claude-config

Use when building a standalone FastMCP server that wraps a REST API as MCP tools — either adding/editing a tool in APEX's own `mcp/server.py`, or scaffolding a NEW wrapper for an external vendor API (CyberArk, ServiceNow, etc.). Triggers on "add MCP tool", "wrap endpoint as MCP", "sync mcp/server.py", "MCP wrapper for {vendor}", "expose REST API as MCP".

Yeni bir feature için hafif PRD üretir (tam spec-first-feature pipeline'ı değil). docs/SYSTEM.md + hedefli grep ile harmony'yi garanti eder, Entegrasyon bölümünü zorunlu kılar ve docs/prd-{feature}.progress.md ile aktif PRD işaretini kurar. prd-run bittikten sonra test-plan → qa-eval-developer → project-manager (AUTO-GO) → git push → live-test pipeline'ını otomatik tetikler. Tetikleyiciler: prd-guard uyarısı sonrası, "kısa PRD yaz", "mini PRD", "bu küçük feature için spec".

PRD-first workflow for designing features in an existing codebase. Produces a production-ready PRD grounded in a SYSTEM.md scan of the actual code, industry research, an explicit risk register, and binary acceptance criteria. Use whenever the user wants to design, plan, scope, or specify a feature — or mentions "PRD", "spec", "feature design", "let's add X", "new page or module", "yeni feature", "PRD hazırlayalım", "spec yazalım", "şu özelliği ekleyelim". Also use for a system documentation file, codebase overview, or architecture doc. Enforces a hard sequence with agent-owned acceptance gates — system doc, research, PRD draft, PRD finalize, implementation — where software-architect/devops-engineer agents render GO or NO-GO and refuse to skip the PRD. Runs autonomously to implementation and auto-invokes /prd-run on architect GO. Operator consulted only on CANNOT-ANSWER product-intent gaps. Execution-time LAWs (remote git, AWS public/delete) still require operator approval.

GetirFinans Splunk ortamı için org-spesifik referans. gf_pdks (PDKS kapı-turnike) ve waf-traffic (F5 BIG-IP ASM/Bot) indexlerinin alan sözlükleri, kritik tuzaklar ve çalışan SPL pattern'leri. Splunk sorgusu yazarken, alan adı doğrularken, ya da index/sourcetype seçerken tetikle. Tetikleyiciler: "splunk sorgusu", "spl yaz", "gf_pdks", "waf-traffic", "f5 log", "pdks sorgu", "kapı geçiş", "waf analiz", "splunk-reference-expert".

Agent işini bitirince merge kuyruğuna ekler. Mevcut branch'i, değişen dosyaları ve commit geçmişini okuyup merge-queue.json'a yazar. Koordinatör bu kuyruğu okur ve sırayla merge eder. Tetikleyici: /submit-to-queue, "kuyruğa ekle", "merge için hazırım".

Use when the operator reports that APEX is misbehaving and wants it diagnosed — Slack bot silent/wrong, MCP/tool call failing, web/API 5xx, or orchestrator misrouting. Triggers on /apex-debug, "apex bozuk", "apex debug et", "bot cevap vermiyor", "tool patlıyor", "dashboard hata veriyor", "orchestrator yanlış routing", "neden çalışmıyor". Runs a read-only triage → evidence → root-cause → fix-in-worktree → architect-verify flow and STOPS at a verified fix proposal (no commit/push/deploy).

Use when deciding how a project should be deployed or what infrastructure/CI-CD to set up, when starting a project's ops layer, when asked "how do I deploy this", when a DEPLOY.md exists and may have drifted, OR when asked to ACTUALLY run/execute a deployment from DEPLOY.md and prove it works. Triggers on "deploy", "deploy et", "uygulamayı deploy et", "run the deploy", "execute deployment", "deploy çalıştır", "go live", "prod'a çık", "deployment", "infra", "infrastructure", "CI/CD", "pipeline", "DEPLOY.md", "drift", "nasıl deploy ederim", "altyapı kur", "production setup".

This skill should be used when the user asks to implement, run, execute, or verify a PRD produced by spec-first-feature. Triggers on /prd-run, "implement this PRD", "Phase 3 başlat", "run the PRD", or any request to take an approved PRD and turn it into working code with automated AC verification. Orchestrates phase-by-phase implementation — domain-routed to specialist agents (inference/orchestrator/rag/mcp/devops-engineer) when the phase matches a domain, else generic prd-run-impl — with verification and fix loops (Opus).

k3s_dc üzerinde çalışan APEX botunu mock test suite ile uçtan uca test eder. Kimlik çözümleme, orchestrator routing, KB, dosya oluşturma ve web search yeteneklerini doğrular.

Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.

You are an advanced Docker containerization expert with comprehensive, practical knowledge of container optimization, security hardening, multi-stage builds, orchestration patterns, and production deployment strategies based on current industry best practices.

Use after a deployment to run QA golden-path tests (core lanes + LLM-driven UI exploration) and classify failures. Triggers on /qa-test, "qa test", "deploy sonrası test", "qa agent çalıştır", "post-deploy qa", "run qa tests", "deployment test et", "qa koş". Runs the deterministic core (smoke/backend/ui-regression/bot lanes) then drives Claude-in-Chrome for critical UI flows, maps every failure to an apex-debug symptom class, and prints a pass/fail summary with handoff suggestions.

Use when onboarding/registering a new MCP server into the APEX backend so the LLM agent can call its tools at runtime — deciding registry table (connector vs user), auth_mode (oauth2/api_key/internal), credential_scope (personal/company), KB seeder sync, and health-probe transport. Triggers on "add MCP integration", "onboard MCP server", "register tool-call MCP", "new vendor MCP", "MCP not showing in agent".

Use when starting or doing any work that touches a project's code or features — to know "what does this code affect (will affect / did affect / was affecting)" BEFORE changing it, and to load the relevant prior completed work so you don't reinvent or contradict it. Reads a per-project derived knowledge catalog (docs/catalog.json) and, once per session per topic, dispatches a subagent that returns a pointer-brief (file:line + verbatim critical constraints, decisions, acceptance-criteria) instead of bloating context. Supports forward queries (feature → affected paths) and reverse queries (path → features/decisions that touched it). Triggers on "what does this affect", "neye etki ediyor / etti / ediyordu", "bu kodu kim kullanıyor", "bu değişiklik neyi kırar", starting a feature, editing a tagged module, "load prior work on X", "impact-lens", "/impact-lens".

Use when attacking a PRD's soundness before implementation — surfacing unstated assumptions, running a pre-mortem on how the feature fails in production, and auditing whether the research actually supports the chosen approach. Invoked by prd-review's adversarial phase, or directly via "devil's advocate this PRD", "PRD'yi çürüt", "what could go wrong with this spec", "pre-mortem this feature", "challenge this PRD's assumptions". PRD-scoped — maps every counter-argument to a PRD section.

Use when a PRD is finished and about to be implemented by an autonomous AI agent (e.g. before /prd-run), or when asked to review/critique/stress-test a PRD or spec for AI-implementability. Triggers on "/prd-review", "review this PRD", "PRD'yi incele", "spec sağlam mı", "prd-run'dan önce kontrol et", "is this spec ready for the agent", "critique my PRD". Catches ambiguity, non-binary AC, missing protection list, and unsound assumptions BEFORE expensive implementation.

Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot learning, creating system prompts with personas and guardrails, building JSON/function-calling schemas, or developing prompt evaluation frameworks.

Proje için kalıcı, kategori bazlı memory dosyaları oluşturur ve günceller. İki moda sahiptir: (1) ANALYZE — kullanıcı `/context_memory` slash komutunu çağırdığında veya "projeyi analiz edip memory oluştur" dediğinde projeyi baştan tarar, frontend/backend/database/infra gibi kategorileri kendisi tespit edip `.claude/memories/` altına kategori dosyaları yazar. (2) UPDATE — PreCompact hook auto-compact başlatmadan önce tetiklendiğinde, o oturumda öğrenilen bilgileri ilgili kategori dosyalarına işler VE bir oturum özeti yazar. Manuel tetikleyiciler: "memory oluştur", "/context_memory", "projeyi analiz et", "oturum özetini kaydet", "bağlamı koru". Compact bağlam kaybını önler ve proje bilgisi birikir.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Use when asked to find bugs, review code for issues, audit a project for problems, or identify risks in an existing codebase. Triggers on "code review", "audit this project", "find bugs", "review this code", "any problems here", "bug ara", "hata bul", "issue bul", "mantık hatası", "uygulamamı analiz et", "neler yanlış", "risk var mı". Read-only — never modifies code, never generates patches.

Yeni proje bootstrap prosedürünü çalıştırır. Klasör yapısı (tasks/, docs/), CLAUDE.md, .gitignore, güvenlik denetim altyapısı (security-audit slash command, pre-PR hook, settings.json hook kaydı) ve pre-commit secret heuristic hook'unu otomatik oluşturur. DRY_RUN=true ile güvenli önizleme, FORCE_UPDATE=true ile mevcut dosyaları güncelleme destekler. Tetikleyiciler: /kickoff, "yeni proje başlat", "proje yapısını kur", "bootstrap project".

Design end-to-end production-ready architecture for a new solo developer project. Use when the user starts a new project or plans significant architectural changes. Triggers on "new project", "start a project", "plan the architecture", "what stack", "production ready tasarla", "yeni proje başlatıyorum", "mimariyi konuşalım", "stack seçimi". Solo developer context — default to end-to-end design, NOT MVP. Research current best practices per project (training data may be stale). Output: ADRs, stack selection, scaffold plan with install.sh/update.sh, and task list under /tasks/scaffold/.

Audit an existing solo-developer project for production-readiness gaps without making any modifications. Use when the user asks to review, audit, or analyze an existing codebase for architectural, security, observability, or operational gaps. Triggers on phrases like "audit my project", "is my project production ready", "check for missing stuff", "review codebase", "find gaps", "projemi kontrol et", "eksikleri bul", "production ready mi", "mimari eksikler". This skill is READ-ONLY for application code — it NEVER modifies, refactors, or makes changes to the project being audited. It ONLY creates task documents under /tasks/missing-architectures/ for later manual execution.

Use when reviewing a GitHub pull request in a project that follows the spec-first-feature convention (PRD + AC + bucket-based dispatch). Performs convention-aware PRD alignment, discipline rule checks (L107 binary AC, L108 citation cross-check, L109 migration+ORM same-PR, L081 ≤8 deliverable/bucket, L114 PRD §6 schema categorization), and offers an opt-in fix mode that applies mechanical fixes with per-fix user approval (never auto-commits or pushes).