Каталог навыков агентов

Comprehensive Perl security covering taint mode, input validation, safe process execution, DBI parameterized queries, we...

Comprehensive Perl security covering taint mode, input validation, safe process execution, DBI parameterized queries, we...

使用Test2::V0、Test::More、prove runner、模拟、Devel::Cover覆盖率和TDD方法的Perl测试模式。

This skill should be used when the user asks to "write Perl tests", "test Perl code", "use Test::More", "run prove", "cr...

Perl testing patterns using Test2::V0, Test::More, prove runner, mocking, coverage with Devel::Cover, and TDD methodolog...

Perl testing patterns using Test2::V0, Test::More, prove runner, mocking, coverage with Devel::Cover, and TDD methodolog...

Perl testing patterns using Test2

This skill should be used when the user asks to "validate Perl script", "check Perl syntax", "verify Perl code", "/perl-...

Design a lesson that embeds PERMA wellbeing elements alongside academic learning objectives. Use when planning lessons t...

ALWAYS use when URLs in a manuscript need permanent archived copies — 'perma these links', 'archive the URLs in my footn...

Use when designing high-lethality / permadeath / single-save combat and the systems around it — making death fair and re...

Especialista en Sistema PERMISOS SyV - validación, marcado y coherencia de alertas de información sensible

Use when changing Feishu document visibility, copy permissions, or download permissions for an uploaded document token.

Analyze OpenClaw skill permissions and explain exactly what each permission allows. Identifies over-privileged skills an...

Permission chain analyzer: extracts role definitions, role check sites, middleware mounts, and mutating routes. Identifi...

Diagnose why Claude Code is (or isn't) prompting for permission. By default reads only repo-local layers (CLI project, C...

基于蓝鲸 IAM 的前端鉴权方案，包含 v-authority 指令实现、权限组件封装及无权限交互规范。

Diagnose permission issues across settings files (read-only analysis)

Write operations for fixing and managing Claude Code permissions - add, remove, consolidate, ensure, apply-fixes.

Auto-approve whitelisted operations to reduce operator prompts. Analyzes approval cache and identifies bottlenecks.

Central authority for Claude Code permissions. Covers permission system (tiered model, read-only, bash, file modificatio...

管理Claude Code的全局工具权限配置，自动将MCP命令或其他工具添加到allowedTools中，避免每次使用时都需要手动批准。工作流程：确认用户需要添加的命令 -> 确认添加级别(默认全局~/.claude.json) -> 执行...

Manages Claude Code permissions in .claude/settings.json for repo plugin operations

Manage opencode permissions: review always-allow lists, suggest safe read-only commands, configure permission patterns

吏部权限矩阵与权限变更流程，定义各 Agent 权限等级、分配与审计规则

Guide for configuring Claude Code permissions effectively. Use when setting up security policies, configuring allow/deny...

Rules for evaluating, classifying, and deduplicating AI tool permissions

Review commands that were blocked by the permission system and decide which to allowlist. Reads the denial ledger writte...

Detects over-broad permission requests where a narrower permission or privacy-preserving alternative API is sufficient,...

Analyze permission denial patterns and generate optimized alwaysAllow and alwaysDeny rules. Use when permission prompts...

Guidelines for interacting with GitHub and request permissions from the user when commands fail due to restrictions in t...

Create child communication safety experiences using PermissionKit to request parental permission for children. Use when...

Command approvals, tool policies, and exec security

A rule under the "Law on access". Take it when creating or editing a Connect procedure, a sign-in interceptor, an admin...

Recommend safe Bash permissions for Elixir mix commands in settings.json. Use when permission prompts slow workflow, "fi...

Configures Claude Code permissions for safe agent autonomy. Creates settings.json with allow/deny rules and a path-restr...

Multi-tenant permission checking for Wasp applications. Use when implementing authorization, access control, or role-bas...

Build a least-privilege .claude/settings.json permission set from what a project actually needs: generate MCP rules with...

Three-layer permission system (Team Roles + Plans + Quotas) for this Next.js application. Covers user roles, team roles,...

Work out which permits a project actually needs and the order to get them — building/renovation, business licensing, eve...

Keeps one dated log of every approval a project has to obtain, from the agencies you name rather than from an assumed li...

Automate construction permit tracking and management. Monitor application status, track renewal deadlines, manage docume...

Permit2 approvals, signature/allowance transfers, witness signing, nonces, SDK types and wagmi integration.

Canonical Permit2 contract addresses by chain. Use when configuring multi-chain support.

Uniswap Permit2 SDK for gasless token transfers in IndexedEx. Use when implementing swap/deposit/withdraw with signature...

TypeScript type references for Permit2 SDK. Use when writing TypeScript code with Permit2.

Transform vague research requests into optimized Perplexity prompts. Automatically detects search intent (factual, expl...

Reference system prompt and tool schemas for Perplexity. Use when imitating, comparing, or analyzing Perplexity's prompt...

Paid research assistant with real-time web search. Use when user asks "what's the latest", "current pricing for", "recen...

Web search and research using Perplexity AI. Use when user says "search", "find", "look up", "ask", "research", or "what...

Search the web with AI-powered answers via Perplexity API. Returns grounded responses with citations. Supports batch que...

Agent-callable Perplexity tools — ask web-grounded questions with citations, run and poll deep research, list models, an...

Режим Deep Research через Perplexity MCP для широких и важных multi-source вопросов, когда допустимы высокий расход и бо...

困惑度过滤器。过滤以保留困惑度分数小于特定最大值的样本。 本SKILL使用依赖data_juicer，请在调用前安装好python环境并安装data_juicer，你可用以下指令进行安装： pip install py-data-juice...

Режим Search only для недорогого поиска через Perplexity с preferred MCP path и direct Search API fallback. Использовать...

Quick factual Q&A with citations. Use for simple lookups and single facts.

Deep research using Perplexity AI. Comprehensive reports with citations and analysis.

Read one or more known URLs through Perplexity Sonar Pro fetch_url_content. Use when the user wants content extracted or...

Режим Fetch URL через встроенный Perplexity Sonar Pro tool `fetch_url_content`. Использовать, когда нужно прочитать, изв...

Install and configure Perplexity SDK/CLI authentication. Use when setting up a new Perplexity integration, configuring A...

Implement Perplexity load testing, auto-scaling, and capacity planning strategies. Use when running performance tests, c...

Pro Search mode through the local Sonar Pro script. Use when the user needs a concise sourced answer, step log, or usage...

Режим Pro Search через local Sonar Pro script с `web_search_options.search_type=pro`. Использовать, когда нужен sourced...

Multi-step reasoning with Chain-of-Thought. Use for 'why' questions and comparisons.

Exhaustive multi-source research reports. Use for deep investigation.

Brain-augmented web research. Sends brain context about a topic to Perplexity, which searches the web with citations and...

Deep Research mode through Perplexity MCP. Use only for broad, important questions where higher cost and longer runtime...

End-to-end pipeline turning a research question into a peer-reviewed, citation-solid .epub brief. Fast path is the brief...

Complex research requiring deeper analysis, multi-step reasoning, and sophisticated source evaluation for technical, aca...

Highest level of research and reasoning capabilities for complex decision-making with significant consequences, strategi...

Routing guide for selecting the correct Perplexity tool. Reference before spawning any Perplexity agent.

Apply production-ready Perplexity SDK patterns for TypeScript and Python. Use when implementing Perplexity integrations,...

Perplexity Sonar search and answer generation through AIsa. Use when the task is specifically to call Perplexity Sonar,...

Raw web search results (URLs, snippets). Use when you need a list of sources, not a synthesized answer.

Strategy guide for Perplexity MCP tools (perplexity_search, perplexity_ask, perplexity_reason, perplexity_research). Hel...

Search only mode for low-cost Perplexity lookup. Use when the user needs links, sources, snippets, or quick web lookup w...

Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skil...

AI-powered web search, research, and reasoning via Perplexity

SEC EDGAR filings search. Use for official regulatory documents.

Load when the user is creating, refactoring, auditing, or fixing an Agent Skill. Provides structural audits, content ana...

Executes Perplexity AI queries via unified Python CLI. Use when conducting web research, asking questions with citations...

Analyze, plan, and execute Perplexity SDK upgrades with breaking change detection. Use when upgrading Perplexity SDK ver...

Leverage Perplexity CLI for web research, deep reasoning, and independent validation. Use when you need current/external...

Find verified free AI credits, free tiers, startup programs and student perks for LLM APIs, GPUs, voice, databases and d...

Find verified free AI credits, free tiers, startup programs and student perks for AI APIs, GPUs and dev tools, each with...

Edit a talking-head video in the PERSA style — a warm, desaturated, grain-and-bloom film grade over hard-cut one-word ca...

Use when legacy prompts or older framework flows reference `perseus` and you need the modern runtime to resolve that cap...

Write Persian that sounds human. Not formal, not robotic, not AI-generated.

Translate English language text into high quality, accurate Persian (Farsi) text

Direct and build professional motion design (promo and launch films, kinetic typography, animated explainers, social cli...

bstack P12 — Persistent Loop Discipline. Cross-context restart loop where state lives in the filesystem (PROMPT.md + git...

Write stable learnings, decisions, and patterns to durable storage like CLAUDE.md or knowledge files. Use when saving pr...

SEMO 세션 간 컨텍스트 영속화 (공통 Skill). Use when (1) 아키텍처 결정 사항 저장,(2) 팀 선호도 기록, (3) 자주 참조하는 파일 캐싱, (4) 세션 간 맥락 유지.

Persist an internal plan to docs/product/plans/. Use when exiting plan mode, when the user says "save the plan", or when...

Standards for Room Database and DataStore