141 skills · sorted by relevance
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.
Design how an AI agent edits its own working conversation history, choosing what to retain, rewrite, or remove. Covers safeguards, capacity monitoring, recovery after overflow, and the computing cost of changing earlier context.
Turn OpenClaw conversations, actions, and tool history into structured long-term memory. Agents can retrieve past facts, decisions, and summaries when needed, helping them continue work across sessions and recover context after it is shortened.
Review how an AI agent loads, retains, summarizes, and shares working information. This historical guide helps examine forgotten constraints, repeated actions, tool selection, and handoffs using context engineering practices published in 2024–2025.
Understand how OpenRig organizes a team of coding agents. This skill explains the main terms, shows how to identify an agent’s role and peers, and clarifies where skills and working context come from.
Hand off OpenRig work through persistent queue items that record the next owner, blockers, and closure reasons. The skill covers notifying recipients, escalating to a human, and keeping supporting evidence accessible across interruptions and missed messages.
Save an unfinished session as a timestamped Markdown handoff. Capture changed files, decisions and their reasons, current progress, blockers, and ordered next steps so work can resume later or continue in another Claude instance.
Show current session status and context health for the sewage project. Use to check context usage, active work state, and what will survive compaction.
The English summary is being prepared. Showing the original description.
Configure or troubleshoot ACP agent discovery, custom models, skills, and compaction in BB.
The English summary is being prepared. Showing the original description.
Inspect BB Pi provider support for message editing and context compaction.
The English summary is being prepared. Showing the original description.
Pick up where you left off from a previous session — use after context resets, compaction, or new conversations
The English summary is being prepared. Showing the original description.
Master the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction strategies, and context partitioning to keep AI sessions sharp and efficient.
The English summary is being prepared. Showing the original description.
Create managed Iceberg tables using Amazon S3 Tables (s3tables API namespace) with automatic compaction and snapshot management. Sets up table bucket, namespace, table, schema, Glue catalog registration, partitioning, IAM access control. Triggers on: create table, data lake table, analytics table, structured data storage, S3 Tables, Iceberg, Athena table, partitioning strategy, access permissions. Do NOT use for: importing files (use ingesting-into-data-lake), vector storage (use storing-and-querying-vectors), querying existing tables (use querying-data-lake), or locating existing table (use finding-data-lake-assets).
The English summary is being prepared. Showing the original description.
Use this skill when designing, generating an MVP blueprint for, auditing, troubleshooting, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral agent architecture for OpenAI, Anthropic, and OpenAI-compatible APIs: agent loops, tool design, record provenance, interactive presentation, user-memory lifecycles, environment-adaptive tools, speculative tool execution, late-bound capabilities, permissions, system prompts, planning, goals, always-on agents and durable runtime, adaptive agent teams, context compaction, memory, skills, MCP/external connectors, public-board communications, realtime voice agents, hardware agents and board deployment, self-refining recursive harnesses, programmable context, continual refinement, observability, evals, prompt caching, agent-legible environments, feedback loops, and safety.
The English summary is being prepared. Showing the original description.
Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development.
The English summary is being prepared. Showing the original description.
建议在逻辑间隔进行手动上下文压缩（Context Compaction），以便在任务阶段中保留上下文，而不是依赖任意的自动压缩。
The English summary is being prepared. Showing the original description.
建议在逻辑间隔处进行手动压缩（Manual Compaction），以在整个任务阶段保持上下文（Context），而非随意的自动压缩。
The English summary is being prepared. Showing the original description.
State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.
The English summary is being prepared. Showing the original description.
Dynamic context injection, mode switching (dev/review/research), selective loading, and strategic compaction for token optimization.
The English summary is being prepared. Showing the original description.
Distill the current conversation into a structured note (decisions made, open questions, file pointers with line numbers, next 1–3 actions) and save to `quality_reports/session_logs/` before auto-compression. Differs from `/checkpoint` (explicit stop-point snapshot) and from auto-compaction (which truncates rather than distills). Use when context is approaching auto-compact threshold, when a long pipeline has accumulated many decisions, or when the user says "compress", "distil this session", "before we hit auto-compact", "structured handoff before context resets".
The English summary is being prepared. Showing the original description.
Continues interrupted Codex work only after read-codex-history verifies rollout identity and fork/compaction lineage — restores the original outcome, unfulfilled requests, and the next action. Use when given a Codex Session ID, asked to pick up a prior Codex run, told Codex was interrupted, fused, compacted or stuck, or asked to take over without `codex resume`. Not for a conversation Codex already natively resumed.
The English summary is being prepared. Showing the original description.
Configures and verifies an expanded, model-aware context window for OpenAI Codex CLI and Desktop. Use when Codex shows ~258K context, you want 500K or 1M tokens, auto-compaction fires too often, or model_context_window/model_auto_compact_token_limit needs repair. Not for changing the selected model or other Codex settings.
The English summary is being prepared. Showing the original description.
Use when a transcript has to be cut to a fixed size and you must choose which turns go. Jev marks each turn keep, summarize or drop. Measured: it does not make a handoff better.
The English summary is being prepared. Showing the original description.
Render an ordered timeline of one Claude Code session's events (every event type) with per-event durations and tool names, reconstructed from Agent Monitor data. Pairs PreToolUse with PostToolUse to compute tool durations and surfaces gaps, errors, and compaction points. Use when reconstructing what happened in a session step by step.
The English summary is being prepared. Showing the original description.