Loading...
Loading...
Found 4,131 Skills
Threat Stack integration. Manage data, records, and automate workflows. Use when the user wants to interact with Threat Stack data.
Triage and audit IDA binaries. Use when asked to analyze a binary, find suspicious behavior, detect crypto/network activity, review decompiled code against source, or run multi-table queries.
Design, audit, and refactor production-safe agentic harnesses with provider-neutral best practices for tools, permissions, planning, context, and observability.
Review .NET changes for bugs, regressions, architectural drift, missing tests, incorrect async or disposal behavior, and platform-specific pitfalls before you approve or merge them. USE FOR: reviewing a pull request or patch in a .NET repository; checking for behavioral regressions, API misuse, or missing tests; auditing architectural or framework-specific. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
Use when examining a confirmed code, pull request, module, application, endpoint, dependency, or configuration scope for vulnerabilities, unsafe behavior, or exploitability.
Audit a pnpm 10+ workspace for configuration and monorepo problems: dependency placement, workspace protocol usage, hoisting, catalog configuration, build order and build hooks, dependency rules, and .npmrc settings that are now defaults. Reads and reports only.
Convert a token name into a vetted, sized buy order. Two capabilities are exclusive to this skill: resolving a token name or symbol to the correct contract among its copycats, and sizing an order — including amount, slippage, gas fees, and position sizing. No other sibling skill performs either of these functions. USE THIS SKILL when preparing to place a buy order, which may involve a token name/symbol, a purchase amount, or both — including straightforward requests with no mention of verification: "I want to buy 200U worth of PENGU", "Help me buy $500 of BONK", "Buy 1 SOL worth of WIF", "Help me buy some dogwifhat", "I want to go all-in with 100U on XX", "Can I buy PENGU now?", "Is PENGU a good buy?", "Should I dive in?", "Is it worth entering?", "Make sure it's the official token not a copycat before buying", "Buy me $500 of PENGU" — and also applies when a contract address is provided along with a purchase amount. DO NOT USE THIS SKILL for a standalone contract address with no name to resolve and no amount to size (e.g., "Can I buy this token?", "Rate this token", "Due diligence", "Is it a honeypot?", "Rug check", "Is this token safe"): such requests belong to gmgn-contract-dd, the skill that returns a 0-100 safety score. This skill never calculates its own safety verdict — it CALLS gmgn-contract-dd and defers to its judgment — so handling such requests would only result in an unwanted order card for the user. Return to this skill once the user specifies an amount. Buy-related questions about a token launcher instead of the token itself — e.g., "Should I buy this dev's new token?", "Is their next token worth investing in?", "Should I buy his next launch?", "Will this dev rug pull at launch?" — fall under gmgn-dev-score, which evaluates the creator's track record; since there's no token name to resolve or amount to size yet, this skill doesn't apply. Return to this skill once the user names the specific token. Mentioning a token without any buy intent falls under gmgn-market search. gmgn-swap is the endpoint of this skill, not a competitor: gmgn-swap signs and submits transactions, while this skill never touches private keys or places orders. A basic buy request starts HERE and only proceeds to gmgn-swap after the user confirms the order card. Note that gmgn-swap cannot start from a token name either — its --output-token requires a contract address, and it only resolves the currency names SOL/BNB/ETH/USDC — so requests like "Help me buy some dogwifhat" must be handled by this skill regardless of context. Go directly to gmgn-swap only when the user explicitly requests to skip pre-buy checks (e.g., "Skip the checks", "Buy directly", "No due diligence needed", "I'm in a hurry"), or for functions this skill doesn't cover: selling, percentage-based sells, limit orders, stop loss, take profit, trailing orders, multi-wallet batch trading, order status checks, and gas price lookups. The division is based on what the request still requires, not who executes it: if a name needs resolving or an amount needs sizing, start here; if a standalone address only needs a safety verdict, use gmgn-contract-dd; if a signed transaction is needed, it's always gmgn-swap's responsibility.
Use when auditing or improving any frontend codebase against the full Front-End Checklist rule corpus through one entry point.
Finding validation before writing any report — 7-Question Gate (all 7 questions), 4 pre-submission gates, always-rejected list, conditionally valid with chain table, CVSS 3.1 quick reference, severity decision guide, report title formula, 60-second pre-submit checklist. Use BEFORE writing any report. One wrong answer = kill the finding and move on. Saves N/A ratio.
Red-team operator discipline — the mindset corrections that separate offensive testing from defensive WAPT. Built from authorized red-team work where conservative defaults caused multiple findings to be missed and one to be incorrectly retracted. Use at the START of any red-team engagement and again whenever feeling stuck or considering "stopping" on a defended target. The single most important skill to load when scope is "external red team" not "bug bounty / WAPT".
SentinelOne Singularity detection engineering — explicit distinction from Microsoft Sentinel, surface map across STAR Custom Logic (sensor-side behavioural rules), Deep Visibility (DVQL), Singularity Data Lake / PowerQuery (SDL alert configuration, scheduled queries, geo/math functions), exclusions and policies, Storyline ID-based correlation, AI Engine policy modes (detect / protect), SIEM ingestion patterns, and entity alignment for cross-platform correlation. Distilled from Sentinel-One/ai-siem community detection library. Use for sentinel_one-keyed configurations in OpenTide MDR objects — never confuse with microsoft-sentinel.
Use when inspecting or changing anything in a Cloudflare account as an agent - DNS records, WAF custom rules, bot settings, redirect, transform, cache or page rules, zone settings, tunnels, Workers, Pages, R2 or analytics. Reads go through a local read-only API token that the agent never sees. Changes are proposed for the human to make in the dashboard, or applied through an approval step when the user has deliberately stored a write token.