AI Skills Hub - Browse 180,000+ Agent Skills

使用 Python CLI 与 Dida365 Open API 交互以管理滴答清单任务/项目，适用于需要通过脚本或命令行调用滴答清单接口的场景（如项目/任务的查询、创建、更新、完成、删除）。

查看/更新 GitHub Issue、PR（含评论与 diff），并按团队规范非交互创建或修改 PR；涉及 GitHub Issue/PR 的操作时使用。

This skill provides screenplay export procedures for PDF, FDX, and HTML. Covers Better Fountain VS Code extension, afterwriting CLI, and Highland for converting Fountain files to industry-standard delivery formats.

FFI 跨语言互操作专家。处理 C/C++ 互操作、bindgen、PyO3、Java JNI、内存布局、数据转换等问题。触发词：FFI, C, C++, bindgen, cbindgen, PyO3, jni, extern, libc, CString, CStr, 跨语言, 互操作, 绑定

可变性专家。处理 E0596, E0499, E0502, interior mutability, Cell, RefCell, Mutex, RwLock, borrow conflict, 可变性, 内部可变性, 借用冲突

Build MCP (Model Context Protocol) clients to connect AI agents with external tools and data sources. Use when building integrations with MCP servers.

错误处理专家。处理 Result, Option, panic, anyhow, thiserror, 自定义错误, 错误传播等问题。触发词：Result, Error, panic, ?, unwrap, expect, anyhow, thiserror, error handling, 错误处理, 错误类型

高级异步模式专家。处理 Stream 实现, 零拷贝, tokio::spawn 生命周期, 插件系统调度, tonic 流式响应等问题。触发词：async, Stream, tokio::spawn, 零拷贝, 插件系统, tonic, 流式, BorrowedMessage, 异步调度

Custom exceptions with static factories and HTTP responses. Use when working with error handling, custom exceptions, or when user mentions exceptions, custom exception, error handling, HTTP exceptions.

Form request validation and comprehensive validation testing. Use when working with validation rules, form requests, validation testing, or when user mentions validation, form requests, validation rules, conditional validation, validation testing.

Background jobs and event listeners for async processing. Use when working with queued jobs, background processing, events, or when user mentions jobs, queues, listeners, events, async processing.

State machines using Spatie Model States for complex state transitions. Use when working with complex state management, state transitions, or when user mentions state machines, Spatie Model States, state transitions, transition validation.

Create comprehensive how-to guides and tutorials. Use when the user needs step-by-step instructional content, tutorials, documentation, or educational guides.

Publish a new version of klaude-code to PyPI. This skill handles version bumping, changelog updates, git tagging, and package publishing. Use when the user wants to release a new version.

Dependency health analysis to detect outdated packages and unused dependencies.

Execute CodeQL security scans with language detection, database caching, and SARIF output. Use when performing static security analysis on Python or GitHub Actions code.

PR review coordinator who gathers comment context, acknowledges every

BLOCKING INTERCEPT: When ANY github.com URL appears in user input, STOP and use this skill. Never fetch GitHub HTML pages directly - they are 5-10MB and will exhaust your context window. This skill routes URLs to efficient API calls (1-50KB). Triggers on: pull/, issues/, blob/, tree/, commit/, compare/, discussions/.

Multi-agent debate orchestration for Architecture Decision Records. Automatically triggers on ADR create/edit/delete. Coordinates architect, critic, independent-thinker, security, analyst, and high-level-advisor agents in structured debate rounds until consensus.

Detect infrastructure and security-critical file changes to trigger security agent review recommendations ensuring proper security oversight for sensitive modifications.

Check investigation session QA skip eligibility per ADR-034. Validates if staged files qualify for investigation-only exemption by checking against allowed paths (.agents/sessions/, .agents/analysis/, .serena/memories/, etc).

Deterministic SVG generation, validation, and rendering. Use for icons, diagrams, charts, UI mockups, or technical drawings requiring structural correctness and cross-viewer compatibility.

Generate audio tones, noise, DTMF signals, and simple sound effects programmatically. Export to WAV or MP3 format.

Validate JSON data against JSON Schema specifications. Use for API validation, config file validation, or data quality checks.

Convert audio files between formats (MP3, WAV, FLAC, OGG, M4A) with bitrate and sample rate control. Batch processing supported.

Copy text to the system clipboard. Use when user asks to copy something, send to clipboard, or similar requests.

Orchestrate multi-simulation campaigns including parameter sweeps, batch jobs, and result aggregation. Use for running parameter studies, managing simulation batches, tracking job status, combining results from multiple runs, or automating simulation workflows.

Validate simulations before, during, and after execution. Use for pre-flight checks, runtime monitoring, post-run validation, diagnosing failed simulations, checking convergence, detecting NaN/Inf, or verifying mass/energy conservation.

Helps you work with Palantir Foundry using the pltr CLI. Use this when you need to query datasets, manage orchestration builds, work with ontologies, run SQL queries, manage folders/spaces/projects, copy datasets, or perform admin operations in Foundry. Triggers: Foundry, pltr, dataset, SQL query, ontology, build, schedule, RID.

Populate domain specs (glossary, entity definitions, use-cases) from discovery results.

Templates and validation for writing product specifications.

Templates and guidelines for epic-level planning with multiple feature changes.

Scaffolds PostgreSQL database component with migrations, seeds, and management scripts.

WHEN writing team updates, progress reports, or stakeholder comms; delivers scannable structure, honest framing, and warm recognition.

WHEN working in TDD Red-Green-Refactor; NOT ad-hoc coding; write tests first, add minimal code to green, then assess refactoring.

WHEN building React components/pages/apps; enforces scalable architecture, state management, API layer, performance patterns.

Expert knowledge for developing, building, and debugging Substreams projects on any blockchain. Use when working with substreams.yaml manifests, Rust modules, protobuf schemas, or blockchain data processing.

Expert knowledge for testing Substreams applications. Covers unit testing, integration testing, performance testing, and FireCode tools usage.

Verify blockchain transactions before announcing success. Use to avoid premature celebration and trust issues. Learned from getting a basename sniped.

Register Basenames (.base.eth) for AI agents. Use when an agent needs to register a human-readable ENS-style name on Base for their wallet address. Supports checking availability, pricing, registration, and setting primary name.

Security guardrails, self-audit tools, and secret scanning for AI agents

AI-native issue tracking with Beads. Use when managing work items, tracking issues, or coordinating tasks in multi-agent workflows. Covers bd commands, dependencies, and sync patterns.

| Sprint Type | Depends On | Reason | |-------------|------------|--------| | Schema | None | Foundation sprint | | Data | Schema | Requires defined columns/structure | | Formula | Schema, Data | Requires columns and populated data | | Formatting | Data | Requires data to format | | Integration | Schema | Requires defined structure for external data | | Automation | All | Scripts reference all previous work |

Manages Google Sheets API calls with rate limiting and quota enforcement

All operations invoke n8n workflows via HTTP POST to endpoints configured in `.env`: - `N8N_BASE_URL`: Base URL for n8n instance - `N8N_API_KEY`: Authentication key

Multi-platform paid advertising campaign management skill. Enables creation, budget control, bid strategy optimization, and performance monitoring for digital advertising campaigns across major platforms.

No description available

All operations invoke n8n workflows via HTTP POST to endpoints configured in `.env`: - `N8N_BASE_URL`: Base URL for n8n instance - `N8N_API_KEY`: Authentication key

Validates data integrity and state consistency between Google Sheets operation sprints

Orchestrate Docker container execution across parallel agent waves with memory-aware spawning

CFN Loop workflow orchestration - three-loop structure management with gate checks and consensus. Use when coordinating Loop 3 implementers and Loop 2 validators, managing iteration cycles, or enforcing quality gates.

Wave checkpoint mechanism provides crash recovery, orphan container detection, and automated resumption capabilities for CFN Docker orchestration. Enables orchestrators to survive process failures and resume wave execution without losing work or leaving orphaned containers.

Unified error handling, batching, and logging for CFN Loop. Use when you need to capture agent errors, batch multiple errors for processing, log structured error data, or categorize and recover from agent failures.

Creates and manages file backups before edit operations in agent workflows.

Skill deployment and promotion lifecycle management. Use when transitioning skills from APPROVED to DEPLOYED status, or promoting skills from staging to production with SLA enforcement.

Automated skill deployment pipeline for CFN Loop integration

Enforces validation pattern compliance across all agent profiles with automated detection and fixing

Reusable bash utility functions for CFN Loop - logging, error handling, retry, file operations. Use when you need structured logging, atomic file operations, retry logic with exponential backoff, or standardized error handling in bash scripts.

No description available

File and log operations for CFN

Centralized file locking and atomic write operations for bash scripts.

This skill should be used when the user asks to "/oblique", "oblique strategy", "give me an oblique strategy", "give me a creative prompt", or wants lateral thinking inspiration for their coding session.

This skill generates case study entries for intelligent textbook projects from GitHub repositories. Use this skill when adding a new case study to the case studies index page, when the user provides a GitHub repo URL and wants to create a case study card entry. The skill handles repo analysis, thumbnail generation/compression, and markdown entry formatting.

Persistent memory for AI coding agents via CLI. USE WHEN user says "save context", "remember this", "checkpoint", "resume session", "prepare for compaction", "wrap up", OR when starting work on a project that may span sessions.

Persistent memory for AI coding agents via MCP tools. USE WHEN user says "save context", "remember this", "checkpoint", "resume session", "prepare for compaction", "wrap up", OR when starting work on a project that may span sessions.

Search ChEMBL bioactive molecules database with natural language queries. Find compounds and assay data with Valyu semantic search.

Search arXiv physics, math, and computer science preprints using natural language queries. Powered by Valyu semantic search.

Search global patents with natural language queries. Prior art, patent landscapes, and innovation tracking via Valyu.

Search Open Targets drug-disease associations with natural language queries. Target validation powered by Valyu semantic search.

Search DrugBank comprehensive drug database with natural language queries. Drug mechanisms, interactions, and safety data powered by Valyu.

Search FDA drug labels with natural language queries. Official drug information, indications, and safety data via Valyu.

Search ClinicalTrials.gov with natural language queries. Find clinical trials, enrollment, and outcomes using Valyu semantic search.

Search bioRxiv biology preprints with natural language queries. Semantic search powered by Valyu.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks

This skill should be used when running ansible-lint, configuring linting rules, testing Ansible playbooks, validating playbook syntax, or setting up integration tests. Covers ansible-lint configuration and testing strategies.

Manage the Matrix/Virgo-Core Proxmox VE cluster (nodes Foxtrot, Golf, Hotel - MINISFORUM MS-A2 with AMD Ryzen 9 9955HX). Covers VM provisioning, VLAN networking, CEPH storage, and automation via Python (proxmoxer), Ansible (community.general.proxmox), and Terraform (Telmate/proxmox).

NetBox IPAM and PowerDNS integration for automated DNS record management.

Python code quality tooling with ruff and pyright. Use when setting up linting, formatting, type checking, configuring ruff or pyright, or establishing code quality standards.

Process video files with audio extraction, format conversion (mp4, webm), and Whisper

Enter and manage Deep Work sessions in Agent Hive. Use this skill when starting a focused work session on a project, generating session context, following the handoff protocol, or managing your responsibilities as an agent during a work session.

Check collaboration status from Codex side. Use when user says claude status, check status, or collaboration status.

Read and integrate response from Codex. Use when user says codex read, get codex response, or check codex results.

Check the current status of Codex collaboration. Use when user says codex status, check codex, or collaboration status.

Define and apply an Overall Evaluation Criterion (OEC) to measure the long-term impact of product changes. Use this skill when designing A/B tests, setting quarterly OKRs, or when short-term wins (like revenue) are potentially harming long-term user retention.

Validating product hypotheses when traffic is low, transactions are infrequent, or traditional A/B testing is statistically impossible. Use this when launching in new markets, managing high-ticket items, or when a power analysis indicates a runtime of 6+ months.

Guide for creating effective custom subagents in Claude Code. Use when users want to create or update specialized AI subagents with custom system prompts, tool restrictions, and specific configurations for task delegation.

Frameworks and scripts for delivering hard news, including underperformance, missed promotions, and pre-termination warnings. Use this when a report is failing to meet expectations, during performance review cycles, or when managing highly defensive reactions.

A framework for converting self-serve product usage into high-value enterprise contracts. Use this when your self-serve revenue hits a ceiling, when you need to transition individual users to team-wide adoption, or when sales teams need higher-intent pipeline based on actual product behavior.

A framework for classifying product decisions based on impact and reversibility. Use this when you feel like a bottleneck for your team, when you have a massive backlog of choices to make, or when you need to justify spending weeks of research on a single high-stakes problem.

A framework for founders and product managers to build a scalable B2B sales process. Use this when you are launching a new B2B product, when your current sales process feels inconsistent, or when you are preparing to hire your first full-time salesperson.

A step-by-step framework to safely transition AI products from prototypes to autonomous agents. Use this when reliability is a major concern, when users are skeptical of AI decision-making, or when deploying LLM-based systems into high-stakes workflows.

Transition from traditional seat-based or consumption-based SaaS pricing to a model where customers pay only for successful business results (resolutions). Use this when building AI agents, moving from tool-based software to outcome-oriented services, or when your product performs a job autonomously.

Manage tasks in SQLite database. Use for adding, listing, completing, or blocking tasks. Triggers on task management, todo operations, or heartbeat task processing.

CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.

Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Moltbot to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

Manage Apple Reminders via the `remindctl` CLI on macOS (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output.