Use when deciding whether to store a memory. Fires as a gate before every remember() call. The default answer is "no" — biological memory is selective, not exhaustive.
Score 70/100
Autonomous p5.js visualization agent. It implements, inspects, critiques design/UX, fixes, and launches the result.
Score 70/100
Agente que simula Sam Altman — CEO da OpenAI, ex-presidente da Y Combinator, arquiteto da era AGI.
Score 70/100
Advanced sample size and power calculations for complex study designs including survival analysis, clustered designs, and multiple comparisons.
Score 70/100
Git commit, branch, and PR conventions - automatically applied when writing commit messages
Score 70/100
Sandbox untrusted package managers with bubblewrap. Use when adding bun/cargo/pnpm sandboxing, configuring bwrap, or isolating dependency installs.
Score 70/100
Audit and recommend minimal sandbox entitlements for secure desktop applications
Score 70/100
Sandbox refresh cycles, sandbox templates, post-refresh automation via the SandboxPostCopy Apex interface, and data handling during refresh.
Score 70/100
Use when designing or reviewing Salesforce sandbox topology, refresh cadence, masking, and environment purpose.
Score 70/100
Use sanger chromatogram qa for data analysis workflows that need structured execution, explicit assumptions, and clear output boundaries.
Score 70/100
Compiler sanitizer skill for runtime bug detection in C/C++. Use when enabling and interpreting AddressSanitizer (ASan), UndefinedBehaviorSanitizer (UBSan), ThreadSanitizer…
Score 70/100
Business card and contact intelligence — search, manage, sync digitized cards for Japanese B2B networking
Score 70/100
中文优先：用于Santamethod相关任务，帮助识别、设计、实现或验证对应工作流。English keywords: Multi-agent adversarial verification with convergence loop.
Score 70/100
Automate SAP SuccessFactors tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Structure-Activity Relationship (SAR) analysis with RDKit: scaffold detection via MCS, R-group decomposition, aligned visualization, activity heatmaps, interpretive SAR output.
Score 70/100
Sass (indented syntax) best practices and coding guidelines for clean, maintainable stylesheets
Score 70/100
Automate Satismeter tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Clinically informed wisdom companion blending psychology and philosophy into a structured thinking partner
Score 70/100
الخدمات المصرفية المفتوحة السعودية -- إطار ساما وLean Technologies وبوابات البنوك
Score 70/100
بوابات الدفع السعودية — ربط بوابات الدفع مثل مويسر وتاب وهايبرباي وتابي وتمارا. استخدم عندما يسأل المستخدم عن قبول المدفوعات أو بوابات الدفع في السعودية.
Score 70/100
المشتريات الحكومية السعودية عبر اعتماد — Saudi government procurement, contracts, and salary certificates via Etimad
Score 70/100
الشحن والتوصيل في السعودية — تتبع شحنات وإنشاء بوالص شحن عبر شركات مثل سمسا وأرامكس وناقل. استخدم عندما يسأل المستخدم عن شحن أو تتبع طرد في السعودية.
Score 70/100
السياحة في السعودية — Saudi tourism attractions, events, visa info, and tourism APIs
Score 70/100
تحويل النص إلى كلام بالعربية السعودية — Saudi Arabic text-to-speech with NAMAA, Lahajati, and dialect support
Score 70/100
Export full conversation to markdown file in D:\claude md
Score 70/100
Save the current conversation context as a reloadable snapshot. Triggered by 'save context', 'save session', 'bookmark this', 'save progress', 'snapshot conversation', 'save my…
Score 70/100
Use when the user wants to save brand knowledge — campaign learnings, competitive intelligence, brand guidelines, or performance insights — to persistent memory (vector database)…
Score 70/100
학습 내용을 TIL 파일로 저장하고 Daily 노트, MOC, 백로그를 일괄 업데이트
Score 70/100
Save conversation or content to Notion database
Score 70/100
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.
Score 70/100
Authentication flaw detection — weak passwords, broken auth, credential stuffing, and bypass vectors
Score 70/100
Authorization flaw detection — IDOR, broken access control, horizontal and vertical privilege issues
Score 70/100
Business logic flaw detection — price manipulation, workflow bypass, race conditions, and abuse vectors
Score 70/100
OS Command Injection detection in shell execution, subprocess calls, and process spawning
Score 70/100
CORS misconfiguration detection — wildcard origin, reflected origin, null origin, and credential leaks
Score 70/100
Sensitive data exposure detection — PII leaks, verbose errors, debug mode, and information disclosure
Score 70/100
Insecure deserialization detection across all serialization formats and languages
Score 70/100
Insecure file upload detection — unrestricted types, MIME mismatch, polyglot files, and webshell upload
Score 70/100
HTTP Header Injection and Response Splitting detection via CRLF injection in headers
Score 70/100
JWT implementation flaw detection — algorithm confusion, weak secrets, missing validation, and storage issues
Score 70/100
LDAP Injection detection in search filters, DN construction, and bind operations
Score 70/100
Mass assignment and over-posting detection — unfiltered request body binding to data models
Score 70/100
Open redirect detection — unvalidated redirect URLs, protocol-relative bypasses, and URI scheme abuse
Score 70/100
Privilege escalation vector detection — role manipulation, admin bypass, and RBAC circumvention
Score 70/100
Race condition and TOCTOU detection — database races, file system races, double-spend, and atomicity failures
Score 70/100
Remote Code Execution detection via eval, exec, dynamic code loading, and code injection vectors
Score 70/100
Session management flaw detection — fixation, hijacking, cookie misconfiguration, and lifecycle issues
Score 70/100
Server-Side Request Forgery detection — URL fetching with user input, DNS rebinding, cloud metadata access
Score 70/100
XML External Entity injection detection across all XML parsers and document formats
Score 70/100
Builds AI agents using OpenAI Agents SDK with async/await patterns and multi-agent orchestration. Use when creating tutoring agents, building agent handoffs, implementing…
Score 70/100
Enforces stateless design, efficient resource usage, and patterns that handle 10x-100x growth
Score 70/100
Planification de la scalabilité d'une application ou infrastructure. Se déclenche avec "scalabilité", "scaling", "montée en charge", "millions d'utilisateurs", "haute…
Score 70/100
Scalability audit — identifies performance bottlenecks, unbounded queries, N+1 patterns, missing indexes, synchronous blocking operations on hot paths, and memory pressure points.
Score 70/100
Test at extremes (1000x bigger/smaller, instant/year-long) to expose fundamental truths hidden at normal scales
Score 70/100
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',…
Score 70/100
Guides Qdrant query volume scaling. Use when someone asks 'query returns too many results', 'scroll performance', 'large limit values', 'paginating search results', 'fetching many…
Score 70/100
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…
Score 70/100
Run a fast secure-code triage pass over C and C++ sources before manual review or remediation planning begins.
Score 70/100
Audit a Claude Code setup before use by flagging hardcoded secrets, broad allow rules, risky hooks, and dangerous MCP server config.
Score 70/100
Find packages that are out of support even when they do not show up as a classic CVE finding yet.
Score 70/100