summarize
The summarize skill processes text-based content into structured summaries organized by key points, supporting details, and action items. Use this when users need to quickly extract essential information from long documents, conversations, articles, or meeting notes while maintaining factual accuracy and relevance to their goals.
git clone --depth 1 https://github.com/clawdotnet/openclaw.net /tmp/summarize && cp -r /tmp/summarize/src/OpenClaw.Gateway/skills/summarize ~/.claude/skills/summarizeSKILL.md
# Summarize When the user asks to summarize, condense, or get a digest of content, produce a structured summary. ## Format 1. **Key Points** — 3–5 bullet points of the most important information 2. **Details** — Brief expansion on each key point if the user needs more depth 3. **Action Items** — Any tasks, decisions, or follow-ups identified (omit if none) ## Guidelines - Keep summaries concise. Default to 3–5 key points unless the user asks for more. - Prioritize what matters to the user's stated goal. If the goal is unclear, ask before summarizing. - Preserve factual accuracy. Do not invent dates, names, numbers, or conclusions not present in the source. - When summarizing a conversation or thread, distinguish between facts, opinions, decisions, and open questions. - For long content, consider a two-pass approach: first extract the structure (sections, topics), then summarize each with appropriate depth.
Organizes repository documentation and keeps new docs in the correct location.
Produce a daily news brief (AI/security/dev) with links, key takeaways, and action items.
Connects to databases, runs SQL queries, and analyzes datasets using code to provide actionable business insights.
Conducts comprehensive web research, synthesizes data from multiple sources, and produces detailed reports.
Triage inbox into “needs reply”, “FYI”, “urgent”, and “safe to archive”, with a short plan for each.
Safely operate Home Assistant by resolving targets first and validating state before writes.
Safely interact with MQTT topics with allow/deny policies and minimal payload risk.
Operates as an autonomous software engineer, capable of writing code, running tests, and managing git repositories.