Agent skill

Summarize

by clawdotnet in clawdotnet/openclaw.net

Summarize, condense, or digest content into structured key points, details, and action items.

MITAuto-check passed

Install Summarize

skills CLI
$ npx skills add clawdotnet/openclaw.net --skill summarize -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install clawdotnet/openclaw.net summarize --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/clawdotnet/openclaw.net.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/OpenClaw.Gateway/skills/summarize .claude/skills/summarize && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
summarize
GitHub stars
520
Token cost
~302 tokens
SKILL.md length
136 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Summarize, condense, or digest content into structured key points, details, and action items.

  • Works in 3 steps: Key Points — 3–5 bullet points of the… → Details — Brief expansion on each key… → Action Items — Any tasks, decisions, or…
  • SKILL.md covers Format and Guidelines
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Summarize is an agent skill from clawdotnet/openclaw.net. Summarize, condense, or digest content into structured key points, details, and action items.

Its SKILL.md is about 300 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Self-hosted Enterprise and Personal AI + agent runtime in .NET (NativeAOT-friendly). The licence is MIT.

Example prompts

  • “/summarize”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  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)

What it can do on your machine

Read from SKILL.md and the folder at commit 2344435. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Summarize loads about 302 tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 136 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~26
When it runs · the whole SKILL.md, loaded when a task matches
~302

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from clawdotnet/openclaw.net at commit 2344435, republished under its MIT licence (© clawdotnet). 136 words, ~302 tokens.

Download SKILL.mdSave it as .claude/skills/summarize/SKILL.md (or your agent's skills folder).
name
summarize
description
Summarize, condense, or digest content into structured key points, details, and action items.
triggers
summarize, condense, digest, tldr, summary, 总结, 摘要, 概括
provenance.origin
openclaw.net
provenance.license
MIT

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.

© clawdotnet, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in src/OpenClaw.Gateway/skills/summarize of clawdotnet/openclaw.net.

Open the folder on GitHubat commit 2344435

Compare with similar skills

Summarize next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Summarize compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Summarize this skillclawdotnet/openclaw.net520—~302Automated safety check: PassMIT
Summarizeopenclaw/openclaw392k1 repos~531Automated safety check: PassMIT
Research Summarizeralirezarezvani/claude-skills28k2 repos~2.7kAutomated safety check: PassMIT
Weekly Project Digeststhedotmack/claude-mem98k—~3.5kAutomated safety check: PassApache-2.0
Summarizerholaboss-ai/holaOS11k—~615Automated safety check: PassCustom licence
Collection Digestoutline/outline41k—~498Automated safety check: PassCustom licence

Similar skills

  • Summarize

    openclaw/openclaw

    Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.

    392k GitHub starsUsed in 1 repo~531 tokens
    Media & CreativeAuto-check passed
  • Research Summarizer

    alirezarezvani/claude-skills

    Structured research summarization agent skill for non-dev users.

    28k GitHub starsUsed in 2 repos~2.7k tokens
    Research & ScienceAuto-check passed
  • Weekly Project Digests

    thedotmack/claude-mem

    Turns a project's claude-mem timeline into a week-by-week narrative, splitting it by ISO week and running one subagent per week that receives the prior week's carry-forward block.

    98k GitHub stars~3.5k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Summarizer

    holaboss-ai/holaOS

    Condense long articles, reports, and documents into clear, concise summaries.

    11k GitHub stars~615 tokensUpdated 1 mo ago
    Auto-check passed
  • Collection Digest

    outline/outline

    Summarize what changed in an Outline collection since a date; use when the user asks what is new, what was updated, or wants a digest of recent documents.

    41k GitHub stars~498 tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Hacker News Summarizer

    ykdojo/claude-code-tips

    Fetches Hacker News top stories, a chosen story with its comment thread and the linked article through the official APIs, then summarizes them.

    10k GitHub stars~942 tokensUpdated 13 days ago
    Writing & ContentAuto-check passed

More from clawdotnet/openclaw.net

All 12 skills in this repo
  • History Explorer

    clawdotnet/openclaw.net

    Inspect recent session conversation turns and meta-run history.

    520 GitHub stars~805 tokensUpdated 4 days ago
    Auto-check passed
  • Meta Skill Creator

    clawdotnet/openclaw.net

    Use this meta-skill instead of answering directly only when the current user explicitly asks to create, compose, synthesize, or propose a new meta-skill that orchestrates multiple existing skills.

    520 GitHub stars~4.8k tokensUpdated 4 days ago
    Auto-check passed
  • Community Research Insight

    clawdotnet/openclaw.net

    Extract structured insight briefs from community research transcripts or notes.

    520 GitHub stars~3k tokensUpdated 4 days ago
    Auto-check passed
  • Docs Governance

    clawdotnet/openclaw.net

    Organizes repository documentation and keeps new docs in the correct location.

    520 GitHub stars~441 tokensUpdated 4 days ago
    Auto-check passed
  • Daily News Digest

    clawdotnet/openclaw.net

    Produce a daily news brief (AI/security/dev) with links, key takeaways, and action items.

    520 GitHub stars~211 tokensUpdated 4 days ago
    Auto-check passed
  • Data Analyst

    clawdotnet/openclaw.net

    Connects to databases, runs SQL queries, and analyzes datasets using code to provide actionable business insights.

    520 GitHub stars~291 tokensUpdated 4 days ago
    Auto-check passed

Questions about Summarize

What does Summarize do?

Summarize, condense, or digest content into structured key points, details, and action items. net. Summarize, condense, or digest content into structured key points, details, and action items.

How do I install Summarize in Claude Code?

Run `npx skills add clawdotnet/openclaw.net --skill summarize -a claude-code`. Or copy the skill folder (src/OpenClaw.Gateway/skills/summarize in clawdotnet/openclaw.net) into .claude/skills/summarize in your project. Claude Code loads it when a task matches its description.

How do I install Summarize in Codex?

Run `npx skills add clawdotnet/openclaw.net --skill summarize -a codex`. Or copy the skill folder (src/OpenClaw.Gateway/skills/summarize in clawdotnet/openclaw.net) into .agents/skills/summarize in your project. Codex loads it when a task matches its description.

Can I use Summarize in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add clawdotnet/openclaw.net --skill summarize -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/summarize, .gemini/skills/summarize, .github/skills/summarize and .opencode/skills/summarize in your project.

What does Summarize need to run?

SKILL.md names no scripts, command-line tools or credentials: Summarize is instructions for the agent only.

Does Summarize access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Summarize safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Summarize use?

Summarize is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Summarize use?

About 302 tokens (SKILL.md is roughly 1.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Summarize?

Skills that share tags, products or a category with Summarize: Summarize (openclaw/openclaw, 392k stars), Research Summarizer (alirezarezvani/claude-skills, 28k stars), Weekly Project Digests (thedotmack/claude-mem, 98k stars) and Summarizer (holaboss-ai/holaOS, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Summarize?

clawdotnet (a GitHub organization) maintains it in clawdotnet/openclaw.net, which has 520 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 3, 2026.

Source: clawdotnet/openclaw.net on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.