학습 내용을 TIL 파일로 저장하고 Daily 노트, MOC, 백로그를 일괄 업데이트
Save conversation or content to Notion database
Implementación práctica de Savia Flow — dual-track, specs ejecutables, métricas de flujo
Carga completa de la identidad y personalidad de Savia. Perfil, tono, reglas, y memoria al inicio de cada sesión.
Savignys klassischer Vierer-Kanon der Auslegung (grammatikalisch, logisch-systematisch, historisch, teleologisch).
Aide à planifier un objectif d'épargne avec calcul, timeline et stratégie. À utiliser quand l'utilisateur veut épargner pour un achat, un voyage, un fonds d'urgence.
SavvyCal integration. Manage Users. Use when the user wants to interact with SavvyCal data.
Stage and commit the current session's changes only. Session-isolated (never -A), doc-sync-gated, conventional message, no push.
Scan docs/superpowers/ for active specs and plans. Show status table with cycle stage, progress, and blockers. Suggest what to tackle next.
Authentication flaw detection — weak passwords, broken auth, credential stuffing, and bypass vectors
Authorization flaw detection — IDOR, broken access control, horizontal and vertical privilege issues
Business logic flaw detection — price manipulation, workflow bypass, race conditions, and abuse vectors
OS Command Injection detection in shell execution, subprocess calls, and process spawning
CORS misconfiguration detection — wildcard origin, reflected origin, null origin, and credential leaks
Sensitive data exposure detection — PII leaks, verbose errors, debug mode, and information disclosure
Insecure deserialization detection across all serialization formats and languages
Insecure file upload detection — unrestricted types, MIME mismatch, polyglot files, and webshell upload
HTTP Header Injection and Response Splitting detection via CRLF injection in headers
JWT implementation flaw detection — algorithm confusion, weak secrets, missing validation, and storage issues
LDAP Injection detection in search filters, DN construction, and bind operations
Mass assignment and over-posting detection — unfiltered request body binding to data models
Open redirect detection — unvalidated redirect URLs, protocol-relative bypasses, and URI scheme abuse
Privilege escalation vector detection — role manipulation, admin bypass, and RBAC circumvention
Race condition and TOCTOU detection — database races, file system races, double-spend, and atomicity failures
Remote Code Execution detection via eval, exec, dynamic code loading, and code injection vectors
Session management flaw detection — fixation, hijacking, cookie misconfiguration, and lifecycle issues
Server-Side Request Forgery detection — URL fetching with user input, DNS rebinding, cloud metadata access
XML External Entity injection detection across all XML parsers and document formats
Практическое руководство по настройке сети для тестирования протокола IEC-104 между эмулятором платы (клиент) и SCADA-системой (сервер) через роутер на базе OpenWrt, включая…
Use for scaffolding, new projects, package setup, quality tooling, CI, and repo structure.
Builds AI agents using OpenAI Agents SDK with async/await patterns and multi-agent orchestration. Use when creating tutoring agents, building agent handoffs, implementing…
Idiomatic Scala patterns: ADTs with sealed traits and case classes, typeclass pattern, Option/Either/Try error handling, for-comprehensions, Cats Effect (IO, Resource, Ref,…
Enforces stateless design, efficient resource usage, and patterns that handle 10x-100x growth
Guidance for scaling systems from startup to enterprise scale. Use when planning for growth, diagnosing bottlenecks, or designing systems that need to handle 10x-1000x current…
Analyze system scalability with capacity math, bottleneck identification, scale-out triggers, cost projections, and migration decision points. Outputs .forge/scalability.md.
Planification de la scalabilité d'une application ou infrastructure. Se déclenche avec "scalabilité", "scaling", "montée en charge", "millions d'utilisateurs", "haute dis — from…
ScalarDBの制約を考慮したデータモデル設計を行います。Partition Key・Clustering Key・Secondary Index の設計、ホットスポット評価、メタデータオーバーヘッド見積もり、バックエンドDB選定を含みます。ワークフローStep 04（データモデル設計）で使用します。
Scale AI integration. Manage Organizations, Users, Goals. Use when the user wants to interact with Scale AI data.
Nutze diesen Skill für Phaser Scale Manager, responsive Layouts, FIT, RESIZE, EXPAND, Parent-Grössen und Resize-Events.
Scalability audit — identifies performance bottlenecks, unbounded queries, N+1 patterns, missing indexes, synchronous blocking operations on hot paths, and memory pressure points.
Test at extremes (1000x bigger/smaller, instant/year-long) to expose fundamental truths hidden at normal scales
Scaled Access integration. Manage data, records, and automate workflows. Use when the user wants to interact with Scaled Access data.
Scaleway integration. Manage data, records, and automate workflows. Use when the user wants to interact with Scaleway data.
Review and optimize Scaleway cost posture across Instance type rightsizing, reserved instance utilization, idle Object Storage buckets and SBS block volumes, Serverless function…
Review Scaleway IAM policies, API key governance, service account bindings, and organization/project-level permission sets for least-privilege posture.
Guides Qdrant query throughput (QPS) scaling. Use when someone asks 'how to increase QPS', 'need more throughput', 'queries per second too low', 'batch search', 'read replicas',…
Guides Qdrant query volume scaling. Use when someone asks 'query returns too many results', 'scroll performance', 'large limit values', 'paginating search results', 'fetching many…
Integrate Scallop money market on Sui. Use when the user mentions Scallop or wants to lend or borrow on Sui via Scallop.
Scalr integration. Manage Organizations, Users, Goals. Use when the user wants to interact with Scalr data.
Сканирует все 5 измерений арбитража — ценовой, временной, информационный, структурный, каузальный.
Systematically identify and map internal and external blockers preventing CX improvement. Use when starting a CX transformation project, when a user describes why a CX program…
Run a fast secure-code triage pass over C and C++ sources before manual review or remediation planning begins.
Audit a Claude Code setup before use by flagging hardcoded secrets, broad allow rules, risky hooks, and dangerous MCP server config.
Perform a fresh-context scan of code and docs that turns verification observations and missing-test gaps into findings.
Scan up to 10 Discord channels for alerts, notifications, and error messages from bots within a configurable investigation window.
סורק משרות הוראה — igm (ארגון המורים) + itu (הסתדרות המורים) + שתיל. כותב ל-data/jobs-pending.json ב-Edura (סטייג'ינג, לא חי).
Analyze gaps in user-facing features and desirable characteristics, developer-facing tooling and desirable characteristics, and other opportunities not currently tracked — from…
Audit the user's Claude Code agent harness for improvements — global config, project config, recent session patterns, and opportunities for better guardrails and feedback loops.
Find packages that are out of support even when they do not show up as a classic CVE finding yet.
Run CodeShield on model-produced code or command suggestions before they reach a user, a repo, or an execution step, so insecure patterns get blocked or warned on first.