Каталог навыков агентов

Build a throwaway single-file HTML demo that answers one question about a state model, logic, or data shape. Use when so...

Run one human-evaluated prototype of an uncertain product or technical claim through a verdict. Use when the finder-phas...

Define what to build at what fidelity to learn what you need without over-investing. Use before starting any prototype.

Detects JavaScript deep-merges or property assignment from user input that can pollute Object.prototype. Use when writin...

A closed-loop system for evolving UI designs using AI personas as users.

Prototype review, 原型评审, 交互原型审查。Use when: prototype-designer 完成后、进入 API Contract/HLD 之前需要审查原型的上游对齐、视觉品质、真实交互、工程隔离和下游可用性。

Create a prototype spec with structured process, quality checks, and system integration

Plan prototyping approach - fidelity levels, tool selection, prototype types, testing strategies, and design-to-developm...

9 种原型模板的结构定义和代码规范，覆盖网页、SaaS、仪表盘、移动端、PPT、文档等设计场景。 每种模板定义了标准的 HTML 结构、必需的区块、布局规则和 Anti-Slop 约束。 触发词：原型模板、页面结构、布局模板、网页结构、组件...

Convert Claude Code prototypes into structured Figma design files with component mapping, state flows, and interaction a...

Build 2-4 visual variants of a UI to decide what something should look like, viewable together for direct comparison. Us...

Build multiple genuinely different versions of a UI piece you describe, rendered behind a visual picker so you can flip...

可点击的功能性 Web 原型, 含导航、英雄区、特性区、CTA

Master prototyping with interactive mockups, user flows, animations, and high-fidelity prototypes for user testing.

CAD fundamentals, 3D printing (FDM/SLA/SLS), CNC machining, workshop skills, rapid prototyping methodology, and testing...

Prototyping and testing skill set covering prototyping strategy selection, usability test planning, heuristic evaluation...

Prove that your work is satisfactory

Prove a passing check was capable of failing before recording it as evidence. Use when a test, CI job, build-and-diff, s...

Verify that a passing test or CI check exercised its target and could detect the claimed failure.

Shows evidence that a branch meets its spec's success criteria and lists every spec change since approval. Use when a br...

Create original short videos using the 双系统碰撞｜同时证明两种规则 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the user wan...

Settle a suspected file-corruption or "the edit dropped lines" scare in this environment before editing anything — disti...

[Code Quality] Prove fix correctness with code proof traces, confidence scoring, and stack-trace-style evidence chains....

Prove that the tests for a code change would have caught the bug, by running every added or edited test with the change...

Before declaring any task complete, actually verify the outcome. Run the code. Test the fix. Check the output. Claude's...

Produce reproducible evidence for a specific claim that software or a workflow works. Use for “give me irrefutable proof...

Use after finishing a task, before saying it's done. Check the real thing, run the feature, read the actual value, inspe...

让 agent 拿证据交差，而不是只说一句「做好了」。三种时候用：agent 准备交差时；用户为同一件事第二次纠正 agent（又错了、说过多少遍、怎么让它别再犯）；要写测试、或者清理没用的测试时。prove it、stop repeati...

Adversarially verify claims that code, fixes, tests, CI, deployments, logs, or systems are correct, complete, healthy, o...

Verify that work actually shipped and actually works in production before telling the user it does. Checks uncommitted/u...

Gauntlet for absolute claims (always/never/guaranteed/optimal); pressure-test, then refine with explicit boundaries.

Assess whether observed evidence proves the requested behavior before declaring work complete. Consult for verification...

Verify against the real artifact before claiming done.

Use when a leading diagnosis or nontrivial fix has initial support and needs one adversarial counterexample before accep...

Create original short videos using the 机械同行｜启动后稳定伴行 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the user wants...

Use when a local security patch commit needs independent scoped and three-arm proof.

Guidance for proving mathematical properties in Coq using induction, specifically addition commutativity and similar ari...

Verify a claim whose evidence is an ABSENCE — blocked, denied, unreachable, isolated, not-logged, no-longer-present. Enf...

Ruthlessly audit project features for justification. Challenge every feature to prove its value with evidence or face re...

收集系统全链路操作日志，生成可追溯的执行证据链与向量索引，是多智能体系统可观测性与安全审计的底座。

Trace artifact provenance.

Use when adding or changing external data, papers, figures, copied text, generated artifacts, licenses, citations, or re...

AI generation provenance and audit trail tracking. Records decision factors, data lineage, reasoning chains, confidence...

离线审核数据资产指纹、来源定位、工具参数、代码版本和有序变换链连续性，适用于分析结果追溯、制品验收和数据血缘完整性检查。

Generate Provenance resources for audit trails with agents, activities, entities, and security labels. Model realistic E...

Use when optimizing prover performance, reducing proof generation memory usage, configuring prover infrastructure in Doc...

You are a coding standards expert specializing in provide real file links rule.

Use when setting up providers, consuming state, optimizing rebuilds, using ProxyProvider, or migrating from deprecated p...

Status: Production Ready | Category: Provider Integration | Complexity: Low

Inspect or select a Clade execution connection while keeping agent runtime, inference provider, wire protocol, and model...

Follow-up sweep for pending third-party provider access campaigns. Use when the recurring 30-minute Provider Access Laun...

Discovery batch that grows the Provider Access Launch queue. Use when asked to find more user-connected OAuth, API, API-...

Decision-ready scouting record for a user-connected provider access campaign. Use when an assigned Provider Access Launc...

End-to-end execution of a scouted third-party provider access campaign. Use when a Provider Access Launch task is ready_...

Implement Terraform Provider actions using the Plugin Framework. Use when developing imperative operations that execute...

Validate and debug Vercel AI SDK provider configurations including API keys, environment setup, model compatibility, and...

Create, update, and review Terraform provider documentation for Terraform Registry using HashiCorp-recommended patterns,...

OpenRouter framework integration templates for Vercel AI SDK, LangChain, and OpenAI SDK. Use when integrating OpenRouter...

Skill for managing model provider priorities with authentication (OAuth/Subscription/API), usage limits, and automatic f...

Claude subscription account manager for macOS (Claude Code CLI, Orca, Keychain): account discovery, usage telemetry, one...

Implement an OpenDataSuite SDK contract (ArtifactProvider, MetadataProvider, ChangeProvider, StateStore, Executor, Clone...

Implement Terraform Provider resources and data sources using the Plugin Framework. Use when developing CRUD operations,...

Use to track enrichment provider success, cost, latency, and quality trends.

Reports which delegation CLIs are installed and authenticated, installs missing ones, and stores the result. Use before...

Use this skill for a specific cloud workflow. Mention provider, trigger phrases, expected inputs, and when not to use it...

Swap the external provider/library that backs a crouton package (e.g. the map renderer, geocoder, editor engine, storage...

Terraform provider acceptance test patterns using terraform-plugin-testing with the Plugin Framework. Covers test struct...

Upgrade any Pulumi provider to a newer version and reconcile the resulting diff. Use when users want to upgrade or updat...

Provider verification workflow for contract testing

Prüfung der Verantwortlichkeit von Diensteanbietern für fremde/nutzergenerierte Inhalte: beschränkte Verantwortlichkeit...

Use when switching between LLM providers, accessing provider-specific features (Anthropic caching, OpenAI logprobs), or...

Implements feedback and notification systems including toasts, alerts, modals, progress indicators, and error states. Us...

Use this skill when showing available Kata commands, displaying the usage guide, explaining command reference, or when t...

Provide comprehensive prioritized performance optimization recommendations for frontend, backend, and infrastructure. Us...

This skill enables Claude to provide comprehensive, prioritized performance optimization recommendations for software pr...

Find what a change could break beyond the diff, then prove the one fact it is safe because of by running real code. Appl...

This skill should be used when the user asks to "provision a VPS", "create a Hetzner server", "spin up a cloud server",...

Audit required bioinformatics command-line tools against Lmod or Environment Modules on Linux HPC clusters, resolve exec...

Provision a new sap-tutorials tutorial repo pair (public source + private -Contribution), their four org teams, and the...

Automate resource provisioning across cloud providers, bare metal, and virtual machines. Use when creating, managing, or...

Grafana provisioning across all delivery methods: file provisioning YAML (datasources, dashboards, alerting), Kubernetes...

Cloud-native infrastructure knowledge reference covering Kubernetes, Helm, Kustomize, Operators, CRDs, GitOps (ArgoCD, F...

Use when building system provisioning manifests, handling multi-OS setups, managing package manager conflicts, or design...

Edward de Bono's Provocation (Po) technique — state something deliberately wrong or absurd about the problem, then extra...

Extract movement from a statement known to be false. Use when nobody can see past an obvious answer.

Generates provocative but strategically relevant concepts for websites and digital experiences before interface design b...

Analyze OpenShift installation failures in Prow CI jobs by examining installer logs, log bundles, and sosreports. Use wh...

Analyze OpenShift bare metal installation failures in Prow CI jobs using dev-scripts artifacts. Use for jobs with "metal...

Analyze Kubernetes resource lifecycle in Prow CI job artifacts by parsing audit logs and pod logs from GCS, generating i...

Analyze a failed test by inspecting the code in the current project and artifacts in Prow CI job. Provide a detailed ana...

Extract and decompress must-gather archives from Prow CI job artifacts, generating an interactive HTML file browser with...

Search indexers and manage Prowlarr. Use when the user asks to "search for a torrent", "search indexers", "find a releas...

AWS security posture assessment using Prowler. Runs compliance and security scans, filters findings through the Director...

Main entry point for Prowler development - quick reference for all components. Trigger: General Prowler development ques...

Prowler API patterns: RLS, RBAC, providers, Celery tasks. Trigger: When working in api/ on models/serializers/viewsets/f...

Manages changelog entries for Prowler components following keepachangelog.com format. Trigger: When creating PRs, adding...