Yanyutin753
from GitHub
调研与分析
- 📁 agents/
- 📁 assets/
- 📁 eval-viewer/
- 📄 SKILL.md
Create new skills, modify and improve existing skills, and measure skill performance. TRIGGER when user says "create a skill", "new skill", "make a skill", "add a skill", "edit skill", "update skill", "run evals to test a skill", "benchmark skill performance", or describes wanting to add new capabilities to the AI assistant.
officebeats
from GitHub
调研与分析
Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.
serenorg
from GitHub
调研与分析
- 📁 scripts/
- 📄 .env.example
- 📄 .gitignore
- 📄 config.example.json
Alpaca-branded SaaS short trader with MCP-native execution: scores AI disruption risk, builds capped short baskets, and tracks paper/live PnL in SerenDB.
botlearn-ai
from GitHub
调研与分析
- 📁 knowledge/
- 📁 strategies/
- 📁 tests/
- 📄 manifest.json
- 📄 package.json
- 📄 README.md
- "find papers"
- 📁 references/
- 📄 README.md
- 📄 SKILL.md
Conduct comprehensive, multi-source research on any topic using the 7-phase Deep Research protocol with Graph of Thoughts. Use when user needs thorough research with verified claims, citations, and source triangulation. Triggers on "deep research [topic]", "research [topic] thoroughly", "I need comprehensive research on...", or "investigate [topic]".
DmitriyYukhanov
from GitHub
调研与分析
Set up and orchestrate Claude Code agent teams - multiple Claude Code instances working together with shared tasks, inter-agent messaging, and centralized management. Use when the user wants to (1) create or start an agent team for parallel work, (2) configure agent team settings like display mode or teammate mode or permissions, (3) coordinate teammates for code review or debugging or feature development or research, (4) understand when to use agent teams vs subagents, (5) troubleshoot agent team issues. Triggers include mentions of "agent team", "team of agents", "parallel agents", "teammates", "split pane", "tmux teammates", "delegate mode", "spawn teammates", or wanting multiple Claude instances collaborating. --- # Agent Teams Coordinate multiple Claude Code instances working together. One session acts as team lead, spawning and coordinating teammates that work independently in their own context windows and communicate directly with each other. ## Quick Setup ### 1. Enable the feature (experimental, disabled by default) Add to `settings.json`: ```json { "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" } } ```
brumaombra
from GitHub
调研与分析
Researches a topic on the web and produces a structured, well-cited report with key findings and source references.
QuantumBFS
from GitHub
调研与分析
Use when brainstorming research ideas — a research collaborator that understands your background, helps find interesting problems together, and shares relevant resources along the way
- 📁 references/
- 📄 references
- 📄 SKILL.md
Analyze stocks and companies using financial market data. Get company profiles, technical insights, price charts, insider holdings, and SEC filings for comprehensive stock research.
- 📁 references/
- 📄 references
- 📄 SKILL.md
Analyze stocks and companies using financial market data. Get company profiles, technical insights, price charts, insider holdings, and SEC filings for comprehensive stock research.