Create a delightful, unexpected "wow" experience for the user by dynamically discovering and creatively combining other enabled skills. Triggers when the user says "surprise me" or any request expressing a desire for an unexpected creative showcase. Also triggers when the user is bored, wants inspiration, or asks for "something interesting".
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 .
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:
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
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
Personalized artifact: Use known user context to create something personal and delightful
Step 4: Execute
Read the full SKILL.md body of each selected skill
Follow each skill's instructions for technical execution
Combine outputs into one cohesive deliverable
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.
Good reveal: "I made you something ✨" + [the artifact]
Bad reveal: "I decided to combine the pptx skill with the canvas-design skill to create a presentation about..." (kills the surprise)
Evaluate and carry out non-trivial software-system changes from first principles. Use when assessing RFCs, issues, designs, features, refactors, migrations, dependency changes, or proposed fields, events, APIs, modules, and services whose need, consumers, system fit, validation, or rollback require scrutiny. Read the actual system, identify the concrete problem and named semantic consumers, choose the smallest sufficient solution, reject pseudo-requirements and speculative abstractions, and require evidence proportional to risk. Do not use for mechanical edits, source-code explanation, or a dedicated review of an already-complete diff.
Reviews DeerFlow skill packages for readiness, triggers, safety boundaries, resources, and evidence. Invoke when users ask to audit, grade, or production-check an existing skill.
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.
End-to-end smoke test skill for DeerFlow. Guides through: 1) Pulling latest code, 2) Docker OR Local installation and deployment (user preference, default to Local if Docker network issues), 3) Service availability verification, 4) Health check, 5) Final test report. Use when the user says "run smoke test", "smoke test deployment", "verify installation", "test service availability", "end-to-end test", or similar.
Use when a DeerFlow maintainer needs comment-only GitHub issue or PR handling: resolve issue/PR scopes with gh, analyze issues, post or draft issue comments, perform PR review comments, review PR or issue batches, compare competing PRs that target the same issue, give fix strategy, risk classification, and validation guidance. Intended for maintainers and trusted local agents, not general contributors.
Ensure async-path backend code that could block the asyncio event loop is protected by a teeth-verified runtime anchor in tests/blocking_io/. Use when changing backend Python under app/, packages/harness/deerflow/, or scripts/, when running a blocking-IO triage round over the whole repo, or when a reviewer/CI asks for blocking-IO coverage. Runs a deterministic scan (changed-lines or full-repo), routes each candidate, drafts/extends an anchor, and proves it fails when the blocking IO regresses.
Use this skill when the user requests to review, analyze, critique, or summarize academic papers, research articles, preprints, or scientific publications. Supports comprehensive structured reviews covering methodology assessment, contribution evaluation, literature positioning, and constructive feedback generation. Trigger on queries involving paper URLs, uploaded PDFs, arXiv links, or requests like "review this paper", "analyze this research", "summarize this study", or "write a peer review".
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.
Use this skill when the user requests to generate, create, or make presentations (PPT/PPTX). Creates visually rich slides by generating images for each slide and composing them into a PowerPoint file.
