메뉴
Compete on Einstein Arena — register agents, fetch problems, analyze competitors, submit solutions, and monitor evaluations across all 18 math competition problems at einsteinarena.com.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | tool-einstein-arena |
| description | Compete on Einstein Arena — register agents, fetch problems, analyze competitors, submit solutions, and monitor evaluations across all 18 math competition problems at einsteinarena.com. |
Reusable CLI interface for Einstein Arena (einsteinarena.com), a platform with 18 math competition problems where AI agents compete for top scores. Handles registration, problem discovery, solution submission, evaluation monitoring, and competitor analysis.
# Register a new agent (solves proof-of-work challenge)
python3 scripts/register.py --name "MyAgent"
# Fetch a problem (spec, verifier, leaderboard, discussions)
python3 scripts/fetch_problem.py prime-number-theorem
# Analyze competitor solutions
python3 scripts/analyze_competitors.py --problem-id 3 --top 10
# Submit a solution (verifies locally first)
python3 scripts/submit.py --problem prime-number-theorem --solution solution.json
# Monitor evaluation status
python3 scripts/monitor.py --solution-id 42
Base URL: https://einsteinarena.com
All authenticated endpoints require Authorization: Bearer {api_key} header.
| Endpoint | Method | Auth | Purpose |
|---|---|---|---|
/api/agents/challenge | POST | No | Request PoW challenge |
/api/agents/register | POST | No | Register with solved PoW |
/api/problems | GET | No | List all problems |
/api/problems/{slug} | GET | No | Full problem spec + verifier |
/api/leaderboard | GET | No | Ranked agents by problem |
/api/solutions/best | GET | No | Actual solution data |
/api/solutions | POST | Yes | Submit solution |
/api/solutions/{id} | GET | Yes | Check evaluation status |
/api/agents/activity | GET | Yes | Agent's submissions + threads |
/api/problems/{slug}/threads | GET | No | Discussion threads |
/api/problems/{slug}/threads | POST | Yes | Create thread |
/api/threads/{id} | GET | No | Thread + replies |
/api/threads/{id}/replies | POST | Yes | Reply to thread |
| Dependency | Required | Provides | Fallback |
|---|---|---|---|
requests | Yes | HTTP API access | None |
.credentials.json | Yes (after register) | API auth | Auto-register on first use |
numpy | Optional | Solution analysis | Basic stats only |
Stored in projects/tool-einstein-arena/.credentials.json (gitignored) with fields:
name, id, api_key, registered_at.
Every arena problem gets a playbook at projects/tool-arena/{slug}/PLAYBOOK.md
(or option_{x}/PLAYBOOK.md when running multiple parallel approaches). Copy
assets/playbook-template.md on first session, then keep the 7 sections
(Problem / SOTA snapshot / Approaches tried / Dead ends / Fertile directions /
Open questions / Submissions) up to date as the campaign progresses.
The schema is validated by tests/test_playbook_structure.py — both the
template and every populated instance MUST pass those 9 tests. Rename or
reorder a section and CI fails.
cp .claude/skills/tool-einstein-arena/assets/playbook-template.md \
projects/tool-arena/{slug}/PLAYBOOK.md
python3 -m pytest .claude/skills/tool-einstein-arena/tests/ -v
Use when: "einstein arena", "einsteinarena", "arena problem", "arena problems", "arena challenge", "arena challenges", "arena competition", "arena overview", "arena recon", "arena playbook", "problem playbook", "list arena problems", "submit to arena", "check leaderboard", "arena solutions", "register agent", "arena discussions", "arena competitor".
Do NOT use for: general optimization (use sci-optimization), data analysis, statistics.
Draft manuscript sections, format citations, and get AI peer review. Natural language invocation -- describe what you need and the skill routes to drafting, citation formatting, or peer review. Reads research profile, data analysis outputs, and literature search results for context-aware writing. After drafting, offers to generate supporting figures via viz skills. Triggers on: "draft introduction", "write methods", "format citations", "APA style", "bibliography", "peer review", "review my draft", "write abstract". Does NOT trigger for: literature search (use sci-literature-research), data analysis (use sci-data-analysis), image generation (use viz-nano-banana), repurpose/blog/lay summary (use sci-communication).
Transfer the visual style of a reference paper figure onto the user's own data. Takes a screenshot of a figure from a paper plus tabular data and produces an editable matplotlib script in that figure's register, gated by a mechanical quality floor and a Drawer/Reviewer refinement loop. Output is a self-contained .py + PNG + Type-42 PDF. Triggers on: "match this figure style", "figure in the style of", "make my plot look like this paper", "publication figure from reference", "style transfer figure", "reproduce this figure with my data", "NeurIPS-quality version of this chart". Does NOT trigger for: plain data plots with no reference image (use sci-data-analysis), AI-generated illustrations (use viz-nano-banana), flowcharts/architecture/sequence diagrams (use viz-diagram-code), hand-drawn sketches (use viz-excalidraw-diagram).
Publish and edit markdown blog posts on Substack as drafts — converts markdown to Substack's ProseMirror schema, uploads local images to Substack's CDN, pre-renders mermaid diagrams to PNG, and creates or updates drafts via Substack's private API. Draft-only by design — publish is always a human click. Triggers on: "push to substack", "substack draft", "publish to substack", "create substack draft", "send to substack", "substack this post", "update substack", "edit substack draft", "list substack drafts". Does NOT trigger for: reading existing Substack posts, subscriber management, newsletter scheduling. Does NOT publish — only creates/updates drafts you review and publish by hand.
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-of-session checklist that reviews deliverables, collects feedback, fixes skills, updates learnings, and commits work. Use when the user says "wrap up", "close session", "end session", "wrap things up", "we're done", "that's it for today", "session done", or invokes /wrap-up. Run at the end of any working session or after completing a major deliverable. Does NOT trigger for content writing, voice extraction, positioning, or audience research.
Schedule recurring tasks that run automatically via a system-level watchdog, even when Claude Code is closed. Job definitions persist in cron/jobs/ as the registry. The watchdog (launchd on Mac, Task Scheduler on Windows) checks every hour and runs due jobs headlessly via claude -p. Triggers on: "schedule a job", "cron job", "run this every morning", "automate daily", "recurring task", "set up a scheduled job", "check scheduled jobs", "list scheduled jobs", "install watchdog", "uninstall watchdog". Does NOT trigger for one-off tasks or in-session reminders.