project with specific content requirements, unlike general issue creation.
Compared to similar skills
kaizen-bug-router side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| kaizen-bug-router (this skill) | 0 | 1mo | Review | Intermediate |
| resolve-conflicts | 81 | 8mo | Review | Intermediate |
| claude-automation-recommender | 47 | 2mo | Review | Beginner |
| codex-skill | 12 | 5mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
resolve-conflicts
antinomyhq
Use this skill immediately when the user mentions merge conflicts that need to be resolved. Do not attempt to resolve conflicts directly - invoke this skill first. This skill specializes in providing a structured framework for merging imports, tests, lock files (regeneration), configuration files, and handling deleted-but-modified files with backup and analysis.
claude-automation-recommender
anthropics
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.
codex-skill
feiskyer
Use when user asks to leverage codex, gpt-5, or gpt-5.1 to implement something (usually implement a plan or feature designed by Claude). Provides non-interactive automation mode for hands-off task execution without approval prompts.
git-advanced-workflows
wshobson
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
subagent-driven-development
davila7
Use when executing implementation plans with independent tasks in the current session
validate-openapi-specs
epieczko
Validates and registers hook manifest files (YAML) in the Hook Registry for versioned hook management.