Results for “context-engine”

Runtime router for context decisions during a task — decide read-more / stop / ask / assume / delegate, pick a minimal read-set, and time compaction. Front-page mental model is Write / Select / Compress / Isolate; a lazy pattern index routes to 25 context-engineering patterns, one reference per decision. Use when context is near budget, a long session is degrading, you must choose what to read for a task, or you are deciding /compact vs /clear vs a sub-agent. NOT for structural .claude/ overhead audits (see mk:context-audit); NOT for owning persistence (see mk:memory); NOT for USD cost (see mk:budget).

The English summary is being prepared. Showing the original description.

Plan and improve AI agent systems by managing the information models receive. This collection covers memory, agent coordination, tool design, context compression, evaluation, and the operating controls needed for reliable autonomous workflows.

• Planning information management for a new AI agent
• Investigating failures in long agent conversations
• Designing agent memory and multi-agent coordination

Learn how instructions, documents, tool results, and conversation history form an AI model’s context. Understand attention limits, why information in the middle can be missed, and how relevance and placement inform decisions about what to include.

• Learning the basics of context engineering
• Understanding why more input does not always help
• Explaining how instruction placement affects attention

Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.

The English summary is being prepared. Showing the original description.

Audits and reorganises what an AI coding agent carries in its context window: instruction files, path-scoped rules, skills, subagents, hooks and the running conversation. Use when someone says "the agent ignores our CLAUDE.md", "set this repo up for Claude Code / Codex / Cursor", "my AGENTS.md is too long", "quality drops in long sessions", "it keeps inventing APIs", "what should go in a skill versus the rules file", or asks how to hand work to a subagent. Grounded in the documented loading behaviour of Claude Code, with the equivalents for Codex, Gemini CLI and Cursor.

The English summary is being prepared. Showing the original description.

Use when Odylith context-engine packets, retrieval, anchor resolution, or routing support flows need operation-level work.

The English summary is being prepared. Showing the original description.

Work with Odylith context-engine packets, retrieval, and routing support flows.

The English summary is being prepared. Showing the original description.

Expert en ingénierie du contexte IA (compression de prompts, chunking, gestion tokens, optimisation fenêtre)

The English summary is being prepared. Showing the original description.

Organize the information an AI coding agent needs for each task. This skill guides project rules, relevant file selection, conversation summaries, and session handoffs so the agent can follow existing conventions and retain key decisions.

• Set up project rules for AI coding agents
• Select relevant files before starting a task
• Trim stale information from a long conversation

Organize the instructions, conversation history, and tool information an agent receives. Use the skill to clarify business rules, structure SKILL.md files for loading when needed, and distinguish external source material from instructions to reduce prompt injection risks.

• Reorganizing an agent's system instructions
• Reviewing SKILL.md structure and activation conditions
• Turning vague business rules into explicit decisions

Give an agent rules for consulting long-term memory before work and saving decisions, corrections, and failures afterwards. It helps carry preferences and project conventions across sessions while preserving dated history and making conflicting memories visible.

• Carry preferences and project conventions across sessions
• Record user corrections for future tasks
• Preserve the history of changed decisions

Use OpenViking through OpenClaw to manage long-term memories, search archived conversations, and find imported resources or Agent Skills. Inspect recall traces to understand search results and recover full tool outputs stored outside the conversation.

• Recall past preferences and decisions
• Find exact commands in archived conversations
• Import and search documents or Agent Skills

Turn a strategic question or intake notes into a one-page brief for discussion. Outline options, assumptions, constraints, success measures, and signals for reconsidering the decision, then save the brief as a Markdown file.

• Preparing a pricing decision for discussion
• Comparing market-entry options
• Defining success and exit criteria before a decision

Send a founder’s strategic question to the appropriate executive advisor by matching its wording and intent. Questions spanning several roles go to a boardroom discussion, while unclear questions receive an intake to clarify the issue.

• Finding the right advisor for a business question
• Framing fundraising decisions across multiple roles
• Routing sales or customer retention concerns

Route business questions to relevant executive advisor roles, coordinate discussions across multiple functions, and combine their findings into clear agreements, disagreements, and action items. Record decisions and flag approved decisions that are due for review.

• Comparing fundraising with spending cuts
• Reviewing decisions across several business functions
• Clarifying conflicting advisor opinions

Load company background for executive advisor sessions, check whether it is outdated or incomplete, and propose updates learned during conversations. Apply rules for excluding sensitive details and anonymizing permitted information before external searches or API calls.

• Loading company background before an executive advisor session
• Checking outdated or incomplete company information
• Proposing context updates from new conversation details

Plan how an AI agent uses limited input space through reusable prompt prefixes, shorter tool outputs, summaries, and task splitting. Measure token use, response quality, and latency to choose optimizations that provide a net benefit.

• Reducing token use from lengthy tool outputs
• Improving prompt cache reuse
• Planning context budgets for long conversations

Model what an agent believes, wants, and commits to doing. Connect external facts to goals and plans using structured relationships, with evidence and validity periods that help trace why the agent chose an action.

• Convert RDF data into agent beliefs
• Trace the reasons behind agent decisions
• Track belief validity and changes over time

Design file-based storage for agent context, including large tool results, plans, logs, and handoff notes. Keep information available outside the conversation and retrieve relevant sections when needed, instead of loading everything at once.

• Saving large tool results for selective reading
• Keeping plans available during long tasks
• Sharing findings between agents through files

Write and review launch prompts for agents working autonomously for hours or days. Define successful deliverables, excluded partial results, stopping rules, worker handoffs, and evidence-based review requirements so completion can be assessed against explicit criteria.

• Turning vague requests into precise task briefs
• Defining stopping rules for long autonomous runs
• Specifying deliverables for parallel workers

Design persistent agent memory that retains knowledge across sessions and retrieves relevant facts when needed. Compare storage approaches, track people and changing information, and plan memory consolidation and evaluation based on the kinds of questions the agent must answer.

• Retain user preferences across conversations
• Track people and entities consistently across sessions
• Retrieve facts valid at a specific point in time

Design the controls around autonomous agents: what they can edit, how results are evaluated, how progress is logged, and when human approval is required. Build research and experiment loops with clear recovery and review rules.

• Designing autonomous research and experiment loops
• Separating editable work from fixed evaluation rules
• Preserving progress and failed attempts across long runs

Turn ePub books into training examples for models that reproduce an author's writing style. Covers text extraction, coherent segmentation, varied instructions, model training, and checks for copied phrases and style transfer to new scenarios.

• Build training datasets from ePub books
• Train a model on an author's writing style
• Check for copied phrases in generated prose

Guide multi-source research through source checks, comparison of key claims, and recovery from failed tool calls. Produce reports that distinguish retrieved evidence from unresolved questions and clearly document remaining gaps.

• Checking key claims against multiple sources
• Recovering from failed source retrieval
• Documenting evidence and gaps in research reports