tools-only/X-Skills - Page 12

sam-context-size-management

Define explicit guidance for measuring and managing context size per agent. What's the target token budget? How to detect context pressure?

Langue du texte source : anglais

evaluate-sdlc-layers

Evaluate and iterate on the SDLC Layer Separation Architecture implementation. Runs validation checks (cross-references, doc completeness, layer metadata, integration points), produces a findings report, and supports iterative fixes. Use when validating…

Langue du texte source : anglais

development-harness-task-status-mcp

Wrap `implementation_manager.py` CLI as MCP tools. Agents could query task status, list pending tasks, and update task state programmatically. Tools: `query_tasks`, `list_pending`, `update_task_status`, `parse_task_file`.

Langue du texte source : anglais

groom-backlog-item

Groom backlog items — trigger /groom-backlog-item <title|section|all> — fact-checks item claims against primary sources, runs RT-ICA per item, then spawns @backlog-item-groomer agents. Writes groomed content into per-item files in .claude/backlog/. Use when…

Langue du texte source : anglais

impactful-writing

Write clear, emotionally resonant, and well-structured content that readers remember and act upon. Use when writing or editing any text—Twitter posts, articles, documentation, emails, comments, updates—for maximum clarity, engagement, and impact.

Langue du texte source : anglais

weaviate

Search, query, and manage Weaviate vector database collections. Use for semantic search, hybrid search, keyword search, natural language queries with AI-generated answers, collection management, data exploration, filtered fetching, data imports from…

Langue du texte source : anglais

idea-validator

Validate batches of YouTube video ideas against search demand, competition, and audience fit. Returns scored assessments.

Langue du texte source : anglais

yt-scraper

Orchestrate YouTube scraping via Apify actors. Triggers channel/video/search scraping, fetches datasets, and persists results as JSON.

Langue du texte source : anglais

yt-brief

Refine a YouTube video idea into a structured production brief with angle, key points, value proposition, CTA asset, and audience segment. Use this skill whenever the user says "create a brief", "brief this idea", "develop this idea", "write a video brief",…

Langue du texte source : anglais

yt-packaging

Create optimized YouTube titles and thumbnail concepts for maximum CTR. Use this skill whenever the user says "title ideas", "thumbnail concepts", "package this video", "CTR optimization", "title options", "packaging", or has an approved brief and needs to…

Langue du texte source : anglais

yt-outline

Build detailed step-by-step YouTube video outlines with demo prep, screen-share sequences, and visual planning. Use this skill whenever the user says "create an outline", "outline this video", "video outline", "build the outline", "production outline", or has…

Langue du texte source : anglais

channel-analyzer

Analyze a batch of YouTube channels for competitive intelligence. Produces structured competitive analysis per channel.

Langue du texte source : anglais

yt-pipeline

Run the full YouTube content production pipeline

Langue du texte source : anglais

yt-research

Research competitor YouTube channels, niches, and trending topics for your content strategy. Use this skill whenever the user says "research channels", "analyze competitors", "find trending topics", "niche analysis", "competitive research", "what are other…

Langue du texte source : anglais

yt-ideation

Generate and validate YouTube video ideas aligned with content pillars, audience strategy, and priority tiers. Use this skill whenever the user says "generate ideas", "brainstorm videos", "what should I make next", "video ideas", "content ideas", "ideation",…

Langue du texte source : anglais

langfuse-observability

Instrument LLM applications with Langfuse tracing. Use when setting up Langfuse, adding observability to LLM calls, or auditing existing instrumentation.

Langue du texte source : anglais

langfuse-prompt-migration

Migrate hardcoded prompts to Langfuse for version control and deployment-free iteration. Use when user wants to externalize prompts, move prompts to Langfuse, or set up prompt management.

Langue du texte source : anglais

conventional-commits

When writing a git commit message. When task completes and changes need committing. When project uses semantic-release, commitizen, git-cliff. When choosing between feat/fix/chore/docs types. When indicating breaking changes. When generating changelogs from…

Langue du texte source : anglais

slack

Send messages, upload files, read conversations, react to messages, and manage Slack workspaces using SlackCLI. Use when the user wants to interact with Slack — send a message, share a file, read channel history, find a user, react to a message, or check…

Langue du texte source : anglais

work-backlog-item

Use when working, planning, or closing a backlog item. Bridges BACKLOG.md to the SAM planning pipeline with optional GitHub Issue/Project/Milestone tracking. No args: interactive browser. With '#N': load item directly from GitHub Issue #N (labels and…

Langue du texte source : anglais

backlog-item-groomer

Produce groomed content for a backlog item — discovers related skills, agents, prior work, and dependency graph; performs RT-ICA assessment; outputs groomed item template for writing into .claude/backlog/{priority}-{slug}.md. Activate when preparing to work…

Langue du texte source : anglais

c4-diagram

Generate C4 architecture diagrams from system notes

Langue du texte source : anglais

diagram-review

Analyse architecture diagrams and flowcharts

Langue du texte source : anglais

diagram

Generate architecture diagrams using Python diagrams library

Langue du texte source : anglais

evaluate-sdlc-layers

Evaluate and iterate on the SDLC Layer Separation Architecture implementation. Runs validation checks (cross-references, doc completeness, layer metadata, integration points), produces a findings report, and supports iterative fixes. Use when validating…

Langue du texte source : anglais

groom-backlog-item

Groom backlog items — trigger /groom-backlog-item <title|section|all> — fact-checks item claims against primary sources, runs RT-ICA per item, then spawns @backlog-item-groomer agents. Writes groomed content into per-item files in .claude/backlog/. Use when…

Langue du texte source : anglais

aws-cloudformation-bedrock

Provides AWS CloudFormation patterns for Amazon Bedrock resources including agents, knowledge bases, data sources, guardrails, prompts, flows, and inference profiles. Use when creating Bedrock agents with action groups, implementing RAG with knowledge bases,…

Langue du texte source : anglais

nextjs-app-router

Provides patterns and code examples for building Next.js 16+ applications with App Router architecture. Use when creating projects with App Router, implementing Server Components and Client Components ("use client"), creating Server Actions for forms,…

Langue du texte source : anglais

langchain4j-mcp-server-patterns

Provides Model Context Protocol (MCP) server implementation patterns with LangChain4j. Use when building MCP servers to extend AI capabilities with custom tools, resources, and prompt templates.

Langue du texte source : anglais

spring-ai-mcp-server-patterns

Provides Model Context Protocol (MCP) server implementation patterns with Spring AI. Use when building MCP servers to extend AI capabilities with custom tools, resources, and prompt templates using Spring's official AI framework.

Langue du texte source : anglais

qdrant

Provides Qdrant vector database integration patterns with LangChain4j. Handles embedding storage, similarity search, and vector management for Java applications. Use when implementing vector-based retrieval for RAG systems, semantic search, or recommendation…

Langue du texte source : anglais

aws-lambda-typescript-integration

Provides AWS Lambda integration patterns for TypeScript with cold start optimization. Use when deploying TypeScript functions to AWS Lambda, choosing between NestJS framework and raw TypeScript approaches, optimizing cold starts, configuring API Gateway or…

Langue du texte source : anglais

aws-cloudformation-lambda

Provides AWS CloudFormation patterns for Lambda functions, layers, event sources, and integrations. Use when creating Lambda functions with CloudFormation, configuring API Gateway, Step Functions, EventBridge, SQS, SNS triggers, and implementing template…

Langue du texte source : anglais

aws-cloudformation-auto-scaling

Provides AWS CloudFormation patterns for Auto Scaling including EC2, ECS, and Lambda. Use when creating Auto Scaling groups, launch configurations, launch templates, scaling policies, lifecycle hooks, and predictive scaling. Covers template structure with…

Langue du texte source : anglais

aws-sdk-java-v2-messaging

Provides AWS messaging patterns using AWS SDK for Java 2.x for SQS queues and SNS topics. Handles sending/receiving messages, FIFO queues, DLQ, subscriptions, and pub/sub patterns. Use when implementing messaging with SQS or SNS.

Langue du texte source : anglais

rag

Provides patterns to build Retrieval-Augmented Generation (RAG) systems for AI applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge…

Langue du texte source : anglais

atac

DSL and CLI for building and running Agentic Trajectories (ATaC).

Langue du texte source : anglais

refresh-research

TRIGGER — /refresh-research invoked or bulk research update requested. Inventories ./research/ entries, detects stale entries by review date or age, runs RT-ICA pre-flight, spawns research-curator agents in waves of 5, collects per-wave results, updates…

Langue du texte source : anglais

edge-candidate-agent

Generate and prioritize US equity long-side edge research tickets from EOD observations, then export pipeline-ready candidate specs for trade-strategy-pipeline Phase I. Use when users ask to turn hypotheses/anomalies into reproducible research tickets,…

Langue du texte source : anglais

work-backlog-item

Use when working, planning, or closing a backlog item. Bridges BACKLOG.md to the SAM planning pipeline with optional GitHub Issue/Project/Milestone tracking. No args: interactive browser. With '#N': load item directly from GitHub Issue #N (labels and…

Langue du texte source : anglais