3,343 件 ・ 関連度順
概要と使いどころ
Use this agent when you need to review UniProt annotation rules (ARBA, UniRule) for quality, biological accuracy, and GO annotation appropriateness. This agent performs comprehensive analysis of rule condition sets, evaluates literature support, assesses taxonomic scope, and recommends curation actions.
日本語の概要は準備中です。原文の説明を表示しています。
Evaluate and review GO-CAM (Gene Ontology Causal Activity Model) activities / annotons — molecular-function typing, has-input, causal relations, complexes, evidence — and check their consistency with gene annotation reviews. Use when reviewing cached GO-CAMs under gocams/, filling a GoCamReview YAML (gocams/<id>/<id>-review.yaml), or grounding a module in GO-CAM models.
日本語の概要は準備中です。原文の説明を表示しています。
Operate a logged-in Miaoshou ERP workflow for TikTok Shop Malaysia product discovery, product screening, profit estimation, listing preparation, and reviewed publishing. Use when the user asks to search or select products in 妙手 ERP, evaluate low-price traffic products, prepare Malaysian TikTok Shop listings, move products into the TikTok collection box, or publish approved listings. Prefer browser operation through the user's existing login; never store credentials or call undocumented private endpoints.
日本語の概要は準備中です。原文の説明を表示しています。
Use when building RAG or LLM applications with LlamaIndex - data loaders, node parsing, vector stores, retrievers and rerankers, query engines, agents and workflows, streaming, or evaluation
日本語の概要は準備中です。原文の説明を表示しています。
Fierce autonomous internal co-founder. Bounded web research for evidence-backed improvements. Structured idea formulation with self-critique filter that rejects ideas not serving the goal. Auto-implements high-confidence aligned improvements, proposes medium-confidence ideas for approval. Evaluates viral coefficient, AI search visibility (GEO), and solo SaaS economics. Considers higher pursuits: employing disabled people, spiritual tech investigation, 99% wealth donation ethos.
日本語の概要は準備中です。原文の説明を表示しています。
Use when writing, reviewing, or changing build scripts, CI workflows, deploy pipelines, repo setup, or evaluating a new tool/dependency
日本語の概要は準備中です。原文の説明を表示しています。
Use when considering, evaluating, or performing a refactor, restructure, cross-file rename, or cleanup
日本語の概要は準備中です。原文の説明を表示しています。
LLM observability with Langfuse — OpenTelemetry-based tracing, evaluations, prompt management, datasets, and production best practices
日本語の概要は準備中です。原文の説明を表示しています。
General workflow for auditing ML CI failures, experiment regressions, training run failures, golden metric failures, and telemetry-backed ML work-product claims from local repositories, logs, metrics, configs, and artifacts. Use when Codex needs to decide whether an ML failure is a model/convergence issue, correctness bug, data/config issue, infrastructure/runtime issue, evaluation/gating policy issue, or unsupported claim, and produce structured evidence-backed outputs.
日本語の概要は準備中です。原文の説明を表示しています。
Identify and exploit Server-Side Template Injection (SSTI) vulnerabilities within web applications. Use this skill when testing web applications that render dynamic content using template engines like Jinja2 (Python), Twig (PHP), Freemarker (Java), or Pug (Node.js). Covers identification via mathematical evaluation, context mapping, escaping sandboxes, and achieving Remote Code Execution (RCE).
日本語の概要は準備中です。原文の説明を表示しています。
Sandbox escape playbook. Use when breaking out of Python sandbox, Lua sandbox, seccomp filter, chroot jail, container/Docker, browser sandbox, or namespace isolation to achieve unrestricted code execution or file access.
日本語の概要は準備中です。原文の説明を表示しています。
Server-Side Template Injection (SSTI) occurs when user input is embedded directly into a template engine (Jinja2, Twig, Freemarker, Pebble, Velocity, Smarty, Mako) and evaluated, enabling remote code execution. Detect via math expressions `{{7*7}}` returning `49`, or `${7*7}`, `<%= 7*7 %>`. Leads to full RCE via template sandbox escape, Python `__class__.__mro__` traversal, and Java reflection chains. Tools: tplmap, Burp Suite.
日本語の概要は準備中です。原文の説明を表示しています。
SSTI playbook. Use when template expressions, server-side rendering, preview features, or templating engines may evaluate attacker-controlled content.
日本語の概要は準備中です。原文の説明を表示しています。
Detects authentication and biometric bypass vulnerabilities in mobile apps (Android/iOS). Trigger on: BiometricPrompt, LocalAuthentication, LAContext, evaluatePolicy, CryptoObject, Android Keystore, Secure Enclave, kSecAccessControlBiometryCurrentSet, userAuthenticationValidityDurationSeconds, confirmCredentials, biometric fallback, PIN bypass, passive authentication, enrolled biometrics detection, Frida hook auth, jailbreak bypass, TouchID, FaceID, fingerprint. Covers MASVS-AUTH-1/2/3.
日本語の概要は準備中です。原文の説明を表示しています。
Systematically bypass LLM safety filters and content moderation systems using advanced jailbreaking techniques. Use this skill when testing AI systems for safety alignment robustness, evaluating content moderation effectiveness, or conducting authorized AI red team assessments. Covers role-play attacks, few-shot manipulation, encoding bypass, multi-modal exploitation, and automated jailbreak discovery methods.
日本語の概要は準備中です。原文の説明を表示しています。
Simulate supply chain and adversarial machine learning attacks by injecting poisoned data or targeted backdoors into training and fine-tuning datasets. Use this skill when assessing the integrity controls of MLOps pipelines or evaluating the resilience of AI models against highly targeted, stealthy manipulation intended to alter model behavior on specific triggers.
日本語の概要は準備中です。原文の説明を表示しています。
Expression Language injection playbook. Use when Java EL, SpEL, OGNL, or MVEL expressions may evaluate attacker-controlled input in Spring, Struts2, Confluence, or similar frameworks.
日本語の概要は準備中です。原文の説明を表示しています。
AI/LLM red-team assessment using the OWASP LLM Top 10 (2025) + OWASP AI Testing Guide (AITG v1, Nov 2025) frameworks, plus OWASP MCP Top 10 runtime testing for agentic/MCP targets. Tests prompt injection, jailbreaks, system prompt leakage, sensitive data extraction, excessive agency, improper output handling, model extraction, content bias, evasion, membership inference, MCP token exposure, MCP command injection, and more. Uses four tools in combination: FuzzyAI (single-turn jailbreak fuzzing), PyRIT (multi-turn orchestrated attacks), Garak (probe-based vulnerability scanning), and promptfoo (plugin-based red-team evaluation). Each tool covers different OWASP categories; running them together gives systematic coverage. Includes a conditional MCP reconnaissance phase and a post-access AI infrastructure phase (chained from /post-exploit). Produces: OWASP LLM Top 10 + AITG + MCP coverage matrix, findings per category, architecture diagram of the AI system, PoCs for confirmed exploits. Chains into /gh-export for issue filing.
日本語の概要は準備中です。原文の説明を表示しています。
Build evaluation frameworks for LLM systems — harness design, graders, datasets, regression tracking, and human-in-the-loop eval. Use when you need systematic measurement of model or agent quality.
日本語の概要は準備中です。原文の説明を表示しています。
Work with text embeddings — choosing models, pooling, similarity measures, evaluation, and multilingual considerations. Use when building semantic search, clustering, or any similarity-based feature.
日本語の概要は準備中です。原文の説明を表示しています。
Uncensored open-model inference on Featherless AI — raw model behavior for research and evaluation.
日本語の概要は準備中です。原文の説明を表示しています。
Fine-tune large language models — data curation, SFT, parameter-efficient methods (LoRA), evaluation, and avoiding common training failures. Use when a base model needs task-specific behavior or domain knowledge.
日本語の概要は準備中です。原文の説明を表示しています。
Build discernment habits: nudges and checklists for evaluating claims, spotting manipulation, and thinking clearly under pressure. Use when you want better judgment about what to believe and share.
日本語の概要は準備中です。原文の説明を表示しています。
Evaluating diagnostic tests — sensitivity, specificity, ROC analysis, likelihood ratios, and study design.
日本語の概要は準備中です。原文の説明を表示しています。