Connect an AI agent to 37Soul to browse its feed, post tweets, and reply to messages that genuinely resonate. A local log records reactions and interests over time, helping the agent reflect on its social personality.
- Browsing the 37Soul feed
- Replying to a post that resonates
- Sharing a thought on 37Soul
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 1, 2026
Turn text, documents, or a reference image into presentation slides with the 2slides API. Choose a theme, language, and generation mode, then get online slides and a PDF; completed decks can also receive narration or image exports.
- Making slides from notes or an outline
- Summarizing a document as a presentation
- Matching slides to a reference image
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 1, 2026
Review a codebase against the 12-Factor App principles for SaaS architecture. Get a factor-by-factor Strong, Partial, or Weak assessment, evidence and gaps, plus prioritized recommendations for improving portability, deployment, and scaling.
- Auditing a SaaS application's architecture
- Reviewing a cloud-native application
- Planning a cloud migration
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 1, 2026
Improve the chances that your content is cited in AI-generated answers. Review where your brand appears, compare citation patterns, and identify ways to make pages clearer, more authoritative, and easier for AI systems to extract.
- Checking whether your brand appears in AI answers
- Finding why competitors get cited instead
- Improving pages for AI answer extraction
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 1, 2026
Plan SaaS retention work to address both customer-initiated cancellations and failed payments. Design cancellation surveys and tailored save offers, outline payment recovery and proactive outreach, and choose metrics for evaluating retention experiments and results.
- Designing a cancellation flow with a brief exit survey
- Matching save offers to customers' cancellation reasons
- Planning retries and emails for failed subscription payments
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 1, 2026
Query historical and current crypto market data for Hyperliquid, Lighter.xyz, and HIP-3, including prices, candles, order books, trades, funding rates, open interest, and liquidations. Check data freshness and coverage to understand what records are available.
- Looking up historical prices or candles for a supported exchange
- Reviewing order book or trade history
- Checking funding rates and open interest over time
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 1, 2026
Record command failures, user corrections, missing feature requests, outdated knowledge, and better approaches in structured Markdown logs. Review those notes before major tasks, resolve or promote useful entries, and turn recurring lessons into reusable guidance or skills.
- Log an unexpected command or tool failure
- Save a user correction for future work
- Track a requested capability the agent lacks
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 1, 2026
Estimate intracellular reaction rates from steady-state carbon-13 tracing measurements. Validate carbon atom mappings and measurement inputs, simulate labeling, fit constrained fluxes, and diagnose which pathway rates the data can meaningfully constrain.
- Estimate metabolic fluxes from carbon-13 labeling
- Validate atom mappings and measurement inputs
- Simulate labeling for proposed reaction rates
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 1, 2026
Convert a 1688 product into Ozon-ready listing data, including category and attribute mapping, Russian text and image translation, upload, and status checks. The workflow uses Ozon’s official API and requires Ozon credentials plus AlphaShop keys for image translation.
- Listing a 1688 product on Ozon
- Mapping product categories and required attributes
- Translating product images for a Russian listing
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 1, 2026
Learn how to source products through 1688.com with guided steps for choosing products, checking suppliers, requesting samples, negotiating prices, and comparing shipping options. The skill also highlights common listing and payment risks and explains when an order may call for help from a sourcing expert.
- Checking a 1688 supplier before placing an order
- Planning product selection for a target market and budget
- Drafting a supplier message to negotiate price or samples
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 1, 2026
Set up and use the 1Password command-line tool `op` to sign in, verify account access, and work with vault data. The skill covers single or multiple accounts and shows how to run commands or fill templates with secrets while limiting exposure in logs and files.
- Set up the `op` command-line tool
- Sign in and verify access to an account
- Run a command with vault secrets
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 1, 2026
Connect an AI agent to the 2020117 network to publish posts, discover or offer services, and exchange tasks such as text generation, translation, and summarization. The skill also covers Lightning payments, Nostr tips, and reputation signals for agent-to-agent work.
- Registering an agent and posting to its timeline
- Offering translation or summarization as a service
- Requesting a text generation job from another agent
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 1, 2026
Review an agent skill or shared code before installation by checking for risky commands, sensitive data access, network behavior, persistence, and dependency concerns. It combines a checklist with shell and Node.js scanners to produce findings and a risk-based verdict.
- Reviewing a skill before installing it
- Auditing code shared by another agent
- Checking installed skills during a periodic review
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 1, 2026
Connect an agent to a shared knowledge base for searching prior solutions before debugging or making architecture choices, then submitting non-trivial fixes for others. For projects on Base and related crypto technologies, it can also request architecture guidance, project reviews, and grant recommendations from an AI mentor.
- Searching for known fixes before debugging
- Sharing a non-obvious bug solution with other agents
- Getting architecture input for a Base project
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 1, 2026
Finds and verifies Aavegotchi GBM auctions on Base, then guides listing, bidding, cancellation, and claiming through Foundry cast. It checks auction data against the blockchain and defaults to simulation; transactions are broadcast only when explicitly instructed.
- Browse active Aavegotchi GBM auctions
- Simulate a bid after checking the current highest bid
- Prepare an NFT auction listing
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 1, 2026
Use this skill to prioritize and plan A/B tests for pages, emails, signup flows, and other digital experiences. It turns test ideas into a practical plan with a hypothesis, success and guardrail metrics, estimated sample size, duration, audience, and implementation notes.
- Prioritizing a backlog of test ideas
- Writing an evidence-based test hypothesis
- Estimating sample size and test duration
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 1, 2026
Plan experiments by defining a specific hypothesis, variants, primary and guardrail metrics, traffic allocation, and sample size before launch. The skill also provides guidance for running and interpreting results so teams can avoid premature conclusions and document decisions and learnings.
- Planning a website A/B test
- Writing a measurable experiment hypothesis
- Choosing primary and guardrail metrics
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 1, 2026
Build Apache Airflow workflows for data pipelines and scheduled jobs. The skill guides task dependencies, retries, waiting for conditions, testing, and deployment, with patterns for tasks that can be safely rerun.
- Building scheduled data pipelines
- Designing task order and dependencies
- Implementing custom tasks and condition checks
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 5, 2026
Resume a paused autoresearch experiment by checking its branch, configuration, strategy, results, and recent commits. Summarize the current metric, experiment outcomes, and observed patterns, then let the user choose how to continue.
- Resuming an experiment after a pause
- Reviewing kept, discarded, and failed attempts
- Summarizing the best metric and recent patterns
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 5, 2026
Build and review interfaces against WCAG 2.2 accessibility guidelines. Covers keyboard navigation, screen readers that read interface content aloud, accessible forms, mobile support, and display preferences, helping identify and fix barriers to using a website or app.
- Audit an interface for accessibility issues
- Add keyboard navigation and focus management
- Improve screen reader support for forms
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 5, 2026
Run one autoresearch experiment at a time. Review prior results, make a single targeted code change, commit it, and evaluate the outcome to decide whether to keep or revert it, without changing the evaluator or adding dependencies.
- Trying one measured code optimization
- Evaluating a single change against experiment history
- Keeping or reverting a performance experiment
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 5, 2026
Schedule an autoresearch experiment to run every 10 minutes, hourly, daily, weekly, or monthly. The skill creates a recurring CronCreate job that makes one change per run, evaluates it, records results, and can stop the loop on request.
- Scheduling an autoresearch experiment to run repeatedly
- Choosing an interval from 10 minutes to monthly
- Stopping an active experiment loop
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 4, 2026
Review AI-generated code for problems hidden behind successful runs. Check failure handling, resource cleanup, unusual inputs, nonexistent dependencies, and departures from project conventions to identify missing safeguards before merging or accepting the work as complete.
- Audit code after an AI generation session
- Review an AI-generated pull request before merging
- Investigate brittle code that appears to work
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 4, 2026
Compare repeated agent evaluation trials before shipping changes to an agent, prompt, model, or tool. The skill checks tool-call paths, identifies flaky cases, and uses paired statistical tests to pass, warn, or block a candidate against a baseline.
- Checking an agent change against a baseline before release
- Finding cases that pass inconsistently across repeated trials
- Checking whether required or forbidden tool calls occurred
LeoYeAI/agent-master-skills☆ 2.2KUpdated Nov 4, 2026