Loading...
Loading...
Found 1,911 Skills
Execute a comprehensive NestJS Project Health Audit. Analyzes tech stack, architecture, API design, data layer, testing, code quality, CI/CD, and documentation. Produces a Google Docs-ready report with section scores and weighted overall score. Use when the user asks to audit a NestJS project, run a health check, evaluate backend quality, or assess technical debt. Triggers on: 'nestjs audit', 'health audit', 'backend audit', 'nestjs health', 'node audit', 'api audit', 'project quality check'.
Solidity smart contract security: vulnerability prevention, secure coding patterns, gas-safe optimizations, and audit preparation. Use when writing or reviewing Solidity code for security, auditing contracts, preventing reentrancy/overflow/access-control issues, optimizing gas safely, or preparing contracts for professional audits. Keywords: solidity security, smart contract audit, reentrancy, access control, CEI pattern, front-running, slither, invariant, vulnerability, exploit, secure solidity.
Analyze wallet portfolios on supported blockchains: view token holdings with current values, track transaction activity and history, check PnL (profit and loss) statistics over different time windows, and query total wallet net worth. Also supports querying the authenticated user's own LiberFi TEE wallet portfolio without needing to provide a wallet address — use the `me` commands when the user wants to check their own LiberFi account's holdings, activity, stats, or net worth. Trigger words: wallet, portfolio, holdings, my tokens, my coins, my balance, what do I hold, what tokens do I have, wallet balance, wallet holdings, wallet activity, transaction history, recent transactions, transfers, swaps, trade history, wallet stats, PnL, profit and loss, profit, loss, gains, returns, performance, how much did I make, how much did I lose, win rate, net worth, total value, portfolio value, total balance, how much is my wallet, wallet overview, wallet summary, wallet analysis, check wallet, view wallet, my portfolio, account balance, my LiberFi wallet, my TEE wallet, my account portfolio, check my account, my holdings without address. Chinese: 钱包, 持仓, 我的代币, 我持有什么, 余额, 钱包余额, 交易记录, 交易历史, 最近交易, 转账记录, 钱包统计, 盈亏, 利润, 亏损, 收益, 收益率, 胜率, 净值, 总价值, 钱包总价值, 钱包概览, 钱包分析, 查看钱包, 我的LiberFi钱包, 我的TEE钱包, 我的账户持仓, 不知道地址查我的钱包. CRITICAL: Always use `--json` flag for structured output. CRITICAL: Public `wallet` commands require both chain and wallet address — always ask the user for these if not provided. CRITICAL: `me` commands do NOT require a wallet address — they use the authenticated user's TEE wallet automatically. They DO require authentication (run `lfi status` first, then `lfi login key` if needed). Do NOT use this skill for: - Token search, info, security audit, K-line → use liberfi-token - Trending tokens or new token rankings → use liberfi-market - Swap quotes, trade execution, or transaction broadcast → use liberfi-swap - Token holder analysis (for a specific token) → use liberfi-token Do NOT activate on vague inputs like "wallet" alone without a wallet address or clear intent to check portfolio data.
Review code changes adversarially using parallel review layers (Blind Hunter, Edge Case Hunter, Acceptance Auditor) with structured triage into actionable categories. Use when the user says "run code review" or "review this code"
Installs, configures, audits, and operates Agent Package Manager (APM) in repositories. Use when initializing apm.yml, installing or updating packages, validating manifests, managing lockfiles, compiling agent context, browsing MCP servers, setting up runtimes, or packaging resolved context for CI and team distribution. Don't use for writing a single skill by hand, generic package managers like npm or pip, or non-APM agent configuration systems.
Backlink profile analysis: referring domains, anchor text distribution, toxic link detection, competitor gap analysis. Requires DataForSEO extension. Use when user says "backlinks", "link profile", "referring domains", "anchor text", "toxic links", "link gap", "link building", "disavow", or "backlink audit".
Phase skill for evidence extraction, replay expectations, and audit of generated planning artifacts.
Guide the design and implementation of order lifecycle management in trading systems. Use when building an order state machine for an OMS or EMS, implementing or debugging FIX protocol connectivity to exchanges, handling cancel/replace race conditions, defining pre-submission validation rules (buying power, position limits, restricted lists), selecting order types and time-in-force instructions, designing multi-leg or OCO or bracket orders, building CAT-compliant audit trails, troubleshooting order rejections or unexpected state transitions, hardening an OMS against edge cases, or implementing order persistence and recovery for failover. Also covers FIX message flows, ClOrdID chaining, and partial fill aggregation.
When the user wants to build, audit, or standardize UTM parameters for Google Ads campaigns — generating UTM URLs, setting up naming conventions, using dynamic value insertion, choosing between auto-tagging and manual UTMs, or ensuring GA4 channel grouping works correctly. Triggers on 'UTM', 'UTM parameters', 'UTM generator', 'UTM builder', 'tracking URL', 'campaign tracking', 'auto-tagging', 'GCLID', 'UTM naming convention', 'GA4 source medium', 'utm_source utm_medium utm_campaign', 'build UTM links', or 'Google Ads tracking links'. For conversion action setup in Google Ads see google-ads-conversion-tracking.
Systematically audit, improve, and enforce test coverage in any repository. Use when asked to improve coverage, add missing tests, set up coverage thresholds, audit test gaps, or wire coverage into CI/hooks. Works across ecosystems (TypeScript, Python, Go, Rust, etc.). Composes with the hk skill for pre-commit enforcement. Triggers on: test coverage, missing tests, coverage threshold, coverage report, untested code, coverage gap, coverage audit.
Validate, lint, audit, or fix .gitlab-ci.yml pipelines, stages, and jobs.
Produces the script and structure for a personalised video audit outreach message — the primary client-acquisition tool for the results- first agency model. The consultant records a 3–5 minute screen-capture video (using Loom, Screencastify, or a WhatsApp voice note) reviewing a prospect's existing digital presence, naming 2–3 specific improvements, and ending with a soft invitation to discuss a risk-free test campaign. No cold calling. No generic email. Each video is personalised to one prospect and converts at approximately 1 paying client per 10 videos sent (Fihn, 2025). Invoke when prospecting for new clients, when following up on a referral, or when building a pipeline of warm prospects before presenting the biz-dev-beyond-agency-offer skill.