Routes to the right vibe-engineering skill for the current task and lists the full catalog. Use when the user asks which skill to use, asks what vibe-engineering can do, or is unsure how to approach a task.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
The vibe-engineering skill router. Skills are normally picked automatically from their descriptions; this skill is for when the user wants to browse, or isn't sure which one fits.
Ask what the user is trying to do (unless it's already clear), then recommend one starting skill and at most two follow-ups. Don't recite the whole catalog unless asked.
→ Before: vibe-research-before-design, then vibe-requirements-validator if there's a PRD
→ During: vibe-scope-guard, vibe-production-mindset (production code)
→ After: vibe-quality-loop, vibe-acceptance-gate
→ 1–5 bugs: fix directly, then vibe-reflect-and-compound for any non-trivial one
→ Intermittent / "flaky" failure: vibe-flake-root-cause
→ 10+ bugs or findings: vibe-gap-closure-loop
→ Prevent recurrence: vibe-adversarial-test-generation
→ Design or large change: vibe-devil-advocate-review (panel mode for multi-agent release candidates)
→ Spec compliance: vibe-spec-sync --audit
→ "Tear this apart" (any artifact, any domain): vibe-devil-advocate-review
→ Docs: vibe-doc-quality-gate · Requirements: vibe-requirements-validator
→ Prose that reads as machine-written: vibe-slop-filter
→ Planning: vibe-scenario-matrix · Coverage: vibe-coverage-enforcer
→ Edge cases: vibe-adversarial-test-generation · Parsers: vibe-fuzz-parser-inputs
→ Snapshots: vibe-golden-file-testing · Concurrency: vibe-concurrent-test-safety
→ Commit: vibe-pre-commit-audit, vibe-spec-sync
→ Deploy: vibe-safe-deploy · Risky change: vibe-rollback-plan
→ Publishing drafted or privately sourced content: vibe-publication-leak-guard
→ Running services: vibe-service-health-dashboard
→ One-shot fan-out: vibe-parallel-task-decomposition → Integrate: vibe-cherry-pick-integration
→ Multi-phase project with long-lived agents: vibe-workstream-orchestration
→ Audit: vibe-gap-analysis → Close gaps: vibe-gap-closure-loop
→ Research: vibe-research-before-design → Record: vibe-decision-journal → Challenge: vibe-devil-advocate-review
→ Learnings, bugs, patterns: vibe-reflect-and-compound
→ Handing off, or winding down at a usage limit: vibe-handover-doc
→ End of sprint: vibe-iteration-review
→ vibe-acceptance-gate, then vibe-anti-rationalization-check
| Area | Skills |
|---|---|
| Research & decisions | vibe-research-before-design, vibe-decision-journal, vibe-devil-advocate-review |
| Quality gates | vibe-acceptance-gate, vibe-quality-loop, vibe-anti-rationalization-check, vibe-spec-sync, vibe-doc-quality-gate, vibe-requirements-validator, vibe-coverage-enforcer, vibe-slop-filter |
| Knowledge & continuity | vibe-reflect-and-compound, vibe-handover-doc |
| Parallel work | vibe-parallel-task-decomposition, vibe-workstream-orchestration, vibe-cherry-pick-integration |
| Testing | vibe-scenario-matrix, vibe-adversarial-test-generation, vibe-fuzz-parser-inputs, vibe-golden-file-testing, vibe-concurrent-test-safety, vibe-flake-root-cause |
| Deployment & ops | vibe-pre-commit-audit, vibe-publication-leak-guard, vibe-safe-deploy, vibe-rollback-plan, vibe-service-health-dashboard |
| Gap analysis | vibe-gap-analysis, vibe-gap-closure-loop |
| Process | vibe-scope-guard, vibe-production-mindset, vibe-iteration-review |
| Meta | vibe-help |
/vibe-engineering:<skill-name> (plugin install) or /<skill-name>$<skill-name>/skills lists what's installedRecommended: vibe-[skill] — [one line on why it fits]
Then: vibe-[skill], vibe-[skill] (optional follow-ups)
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Validates completed work against defined acceptance criteria. Use after completing a task that has specific success criteria defined in issues, specs, or task descriptions.
The English summary is being prepared. Showing the original description.
Generates edge case, failure mode, and spec-driven test cases. Covers boundary values, nil inputs, concurrency, resource exhaustion, malformed data, and requirement-linked traceability tests. Use after happy-path tests exist and before claiming coverage is complete, when requirements lack tests, or before a security review.
The English summary is being prepared. Showing the original description.
Catches shortcuts and reward hacking — weakening or deleting tests to make them pass, hard-coding expected outputs, silently dropping requirements, or claiming work is done without running it. Use before declaring a task complete and whenever a test or requirement feels like it's in the way.
The English summary is being prepared. Showing the original description.
Safely integrates commits from parallel agent branches using sequential cherry-pick. Use after parallel work completes in isolated branches or worktrees.
The English summary is being prepared. Showing the original description.
Audits tests for concurrency safety — race conditions, shared mock state, cleanup ordering. Use when writing tests that involve goroutines, async operations, or shared mutable state.
The English summary is being prepared. Showing the original description.
Enforces tiered test coverage standards with three dimensions — line coverage by tier, spec-to-test traceability, and spec-to-code implementation mapping. Use before claiming code is complete.
The English summary is being prepared. Showing the original description.