surprise-me

A creative workflow that combines available agent skills into one unexpected experience.

In plain words
What is it for?
It is for responding to requests such as “surprise me,” finding suitable skills, and combining one to three of them into a single creative deliverable.
Why use it?
It helps turn a vague request for inspiration or a memorable demonstration into a cohesive result using the tools that are available.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/bytedance/deer-flow/surprise-me
Any agent
npx skills add bytedance/deer-flow --skill surprise-me
Clone the repo
git clone --depth 1 https://github.com/bytedance/deer-flow

Made for: Claude Code, Codex.

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 549 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00067 $0.00549
Opus 5 $0.00034 $0.00275
Sonnet 5 $0.00013 $0.00110
Haiku 4.5 $0.00007 $0.00055

Measured yesterday against content hash e93e72ca445d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

surprise-me scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

6 near-identical copies found in the catalogue:

skills/public/surprise-me/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Surprise Me

Deliver an unexpected, delightful experience by dynamically discovering available skills and combining them creatively.

Workflow

Step 1: Discover Available Skills

Read all the skills listed in the <available_skills>.

Step 2: Plan the Surprise

Select 1 to 3 skills and design a creative mashup. The goal is a single cohesive deliverable, not separate demos.

Creative combination principles:

  • Juxtapose skills in unexpected ways (e.g., a presentation about algorithmic art, a research report turned into a slide deck, a styled doc with canvas-designed illustrations)
  • Incorporate the user's known interests/context from memory if available
  • Prioritize visual impact and emotional delight over information density
  • The output should feel like a gift — polished, surprising, and fun

Theme ideas (pick or remix):

  • Something tied to today's date, season, or trending news
  • A mini creative project the user never asked for but would love
  • A playful "what if" concept
  • An aesthetic artifact combining data + design
  • A fun interactive HTML/React experience

Step 3: Fallback — No Other Skills Available

If no other skills are discovered (only surprise-me exists), use one of these fallbacks:

  1. News-based surprise: Search today's news for a fascinating story, then create a beautifully designed HTML artifact presenting it in a visually striking way
  2. Interactive HTML experience: Build a creative single-page web experience — generative art, a mini-game, a visual poem, an animated infographic, or an interactive story
  3. Personalized artifact: Use known user context to create something personal and delightful

Step 4: Execute

  1. Read the full SKILL.md body of each selected skill
  2. Follow each skill's instructions for technical execution
  3. Combine outputs into one cohesive deliverable
  4. Present the result with minimal preamble — let the work speak for itself

Step 5: Reveal

Present the surprise with minimal spoilers. A short teaser line, then the artifact.

Read the full file on GitHub · 54 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 54 lines · 67 tokens per session scan A e93e72ca445d

Subscribe to this mod's changes

surprise-me is a skill published in the GitHub repository bytedance/deer-flow (81,129 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 549 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

fullstack455/deer-flow · 64 tokens

github-deep-research

Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces structured markdown reports with executive summaries, chronological timelines, metrics analysis, and Mermaid diagrams.…

fullstack455/deer-flow · 68 tokens

claude-to-deerflow

Interact with DeerFlow AI agent platform via its HTTP API. Use this skill when the user wants to send messages or questions to DeerFlow for research/analysis, start a DeerFlow conversation thread, check DeerFlow status or health, list available models/skills/agents in DeerFlow, manage DeerFlow memory, upload files to…

fullstack455/deer-flow · 111 tokens

video-generation

Use this skill when the user requests to generate, create, or imagine videos. Supports structured prompts and reference image for guided generation.

fullstack455/deer-flow · 29 tokens

chart-visualization

This skill should be used when the user wants to visualize data. It intelligently selects the most suitable chart type from 26 available options, extracts parameters based on detailed specifications, and generates a chart image using a JavaScript script.

fullstack455/deer-flow · 50 tokens

consulting-analysis

Use this skill when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial analysis, industry research, competitive intelligence, investment due diligence, or any consulting-grade analytical report. This…

fullstack455/deer-flow · 110 tokens