Loading...
Loading...
Found 105 Skills
Pattern GSD (Get Shit Done) - découper en tâches atomiques avec contextes subagent frais pour combattre le context rot. Use when planning complex work or working past 50% context usage.
Third-party Claude Code token/context/code-review tools. Use when choosing or recommending an external tool to reduce token usage, manage context, or review large codebases.
Expert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output formatting, and prompt evaluation. Use when: prompt engineering, system prompt, few-shot, chain of thought, prompt design.
Strategies for managing LLM context windows effectively in AI agents. Use when building agents that handle long conversations, multi-step tasks, tool orchestration, or need to maintain coherence across extended interactions.
Generate a smart bootstrap prompt to continue the current conversation in a fresh session. Use when (1) approaching context limits, (2) user says "handoff", "bootstrap", "continue later", "save session", or similar, (3) before closing a session with unfinished work, (4) user wants to resume in a different environment. Outputs a clipboard-ready prompt capturing essential context while minimizing tokens.
The project's all-seeing guide. Sentinel MUST activate before Claude takes any action that modifies, creates, or deletes anything in the project. It understands the codebase, architecture, brand, design system, business model, deployment pipeline, testing strategy, and every convention. Trigger on: action requests (build, fix, add, change, update, refactor, implement, create, remove, delete, migrate, deploy, integrate, improve, configure, install, bump, upgrade, debug, troubleshoot, move, rename); casual requests (can you, I need to, let's, go ahead and, help me, we need to); status reports (X is broken/failing, there's a bug); project questions (how does X work here, where would I add, walk me through); planning (scope this, break this down, write a spec). Do NOT trigger on general knowledge, blog posts, interview prep, or tech comparisons for other projects. Key test: does this need THIS project's context? If yes, trigger. Sentinel guides Claude, it does not execute. No task is too small.
Semantic search, context management, and document indexing via OpenViking. Use when the user asks to: index/import documents or files into a knowledge base, perform semantic search across indexed content, browse or explore indexed resources, get summaries/overviews of indexed documents, manage an OpenViking instance, or integrate structured context retrieval into workflows. Also use when sub-agents need to retrieve relevant context from a large document collection.
This skill implements a specific task from a project's ROADMAP.md file. It should be used when the user wants to work on a roadmap action item by its ID (e.g., '1.1', '2.3'). Triggered by requests like '/do-task 1.1', '/do-task 2.3', or 'do task 3.1'. Works alongside the project-init skill (which creates the roadmap) and the checkpoint skill (which commits afterward).
Core patterns for AI coding agents based on analysis of Claude Code, Codex, Cline, Aider, OpenCode. Triggers when: Building an AI coding agent or assistant, implementing tool-calling loops, managing context windows for LLMs, setting up agent memory or skill systems, or designing multi-provider LLM abstraction. Capabilities: Core agent loop with while(true) and tool execution, context management with pruning and compression and repo maps, tool safety with sandboxing and approval flows and doom loop detection, multi-provider abstraction with unified API for different LLMs, memory systems with project rules and auto-memory and skill loading, session persistence with SQLite vs JSONL patterns.
Persistent memory and context management for AI agents using OpenContext. Keep context across sessions/repos/dates, store conclusions, and provide document search workflows.
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. A core context engineering skill — also activates when the user mentions "context engineering" or "context-engineering" in the context of diagnosing and mitigating context failures.
Use when context is growing large (50k+ tokens), performance is degrading, instructions are being ignored mid-conversation, or planning multi-agent workflows. Triggers on "lost context", forgotten instructions, or sessions exceeding 30 minutes.