agentleFS
zhouguoqingzhouguoqing/QianYuan.AIAgenticFramework/.agents/skills/summarize/SKILL.md

summarize

Skill35 starsChanged 6 months agoApache-2.0View on GitHub

Use the steipete/summarize CLI to summarize URLs, local files, stdin, YouTube links, podcasts, and media with LLM models. Use when installing or running summarize, configuring provider/API keys, tuning length/language/json/extract/slides flags, setting ~/.summarize/config.json defaults, or troubleshooting CLI errors.

98 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use openclaw-performance, plugin-sdk-impact and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • clawdbotSkill

    openclaw-performance

    Performance work in OpenClaw: a slow or heavy flow (latency, CPU, memory, SQL, RPC, renders), writing or reviewing a perf PR, or adding a cache. Count the work, delete waste first, cache last.

    Also in 7 projects that use this

  • clawdbotSkill

    plugin-sdk-impact

    Count Plugin SDK consumers across live ClawHub releases and bundled OpenClaw plugins before deprecation, removal, or behavior changes; supports public release-date filters.

    Also in 7 projects that use this

  • AtomicBot-aiSkill

    taskflow-inbox-triage

    Also in 6 projects that use this

  • hkyutongSkill

    node-connect

    Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when QR/setup code/manual connect fails, local Wi-Fi works but VPS/tailnet does not, or errors mention pairing required, unauthorized, bootstrap token invalid or expired, gateway.bind, gateway.remote.url, Tailscale, or plugins.entries.device-pair.config.publicUrl.

    Also in 18 projects that use this

  • molt-botSkill

    discord-e2e

    Test Discord with Convex-leased QA bots: check credentials without a Gateway, exercise owned messages, or prove OpenClaw replies, files, threads, reactions, streaming, and typing. Distinguish API and Gateway evidence from manual user interactions.

    Also in 10 projects that use this

  • molt-botSkill

    openclaw-repair-sweep

    Run scoped OpenClaw issue/PR repair campaigns: coordinate workers, prove root causes, and land or close verified work under the requested authority.

    Also in 10 projects that use this

  • +2 more from molt-bot

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 4 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 86 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill to run summarize effectively in terminal workflows.

    line 8
  2. Very specific:

    Run a minimal real command first (summarize "<input>").

    line 14
  3. Distinctive:

    Add flags incrementally only after a baseline run succeeds.

    line 16
  4. Very specific:

    If it fails, re-run with --verbose or --json before changing multiple variables.

    line 17
  5. Very specific:

    Prefer explicit --model on task-critical runs.

    line 32
  6. Very specific:

    Use ~/.summarize/config.json for stable defaults.

    line 33
  7. Very specific:

    Use --json to inspect extraction and metric fields.

    line 46
  8. Distinctive:

    Do not include full repository-level documentation unless explicitly requested.

    line 51
  9. Distinctive:

    Use references/cli.md only for deeper flag/provider details.

    line 52
  10. Distinctive:

    Read references/cli.md for install commands, provider keys, advanced flags, and error-specific guidance.

    line 56

“Common” is measured: kept by at least 6 in 10 of the 86 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Summarize CLI

Use this skill to run summarize effectively in terminal workflows. Focus on practical usage and command execution, not broad project background.

Workflow

  1. Confirm input type and desired output format.
  2. Run a minimal real command first (summarize "<input>").
  3. Select a model/provider and ensure matching API credentials.
  4. Add flags incrementally only after a baseline run succeeds.
  5. If it fails, re-run with --verbose or --json before changing multiple variables.

Quick Patterns

  • Summarize a URL: summarize "https://example.com"
  • Summarize a local file: summarize "/path/to/file.pdf"
  • Summarize piped input: cat notes.md | summarize -
  • Summarize YouTube/media URL: summarize "https://youtube.com/watch?v=..."
  • Force model/provider: summarize "https://example.com" --model openai/gpt-5-mini
  • Control length: summarize "https://example.com" --length long
  • Return diagnostics JSON: summarize "https://example.com" --json
  • Extract content without summarizing: summarize "https://example.com" --extract --format md

Configuration Rules

  • Prefer explicit --model on task-critical runs.
  • Use ~/.summarize/config.json for stable defaults.
  • Remember precedence for model selection:
    1. --model
    2. SUMMARIZE_MODEL
    3. ~/.summarize/config.json
    4. built-in default (auto)

Troubleshooting Flow

  1. Re-run with --verbose.
  2. Confirm API key matches the chosen provider/model.
  3. Switch to a known-good model (for example openai/gpt-5-mini or google/gemini-3-flash-preview).
  4. For media or YouTube failures, verify external dependencies (yt-dlp, ffmpeg, optionally tesseract).
  5. Use --json to inspect extraction and metric fields.

Scope

  • Prioritize how to run commands and fix concrete failures.
  • Do not include full repository-level documentation unless explicitly requested.
  • Use references/cli.md only for deeper flag/provider details.

References

Read references/cli.md for install commands, provider keys, advanced flags, and error-specific guidance.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.