Menü
Bootstraps the agent to check for applicable vibe-engineering skills before every action. Loads at conversation start for skill discovery.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | vibe-using-vibe-engineering |
| description | Bootstraps the agent to check for applicable vibe-engineering skills before every action. Loads at conversation start for skill discovery. |
| user-invocable | true |
You have access to the vibe-engineering skill collection — 34 engineering discipline skills extracted from real-world development.
Before taking any action, check if a vibe-engineering skill applies. Skills use the vibe- prefix.
vibe-research-before-design — SOTA research before proposing architecture/featuresvibe-start-informed — Research agents for real projects, papers, and documented failuresvibe-decision-journal — Record architectural decisions for cross-session memoryvibe-production-mindset — Set "1 million users" quality expectationsvibe-quality-loop — Implement→Review→Test→Fix→Loop until cleanvibe-scope-guard — Detect and redirect scope creepvibe-anti-rationalization-check — Catch shortcut rationalizationvibe-acceptance-gate — Validate against acceptance criteriavibe-coverage-enforcer — Enforce tiered coverage standardsvibe-concurrent-test-safety — Audit for race conditions in testsvibe-adversarial-test-generation — Generate edge case testsvibe-fuzz-parser-inputs — Fuzz test scaffolding for parsersvibe-golden-file-testing — Snapshot tests with temporal normalizationvibe-pattern-library — Record and suggest established patternsvibe-devil-advocate-review — 5-dimension adversarial challengevibe-spec-vs-code-audit — Spec compliance checkvibe-doc-quality-gate — 6-point document quality checkvibe-pre-commit-audit — Secrets, debug statements, TODO scanvibe-safe-deploy — Pre-flight checks with rollbackvibe-rollback-plan — Documented rollback runbookvibe-structured-output — Enforced output formatvibe-reflect-and-compound — Extract learnings from experiencevibe-debugging-journal — Record bug patternsvibe-iteration-review — Quality grading and trendsvibe-handover-doc — Session continuity documentvibe-parallel-task-decomposition — DAG analysis for parallelismvibe-cherry-pick-integration — Safe parallel branch integrationvibe-wave-based-remediation — Prioritized batch fixesvibe-async-task-queue — Cross-session task persistencevibe-requirements-validator — SMART criteria validationvibe-scenario-matrix — Behavioral scenario test planningvibe-service-health-dashboard — Multi-service health checkvibe-session-context-flush — Smart context summarizationALWAYS — This skill should be loaded at the start of every conversation. It's the skill discovery mechanism.
If there's even a 1% chance a vibe- skill applies to what you're doing, invoke it. Check before acting.
| Thought | Reality |
|---|---|
| "This is too simple for a skill" | Simple tasks compound into complex ones |
| "I already know the pattern" | Skills evolve. Read the current version |
| "I'll check after I start" | Check BEFORE starting |
| "The skill is overkill" | Discipline prevents expensive mistakes |
| "Let me just do this one thing" | That one thing is where bugs hide |
Dispatches research agents to find real projects, papers, and documented failures before proposing any feature, architecture, or technology choice. Triggers on creative/design tasks, not on implementation of already-designed specs.
Validates completed work against defined acceptance criteria. Use after completing a task that has specific success criteria defined in issues, specs, or task descriptions.
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.
Detects and prevents shortcut rationalization — when the agent is about to skip a step, simplify a requirement, or optimize away a constraint. Triggers proactively when rationalization patterns are noticed.
Provides a persistent cross-session task queue for work that should be done but isn't blocking current tasks. Enables background and future-session work tracking.
Safely integrates commits from parallel agent branches using sequential cherry-pick. Use after parallel work completes in isolated branches or worktrees.