「evaluation」の検索結果

Entry point for rafter. Invoke when a sub-skill is unclear, or when the task needs `rafter run` (remote SAST+SCA), `rafter secrets` (local secrets-only), `rafter audit`, policy checks, or command-risk evaluation. Scope by security surface, not task label: engage when the diff touches auth, credentials/secrets/tokens, untrusted input, SQL, shell/exec, file paths, deserialization, crypto, network endpoints, data deletion, or dependencies; for research/experimental/local-only code with none of that, a quick surface check is enough. When such surface IS present and no rafter skill or CLI call has been made, invoke this before handing the task off — an un-evaluated "done" on genuine security surface is not done.

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 this skill when evaluating VCSDD grading dimensions during adversarial review. Provides concrete evaluation checklists for each of the 5 dimensions and convergence signal detection.

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 validating, benchmarking, or monitoring LLM application performance. Keywords: RAG evaluation, LLM-as-a-judge, CI/CD gating, trajectory scoring, test suites, prompt 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。

Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system 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。

Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development.

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。

Expert prompt engineer specializing in designing, optimizing, and managing prompts for large language models. Masters prompt architecture, evaluation frameworks, and production prompt systems with focus on reliability, efficiency, and measurable outcomes.

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。

Design effective reasoning processes for AI agents and optimize decision-making strategies. Use when designing agent prompts, improving decision quality, implementing specialized reasoning modes, creating reasoning traces, or debugging agent mistakes. Covers prompting, chain-of-thought, reasoning depth, and decision 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。

Improve an existing skill or repository through isolated proposals, reproducible evaluation and evidence-based acceptance. Use for self-evolve or skill improvement.

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。

Analyze historical VS Code GitHub Copilot Chat sessions by model, reasoning effort, AIU, time, reliability, workflow behavior, and external quality evidence, or safely prune workspace-scoped local chat history by age. Use for session analysis, repeated-task retrospectives, model evaluation, cost/performance analysis, and old session 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。

"Apply the TPACK framework to evaluate and design technology-integrated instruction at the intersection of technological, pedagogical, and content knowledge. Use this skill when the user needs to assess teacher readiness for technology integration, design professional development for ed-tech, or evaluate whether technology use is pedagogically grounded — even if they say 'how to integrate technology in teaching', 'ed-tech evaluation', or 'teacher technology competency'.".

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。

"M&A integration playbook covering eight modules: strategic rationale, target screening, due diligence (financial/legal/commercial), valuation with valuation bridge, synergy analysis, deal structuring (stock vs. asset, cash vs. equity, earn-out), SPA key clauses, and post-merger integration (PMI). Use for deal evaluation, valuation disputes, structure design, earn-out design, synergy breakdown, integration risk, or hostile takeover defense. Triggers: 『併購』『收購』『M&A』『盡職調查』『DD』『估值橋』『綜效』『earn-out』『換股比例』『PMI』『買殼』『借殼上市』『敵意併購』『交易結構』. For Taiwan EMBA 財管組 case studies and term reports (台大／政大／陽交). Complements Asgard `biz-dcf` and `fin-modeling` (valuation tools) plus `biz-corporate-governance` (governance layer) by providing the transaction-layer framework.".

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。

"Corporate innovation-governance toolkit integrating Stage-Gate process, 3 Horizons model, innovation portfolio management, open innovation, corporate venture capital (CVC), innovation KPIs, and intrapreneurship. Use for innovation-portfolio design, second-curve planning, innovation-project review gating, open-innovation evaluation, CVC setup, innovation-KPI design, or managing tension between core and new businesses. Triggers: 『第二曲線』『創新專案怎麼管』『新事業孵化』『收購投資新創』『Stage-Gate』『研發投資組合』『內部創業』『開放式創新』『CVC』『3 Horizons』『創新 KPI』. For Taiwan EMBA innovation-management/strategy/technology-management cases (台大／中山). Startup basics: use Asgard `ux-lean-startup`; innovation theory: use Asgard `grad-disruptive-innovation`, `grad-ambidexterity`; 家族二代接班治理: use `biz-corporate-governance` 或 `ops-talent-strategy`; ESG/淨零策略結合: use `biz-net-zero-transition`.".

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。

"Management accounting toolkit for internal decision support: ABC costing, variance analysis, transfer pricing, and responsibility accounting. Use for product profitability disputes, budget variance diagnosis, inter-division pricing design, and business-unit manager performance evaluation. Triggers: 『這個產品真的賺錢嗎』『成本分攤』『事業部之間怎麼算錢』『本月成本超支』『評核廠長績效』『內部轉撥』『ABC 作業成本』『差異分析』『責任中心』『管理會計』. For Taiwan EMBA cases, term reports, and management-decision simulations (台大／陽交／成大 財管必修).".

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。

"Enterprise risk management (ERM) framework layer — integrates COSO ERM 2017 (five components, 20 principles), ISO 31000, three-lines model, risk appetite, risk heatmap, and key risk indicators (KRI) into a complete governance playbook covering structure through culture. Use for ERM implementation, risk-system build, risk mapping, risk-appetite statement drafting, three-lines setup, CRO role design, or Taiwan FSC corporate-governance evaluation response. Triggers: 『ERM 導入』『風險管理框架』『COSO』『風險地圖』『風險胃納』『KRI』『CRO 職責』『三道防線』『風險委員會』『ISO 31000』『風險熱圖』『風險治理』. For 師大／政大／陽交 EMBA risk-management/governance/audit cases. Complements Asgard `algo-risk-*` (Altman Z, Benford, credit, VaR) with the framework/governance layer. 獨董挑選/董事會組成/IPO 治理: use `biz-corporate-governance`.".

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 LLM agents and tool-using workflows—task success, tool accuracy, latency/cost, safety, and regression suites. Use when shipping agent features, comparing prompts/models, or debugging agent failures.

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 exploring, continuing, or accepting a deep-learning or computer-science research idea. Converts claims into pilot-first experiment matrices covering diagnostics, failure analysis, authorized execution, evaluation, and paper-story viability.

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 tier suppliers using a weighted scorecard per SCOR DS Supplier Management practices. Score Quality, Delivery, Cost, Responsiveness, and Sustainability. Classify suppliers as Strategic, Preferred, Approved, or Conditional. Use during vendor reviews or procurement decisions.

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 structured vendor/tool evaluation matrices with weighted scoring, TCO analysis, and recommendation memos. Covers criteria definition, deal-breaker identification, and negotiation points. Use when selecting SaaS tools, evaluating technology vendors, or making build-vs-buy decisions.

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 organizational training needs using ADDIE methodology and Kirkpatrick's 4-Level evaluation framework. Maps performance gaps to learning objectives using Bloom's taxonomy. Use when planning L&D budgets, designing training programs, or evaluating training effectiveness.

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。

Write structured Requests for Proposal (RFP) or Requests for Quotation (RFQ) aligned with ISO 20400 sustainable procurement principles. Cover scope, technical requirements, evaluation methodology, and commercial terms. Use when sourcing vendors, services, or equipment.

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 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。