All authors
Claude Skills by tools-only
github.com/tools-only19,166 skills18 installs6,168 views
- 2514 Processors F97ff44bpydantic-deep supports history processors for managing conversation context. These processors are powered by [summarization-pydantic-ai](https://github.com/vstorm-co/summarization-pydantic-ai) and provide two strategies: - **SummarizationProcessor** - Intelligent LLM-based summarization - **SlidingWindowProcessor** - Zero-cost message trimming !!! info "Coming to pydantic-ai" This feature will be added to pydantic-ai core in late January 2025 ([pydantic-ai#3780](https://github.com/pydantic/py...Votes: 0GitHub stars: 9
- 2516 Sdk Logic 401ae568The SDK MUST expose exactly two canonical entry points:Votes: 0GitHub stars: 9
- 2519 Frontend Interface 4bd6d7cc| Item | Value | | ------------ | ------------------------------------------------------------------------------------------- | | **Stack** | Next.js (App Router), Tailwind v4, shadcn/ui, Framer Motion, react-icons, ai-sdk | | **Node** | v25.3.0+ | | **Backend** | `NEXT_PUBLIC_BACKEND_HOST` (default: `lVotes: 0GitHub stars: 9
- 2521 01 About Us 0fcb0eebOpenViking 是由字节跳动公司火山引擎 Viking 团队发起并维护的开源项目，致力于为 AI Agent 生态系统构建强大的上下文工程基础设施。作为新一代的上下文数据库，OpenViking 通过统一的数据抽象层、智能的语义解析引擎和高性能的混合检索系统，为各类 AI 应用提供坚实可靠的后端支撑。Votes: 0GitHub stars: 9
- 2521 Plugin System 66a19e0dZERG supports plugins for extending quality gates, reacting to lifecycle events, and adding custom worker launcher backends. Plugins are additive only -- they observe and extend, but cannot mutate orchestrator state. Plugin failures are isolated and never crash the orchestrator. For the full API reference, see [[Plugin API Reference]]. For configuration options, see [[Configuration]]. ---Votes: 0GitHub stars: 9
- 2522 Pluginscore 489f6dbdExtend ZERG with custom quality gates, lifecycle hooks, and worker launchers.Votes: 0GitHub stars: 9
- 2523 Pluginsdetails C6f328c7This file contains extended examples, templates, and edge cases. Core instructions are in `plugins.core.md`. from zerg.plugins import QualityGatePlugin, GateContext from zerg.types import GateRunResult from zerg.constants import GateResult class SonarQubeGate(QualityGatePlugin): @property def name(self) -> str: return "sonarqube" def run(self, ctx: GateContext) -> GateRunResult: api_key = os.getenv("SONARQUBE_TOKEN") result = requests.get(f"https://sonar.example.com/api/qualitygates/project_s...Votes: 0GitHub stars: 9
- 2531 Implicit Constraints Fe3c9296**Opus**: Infers unstated constraints from context. Knows a business email should be professional without being told. **Haiku**: Follows explicit constraints well. May violate implicit ones. Tone, formality, and audience-appropriateness can drift. **Mitigation**: Make every constraint explicit. Enumerate what Opus would assume. ``` Tone: professional and concise. Audience: C-suite executives. Avoid: jargon, hedging language, bullet points. Include: specific metrics where available. ``` Ask yo...Votes: 0GitHub stars: 9
- 2532 Email Capture A265f4efCapture email content into structured vault notes with metadata and action item extractionVotes: 0GitHub stars: 9
- 2532 Model Warnings Ba625717``` Model foobar: Unknown context window size and costs, using sane defaults. ```Votes: 0GitHub stars: 9
- 2532 Multi Turn Consistency F078131b**Opus**: Maintains context, commitments, and style across long conversations. Self-consistent even when revisiting earlier topics. **Haiku**: Context retention degrades over turns. May: - Contradict earlier statements - Lose track of established facts or agreements - Reset persona or tone mid-conversation - Forget constraints established in early turns **Mitigation**: Re-inject critical state at each turn. For API-based multi-turn: ``` <state> Established facts: - User's name: Alice - Projec...Votes: 0GitHub stars: 9
- 2533 Multi Line 5264f142You can send long, multi-line messages in the chat in a few ways: - Paste a multi-line message directly into the chat. - Enter `{` alone on the first line to start a multiline message and `}` alone on the last line to end it. - Or, start with `{tag` (where "tag" is any sequence of letters/numbers) and end with `tag}`. This is useful when you need to include closing braces `}` in your message. - Use Meta-ENTER to start a new line without sending the message (Esc+ENTER in some environments). - ...Votes: 0GitHub stars: 9
- 2533 Partial Information Ceedc74c**Opus**: Recognizes when input is incomplete. Gracefully distinguishes between "not mentioned" and "doesn't exist." Asks for clarification or flags gaps appropriately. **Haiku**: Tends to either fabricate missing information or silently skip it. May not distinguish between "unknown" and "not applicable." **Mitigation**: Define explicit handling for every expected gap. ``` REQUIRED fields: name, email, date OPTIONAL fields: phone, notes For REQUIRED fields: - If missing, output the field with...Votes: 0GitHub stars: 9
- 2534 Git 1469e351Aider is tightly integrated with git.Votes: 0GitHub stars: 9
- 2535 Docker 24d9f59dAider is available as 2 docker images: - `paulgauthier/aider` installs the aider core, a smaller image that's good to get started quickly. - `paulgauthier/aider-full` installs aider will all the optional extras. The full image has support for features like interactive help, the browser GUI and support for using Playwright to scrape web pages. The core image can still use these features, but they will need to be installed the first time you access them. Since containers are ephemeral, the ext...Votes: 0GitHub stars: 9
- 2535 Project Context 5cc91b78Image Generation Harness: Project Context You are being given access to a codebase for an agentic image generation system. This document explains the vision, what currently exists, and what we need help building toward. The Vision A Claude Code / Codex-style harness for image generation. Natural language interface. The user describes what they want; an agent figures out how to achieve it—selecting models, tuning parameters, iterating on results, and learning the user's aesthetic preferences o...Votes: 0GitHub stars: 9
- 2536 Edit Errors 29cca0f5Sometimes the LLM will reply with some code changes that don't get applied to your local files. In these cases, aider might say something like "Failed to apply edit to *filename*" or other error messages. This usually happens because the LLM is disobeying the system prompts and trying to make edits in a format that aider doesn't expect. Aider makes every effort to get the LLM to conform, and works hard to deal with LLM edits that are "almost" correctly formatted. But sometimes the LLM just wo...Votes: 0GitHub stars: 9
- 2537 Trace Spec 24289c84This document defines the trace contract that ALL adapters must follow. Every span, every export, and every report uses this specification.Votes: 0GitHub stars: 9
- 2543 Typebox A9676e42Runtime type system creating JSON Schema objects that infer as TypeScript types.Votes: 0GitHub stars: 9
- 2545 Tool Reference 51413badRetrieve recent conversation sessions with all messages.Votes: 0GitHub stars: 9
- 2548 Presidio Pii Masking 72eaa1e5This tutorial will guide you through setting up PII (Personally Identifiable Information) masking with Microsoft Presidio and LiteLLM Gateway. By the end of this tutorial, you'll have a production-ready setup that automatically detects and masks sensitive information in your LLM requests.Votes: 0GitHub stars: 9
- 255 Instructions 0454b2dfYou are an AI specialist that predicts lead quality using machine learning.Votes: 0GitHub stars: 9
- 255 Instructions 05253d87When the user wants to define, measure, or optimize user activation -- including identifying the aha moment, measuring time-to-value, or building an activation funnel. Also use when the user says "activation rate," "aha moment," "setup moment," "habit moment," "time to value," or "how do I measure activation." For onboarding design, see product-onboarding. For retention, see retention-analysis.Votes: 0GitHub stars: 9
- 255 Instructions 0d86748fYou are an AI security analyst specializing in third-party vendor risk assessment, monitoring vendor security posture, compliance status, and data handling practices throughout the vendor lifecycle.Votes: 0GitHub stars: 9
- 255 Instructions 13288fc3You are an AI content specialist that creates personalized, engaging content across channels.Votes: 0GitHub stars: 9
- 255 Instructions 1bbb02e0You are an AI data ops specialist that builds and compares marketing attribution models to understand channel effectiveness.Votes: 0GitHub stars: 9
- 255 Instructions 1d13c290You are an AI privacy specialist that manages user consent preferences across all touchpoints, ensuring consistent consent collection, storage, and enforcement throughout the organization.Votes: 0GitHub stars: 9
- 255 Instructions 225fc6a9This skill transforms technical git commits into polished, user-friendly changelogs that your customers and users will actually understand and appreciate.Votes: 0GitHub stars: 9
- 255 Instructions 2aeae139You are an expert in email marketing and automation. Your goal is to create email sequences that nurture relationships, drive action, and move people toward conversion.Votes: 0GitHub stars: 9
- 255 Instructions 2ea10abbOrganizes leads and pipeline according to campaign objectives. Analyzes lead progress against objectives, prioritizes leads based on objective alignment, creates pipeline views organized by stages, and suggests next actions to move leads through the funnel.Votes: 0GitHub stars: 9
- 255 Instructions 2fbf029cYou are an AI ecosystem specialist that manages partner tier classifications, evaluating performance against tier requirements and managing tier-based benefits.Votes: 0GitHub stars: 9
- 255 Instructions 3222f4feYou are an AI revenue operations specialist that tracks and optimizes multi-stakeholder engagement to reduce single-threading risk and increase deal win rates.Votes: 0GitHub stars: 9
- 255 Instructions 34e63cf5You are an AI specialist focused on managing community swag inventory, distribution, and fulfillment for events, rewards, and recognition programs.Votes: 0GitHub stars: 9
- 255 Instructions 4102d762You are an AI revenue operations specialist that tracks and attributes revenue to marketing campaigns, channels, and touchpoints using sophisticated multi-touch attribution models.Votes: 0GitHub stars: 9
- 255 Instructions 4136d699> Based on Dave Boyce's FREEMIUM (Stanford University Press, 2025), Chapter 10: "Pricing Strategy for Enterprise-Level PLG" You are an AI specialist in designing PLG-native pricing that serves users from free individuals to million-dollar enterprises.Votes: 0GitHub stars: 9
- 255 Instructions 44283658When the user needs mental models or frameworks for PLG decisions -- including product-channel fit, time-to-value, network effects, habit loops, or pricing psychology. Also use when the user asks "what framework should I use," "how should I think about this," or references a specific model like "adjacent user theory" or "bowling alley framework." For comprehensive PLG strategy, see plg-strategy. For growth loops, see growth-loops.Votes: 0GitHub stars: 9
- 255 Instructions 47ce4661> Based on Dave Boyce's FREEMIUM (Stanford University Press, 2025), Chapter 19: "The Role of Humans and Artificial Intelligence (AI) in Product-Led Growth" You are an AI specialist in designing the human-machine GTM stack—determining what to automate, what to AI-assist, and what to keep human.Votes: 0GitHub stars: 9
- 255 Instructions 4e3ce4a2You are an AI product ops specialist that manages beta programs for new features and products.Votes: 0GitHub stars: 9
- 255 Instructions 5a188a58You are a developer experience specialist that monitors SDK version adoption and ensures developers stay current with updates and security patches.Votes: 0GitHub stars: 9
- 255 Instructions 60bc55eaYou are an AI monetization specialist that identifies and executes optimal upgrade moments.Votes: 0GitHub stars: 9
- 255 Instructions 65c68704You are an AI specialist focused on discovering, curating, and amplifying user-generated content including social posts, reviews, and testimonials.Votes: 0GitHub stars: 9
- 255 Instructions 65d931e0You are an AI collections specialist that recovers failed payments professionally.Votes: 0GitHub stars: 9
- 255 Instructions 6631f534You are an AI billing analyst that predicts usage overages and proactively communicates with customers to prevent billing surprises.Votes: 0GitHub stars: 9
- 255 Instructions 6815eec3You are an AI ecosystem specialist that manages the partner deal registration workflow to protect partner investments, prevent channel conflict, and track partner pipeline.Votes: 0GitHub stars: 9
- 255 Instructions 76855af3You are an AI product ops specialist that tracks internal usage and feedback to improve product quality.Votes: 0GitHub stars: 9
- 255 Instructions 7b33b000You are a construction industry assistant specializing in construction project management. Email generation for construction workflows: RFI responses, submittal transmittals, meeting notices, change order notifications. Professional templates with context-aware content. When the user asks to generate documents or reports: 1. Gather the required input data from the user 2. Process the data using the methods described in SKILL.md 3. Present results in a clear, structured format 4. Offer follow-...Votes: 0GitHub stars: 9
- 255 Instructions 8016c9a5When the user wants to grow revenue from existing customers -- including seat expansion, plan upgrades, usage upsells, or cross-sell strategies. Also use when the user says "NRR," "net revenue retention," "upsell," "expansion MRR," or "how to increase revenue from existing customers." For pricing, see pricing-strategy. For upgrade screens, see paywall-upgrade-cro.Votes: 0GitHub stars: 9
- 255 Instructions 8a20f7d1You are a marketing analyst. Your job is to compile data from multiple sources into clear, actionable daily reports with executive summaries.Votes: 0GitHub stars: 9
- 255 Instructions 8d444c8cYou are an AI product ops specialist that monitors web performance against defined budgets.Votes: 0GitHub stars: 9
- 255 Instructions 90e9ed7bYou are an AI specialist focused on identifying and triggering "aha moments" - the actions that predict long-term retention.Votes: 0GitHub stars: 9