Context Engineering

token-budget-advisor is a routing skill that helps choose response depth before answering. Use it to control length, detail, or token spend in workflow automation and chat flows. This token-budget-advisor guide covers trigger rules, when not to use it, and how to apply it from skills/token-budget-advisor.

prompt-optimizer is a prompt-optimizer skill that analyzes rough prompts, finds missing context, and rewrites them into clearer, ready-to-paste prompts. It is best for prompt-optimizer guide work, prompt review, and prompt-optimizer for Prompt Writing, especially when you need better structure for Claude Code or ECC workflows. It does not execute the underlying task.

The context-budget skill audits Claude Code context use across agents, skills, rules, and MCP servers. It helps identify bloat, duplicate content, and high-cost components, then returns prioritized cleanup actions. Use this context-budget guide for practical context-budget usage and for Skill Testing in larger setups.

ck is a Claude Code project memory skill for persistent context across sessions. It registers projects, auto-loads briefing data on start, and supports save, resume, info, list, forget, and migrate workflows through deterministic Node.js scripts. A strong fit for ck for Context Engineering.

ai-first-engineering is a concise operating model for teams where AI agents generate much of the implementation work. It helps set Agent Standards for planning, architecture, review, and testing, with guidance on install, usage, and when to apply the skill.

agent-harness-construction is a practical skill for improving agent harness design, including tool schemas, observation formats, error recovery, and context budgeting for stronger completion rates.

prompt-engineering-patterns is a practical skill for production prompt design, covering install context, reusable templates, few-shot examples, structured outputs, and prompt optimization workflows for Context Engineering.

context-driven-development helps create and maintain Conductor project context artifacts like product.md, tech-stack.md, workflow.md, and tracks.md so AI-assisted development stays consistent across sessions and codebases.

The context-engineering skill helps you structure project context so agents follow conventions, reduce hallucinations, and stay focused. Use it when starting a session, switching tasks, or building a context-engineering guide for a codebase.

product-marketing-context helps teams create and maintain `.agents/product-marketing-context.md` so other marketing skills can reuse product, audience, positioning, objections, proof points, and messaging context. It checks for an existing file, supports auto-draft or start-from-scratch setup, and updates only the sections that changed.

teach-impeccable is a one-time UI design setup skill that scans your repo, asks targeted UX questions, and saves persistent design guidance for future sessions.

session-handoff helps agents create and resume structured handoff documents for multi-session work. It includes a create vs resume workflow, a handoff template, a resume checklist, and scripts to create, validate, list, and check handoff staleness for reliable Context Engineering.

agent-md-refactor helps refactor bloated AGENTS.md, CLAUDE.md, or COPILOT.md files using progressive disclosure. It surfaces contradictions, keeps universal rules at the root, and splits the rest into linked docs for cleaner Context Engineering and lower context load.

memory-management helps Claude persist project context across sessions with a HOT/WARM/COLD file workflow. Use it to maintain `CLAUDE.md`, `memory/` folders, glossary entries, and event-driven updates for audits, rankings, competitors, and reports in SEO or Context Engineering workflows.

huashu-nuwa is a Skill Authoring skill that turns a person, topic, or vague need into a reusable perspective skill. It guides install and usage through `SKILL.md`, `references/extraction-framework.md`, `references/skill-template.md`, and example skills for distillation, routing, and quality review.

mnemos is a task-scoped memory skill for agents that need durable context across compactions. It uses a typed MnemoGraph to keep goals and constraints persistent, compress results, and preserve checkpoints for resume. Useful for context engineering, debugging, repo maintenance, and handoffs.

llm-patterns helps you design AI-first application logic where LLMs handle reasoning, extraction, and generation while code handles validation, routing, and error handling. Use the llm-patterns skill for clearer prompt structure, testable LLM workflows, and practical guidance for Skill Authoring.

immortal-skill is a Skill Authoring workflow for turning chats, documents, and platform exports into an evidence-aware digital persona package. It guides role selection, source collection, ethics checks, conflict handling, and output generation for reusable agent skills.

steve-jobs-perspective is a role-driven product critique skill that uses Steve Jobs-style heuristics, research files, and examples to sharpen product decisions, messaging, and strategy.

create-senpai is a Claude Code skill that turns chat exports, meeting notes, screenshots, and photos into a reusable senpai persona with group memory, correction flow, and ongoing updates.

create-boss turns boss chats, notes, emails, and project artifacts into a reusable skill for judgment, managing up, and persona modeling. Install it in Claude Code or OpenClaw to build real manager profiles or entrepreneur archetypes, then refine outputs with correction workflows and reusable Playbooks-ready boss guidance.

shot is a single-file skill from tanweai/pua for full-context persona injection, role-based prompting, and strong sub-agent usage. Best for Context Engineering experiments, P7/P8/P9/P10 role framing, and self-contained prompt loading through skills/shot/SKILL.md.

pua-ja is a Japanese-language escalation skill that pushes stalled agents to investigate harder, use tools before asking users, and verify results after repeated failures. Best for teams that want a trigger-based behavior layer for debugging, research, writing, and pua-ja for Context Engineering.

teach-impeccable is a one-time setup skill that scans your repo, asks only missing UX and brand questions, and saves persistent design guidance for future AI sessions.