1,278 件 ・ 関連度順
概要と使いどころ
AI and LLM red-teaming skill for evaluating prompt injection, jailbreak, data exfiltration, tool abuse, agent hijack, RAG poisoning, model denial of service, and unsafe tool-use chains in Gemini, Claude, GPT, and open-weight models. Use to build evaluation harnesses, attack corpora, defensive guardrails, and red-team reports for AI systems you own or are authorized to test.
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。
Prompt engineering and task-specification skill for improving prompts, agent instructions, system messages, evaluation prompts, coding-agent tasks, multi-step workflows, and LLM output reliability. Use when rewriting vague prompts, adding constraints, reducing ambiguity, improving safety, creating reusable prompt templates, or converting goals into actionable agent instructions.
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。
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。
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。
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。
Creates controlled synthetic slop for demos and evaluation fixtures.
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。
Generate controlled synthetic slop for demos and evaluation fixtures.
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。
Set up LLM-as-judge evaluation for ORC workflows
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。
Sales enablement, technical presales and deal acceleration for B2B SaaS revenue teams. Use this skill when planning outbound campaigns, running discovery calls, building deal strategy, creating battle cards, writing proposals, responding to RFPs, preparing a product demo, scoping a proof of concept or pilot, answering a security questionnaire or the AI annex buyers now attach to it, executing sales sequences, coaching qualification, or deciding what the website's AI chat agent is allowed to say. Also triggers on: outbound, cold outreach, reply handling, reply classification, out-of-office replies, auto-replies counted as replies, our reply rate is inflated, prospect replied remove me, opt-out by reply, is this list ready to send, launch readiness, CRM segment outbound, we emailed a current customer, outbound hit an open opportunity, ownerless leads, prospects engaging our competitors, competitor connections, displacement list, is this personalization creepy, can we mention they visited our site, signal freshness, deal strategy, pipeline, battle card, objection handling, common objections, why do we keep hearing this objection, mine call transcripts for objections, objection register, proposal, RFP, discovery call, MEDDPICC, sales sequence, qualification, sales engineer, solutions engineer, presales, demo plan, demo script, POC, proof of concept, pilot success criteria, technical evaluation, technical win, security questionnaire, vendor security review, SOC 2 questionnaire, AI security questionnaire, AI annex, AI vendor due diligence, the buyer is asking if we train on their data, do you train on customer data, which model do you use, model provider sub-processor, AI subprocessor disclosure, where does inference run, can the customer turn the AI feature off, AI-CAIQ, CSA AI Controls Matrix, ISO 42001, ISO/IEC 42001, NIST AI RMF, EU AI Act Article 50, are we a provider or a deployer, AI feature disclosure, our model vendor changed and nobody told the buyer, technical objection, mutual action plan, MAP, close plan, mutual close plan, buyer enablement, the deal is stalled, deal stalled after the demo, how do I get this deal to close, close date keeps slipping, JOLT, buyer indecision, no-decision loss, website chatbot, chat widget, AI chat agent, AI SDR, inbound AI SDR, conversational marketing, live chat, what should our chatbot be allowed to say, our chatbot quoted the wrong price, the bot promised a discount, do we have to disclose it is AI, EU AI Act chatbot disclosure, chatbot handoff to sales, chat transcript review, prompt injection on our chatbot, Drift, Qualified, Intercom.
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。
Public relations, corporate communications, and analyst relations for B2B SaaS. Use this skill for earned media and press strategy, announcements and press releases, executive and crisis communications, media relationships and briefings, and the Gartner/Forrester/IDC analyst program including Magic Quadrant and Wave evaluation submissions. Also triggers on: PR, public relations, press release, earned media, media relations, journalist, embargo, announcement, crisis comms, corporate communications, analyst relations, AR, Gartner, Forrester, IDC, Magic Quadrant, Forrester Wave, analyst briefing, inquiry, newsjacking, rapid response, should we comment on this news story, expert commentary, reactive comment, source request, Qwoted, is this newsworthy.
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 a task needs the judgment of an Engineering Teacher, Postsecondary — diagnosing a spike in a gatekeeper course's D/F/W rate, running a capstone design course with an industry sponsor, closing the loop on an ABET student-outcome assessment, or building a tenure/promotion teaching-effectiveness case beyond raw student evaluation scores.
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 a task needs the judgment of an Environmental Restoration Planner — screening or comparing CERCLA/RCRA remedial alternatives against the nine evaluation criteria, building a life-cycle cost estimate for a Feasibility Study, scoping a stream or wetland restoration design against a reference reach, sizing compensatory mitigation credits, drafting a Statement of Work or Remedial Action Work Plan, or scoping a Five-Year Review for a site with land-use controls in place.
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 a task needs the judgment of a licensed Customs Broker — classifying goods under the Harmonized Tariff Schedule (HTS), calculating landed duty and fees on an import entry, determining country of origin and free-trade-agreement eligibility, filing an Importer Security Filing (ISF) or entry summary, or deciding whether a classification or valuation position is defensible under CBP's "reasonable care" standard.
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 a task needs the judgment of a cytotechnologist — screening a gynecologic (Pap test) slide and applying Bethesda System criteria, assessing non-gynecologic specimen adequacy (FNA rapid on-site evaluation, body fluid, brushing) against the relevant reporting system, deciding whether a finding can be signed out independently or must be referred to a pathologist, or auditing screening quality metrics (ASC:SIL ratio, rescreen concordance, workload compliance). A reasoning aid, not a substitute for a certified cytotechnologist or pathologist signing out an actual case.
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 a task needs the judgment of a Compensation, Benefits, and Job Analysis Specialist — market-pricing a job against salary survey data, scoring a job through a point-factor or IPE job evaluation, running a pay-equity regression or cohort analysis, building or refreshing a salary structure and compa-ratio bands, classifying a job family's FLSA exemption status through the duties test, or modeling benefits plan cost (loss ratio, PEPM, self-funded vs. fully insured). Distinct from hr-people-manager (owns the comp/leveling judgment calls — whether to approve an exception, promote someone into a level), hr-specialist (owns individual-case leave/I-9/ADA/FLSA reclassification for one employee's drifted duties), and compensation-benefits-manager (owns pay philosophy, negotiation-range policy, and the department that runs this work). This role owns the mechanics: the survey match, the point score, the regression, the band math — the analysis those upstream policy and downstream judgment calls are made against.
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 a task needs the judgment of an Administrative Law Judge, Adjudicator, or Hearing Officer — applying a mandatory sequential/structured evaluation framework in required order, weighing conflicting medical or vocational opinion evidence using specific regulatory factors, writing findings that explicitly address significant contrary evidence in the record, drafting a credibility/consistency finding tied to specific record citations, or checking whether a draft decision would survive substantial-evidence review.
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。
Assess the scientific integrity and trustworthiness of publications before relying on their findings. Use this skill whenever evaluating a paper for a workflow, citing a study, building an analysis on published methods, or when a user asks about the reliability of a study. Checks for formal retractions, corrections, expressions of concern, and — critically — informal contradictions where subsequent studies failed to reproduce key findings. Integrates with PubMed, bioRxiv, and Consensus to provide a trust assessment. Use this skill for ANY publication evaluation, retraction checking, author reliability assessment, or when a user says "can I trust this paper", "is this study reliable", "has this been refuted", or "check this publication".
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。
Test coverage quality analysis — behavioral coverage, critical gap identification, test resilience 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。
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。
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。
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。