41 skills · sorted by relevance
Design and test rules for activating skills through human requests, AI selection, applications, or other skills. Check eligibility before matching descriptions, then return a JSON decision showing the selected channel, score, and policy reason.
Review proposed file operations, commands, network access, secret handling, or destructive actions against explicit sandbox rules that define permitted activity. Receive a JSON verdict and the exact rule behind it without performing the proposed action.
Run a local check of test evidence and retain source paths in the result. The workflow stops when required evidence is missing, keeping the findings tied to their sources.
Evaluate an Agent Skill bundle before release by checking structure, activation conditions, output quality, scripts, safety, file integrity, and host compatibility. Receive a detailed JSON report that distinguishes local evidence checks from production readiness backed by external attestation.
Review Orchard deployment manifests, the files describing deployment settings, and keep source paths in the result. The workflow stops when evidence is missing, tying review findings to the available source material.
Build a catalog from multiple skill directories using an explicit priority order. Review duplicate names, selection decisions, and omitted entries before loading the instruction text of the chosen skill.
Test your understanding of a phase in AI Engineering from Scratch through eight multiple-choice questions. Receive a score, explanations for incorrect answers, and specific lessons to review before continuing your studies.
Review a reusable Agent Skill package before implementation. Validate its identity fields, separate instructions from external capabilities and execution timing, and receive a validation report with a minimal set of building blocks and reasons for each choice.
Study Model Context Protocol (MCP), which connects AI applications with external tools, through guided lessons and exercises. Inspect requests and responses, practice implementation and security checks, and record progress alongside observed results.
Learn to create, discover, invoke, secure, evaluate, package, and port Agent Skills through one interactive lesson at a time. Practical checkpoints and quizzes track demonstrated progress in a local file, so later sessions resume where you stopped.
Publish an approved Orchard release while retaining source paths in the result. The skill requires work to stop when supporting evidence is missing, making evidence availability a condition for proceeding.
Prepare for the MCPA certification through interactive lessons, local Python labs, diagnostic assessments, and mock exams. Track progress, revisit weak domains, and resume learning, with guided support for learners who do not write code.
Review a release proposal by reading its deployment diff and quoting changed replica settings, which describe running instance counts. The review surfaces the specific configuration changes for inspection.
基于「AI工程造价+法律知识库」（1394人订阅，3149个内容）的造价+法律交叉领域AI技能。当用户需要进行工程造价司法鉴定、合同风险审查、变更索赔分析、结算纠纷诊断时使用。触发词包括但不限于：造价+法律、工程司法鉴证、合同风控、变更索赔、结算纠纷、鉴定意见、证据链、工期索赔、费用索赔。也适用于用户需要基于知识库内容进行案件分析、模拟鉴定、风险预警的场景。
The English summary is being prepared. Showing the original description.
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
The English summary is being prepared. Showing the original description.
[Code Quality] Use when a workflow step or the user asks for AI code or plan review: LLM calls, prompts, agents, RAG, evals and guardrails. --mode={code|plan}; --report-only is read-only.
The English summary is being prepared. Showing the original description.
Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and p
The English summary is being prepared. Showing the original description.