“context-engineering”的搜索结果

Audit a repo's agent context — CLAUDE.md files, codebase docs, skills, and tool/MCP designs — against Anthropic's Claude 5 context-engineering guidance ("unhobbling": Anthropic cut ~80% of Claude Code's system prompt with no eval loss). Finds overconstraint, conflicting instructions, redundancy, stale facts, and missing "unknown knowns"; produces a scored findings report with concrete rewrites, then applies approved fixes. Use when someone says "audit my CLAUDE.md", "context audit", "unhobble this repo", "review our agent docs/skills/tools", or after upgrading to Claude 5-generation models.

中文简介正在准备中。当前显示原文说明。

Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.

中文简介正在准备中。当前显示原文说明。

Runtime router for context decisions: read-more/stop/ask/assume/delegate, minimal read-set, compaction timing. Model: Write/Select/Compress/Isolate. NOT for agent-tree overhead audit (context-audit).

中文简介正在准备中。当前显示原文说明。

Read-only audit of the project's agent-tree structural overhead vs the context window. NOT for cost tracking (budget skill); NOT for read/compact decisions (mk:context-engineering).

中文简介正在准备中。当前显示原文说明。

Creates new skills with proper structure, compliance checks, and registration. Enforces mk: prefix, sub-agents.md structure, and context-engineering principles. Use to scaffold a new skill.

中文简介正在准备中。当前显示原文说明。

Read-only audit of .codex/ structural overhead: 'remove X save Y tokens' vs the context window. NOT for cost tracking (budget skill); NOT for runtime read/compact decisions (mk:context-engineering).

中文简介正在准备中。当前显示原文说明。

Runtime router for context decisions: read-more/stop/ask/assume/delegate, minimal read-set, compaction timing. Model: Write/Select/Compress/Isolate. NOT for .codex/ overhead audit (mk:context-audit).

中文简介正在准备中。当前显示原文说明。

Use when refining a draft user prompt before sending it to a coding agent. Decomposes goal/context/constraints/acceptance/output-format, detects ambiguity and model-coupled framing, then emits a model-agnostic rewrite. Supports --analyze, --score, and --deep. NOT for prompts from scratch (mk:brainstorming), plans/reviews (mk:elicit), implementation plans (mk:plan-creator), or general codebase scouting (mk:scout).

中文简介正在准备中。当前显示原文说明。

Read-only audit of `.claude/` structural overhead. Reports prioritized "remove X save Y tokens" recommendations against the model context window. NOT for monetary cost tracking — that's /mk:budget. NOT for transcript size monitoring — long-session continuity defers to Claude Code native compaction. NOT for runtime context decisions (what to read, when to compact) — see mk:context-engineering. Use when planning to add context capacity, diagnosing perceived slowdowns, or auditing health.

中文简介正在准备中。当前显示原文说明。

Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.

中文简介正在准备中。当前显示原文说明。

This skill should be used when the user asks.

中文简介正在准备中。当前显示原文说明。

Use when starting a coding session, setting up a project for AI-assisted development, switching between parts of a codebase, or when agent output quality degrades — hallucinated APIs, wrong patterns, ignored project conventions. Structures what the agent loads and when.

中文简介正在准备中。当前显示原文说明。

Build the smallest, highest-signal context package for an AI coding task — goal, constraints, repo facts, boundaries, and a verification plan. Load when prompts are underspecified, the agent is missing key files or decisions, the user says "use the right context", "here's the repo", or when work is drifting due to missing constraints. Also triggers on "context engineering", "gather context", "what do you need from me", "before you start". Not for cross-session continuity (use memory-startup/memory-recall).

中文简介正在准备中。当前显示原文说明。

Configure or diagnose project context, rules files, context packs, or documented context degradation when explicitly requested; do not trigger automatically at session start, task switching, ordinary repository exploration, implementation, or completion.

中文简介正在准备中。当前显示原文说明。