Search: "card"

Ramp Automation: manage corporate card transactions, reimbursements, users, and expense tracking via the Ramp platform

Operates Fictiv (app.fictiv.com), the on-demand manufacturing platform, end to end in the user's browser. Covers uploading CAD parts, configuring process, material, finish, threads, tolerances and inspections, getting instant or manual quotes, reading and fixing DFM feedback, choosing lead time and region, checking out and paying (card or PO), tracking orders, reordering, and troubleshooting. Applies when the user mentions Fictiv, wants a part CNC machined, 3D printed, sheet-metal fabricated, urethane cast, injection or compression molded, or die cast through an online service, asks to "get a quote" or "order parts" for a STEP/SLDPRT/STL file, wants to check a Fictiv quote or order status, or has a problem with a Fictiv upload, DFM warning, price or checkout. Also applies when the user wants custom parts manufactured and has a Fictiv account, even if Fictiv is not named.

Supports structured what-if scenario analysis for research planning, experimental contingencies, and scientific project decisions. Explores favorable, reference, adverse, wild-card, contrarian, and second-order scenarios with explicit assumptions, evidence, and decision triggers. Use to stress-test a research plan under uncertainty; scenario narratives do not estimate causal effects or calibrated forecast probabilities.

Converts genomic intervals between coordinate conventions, normalises and compares variant representations, and detects assembly or contig-naming mismatches before they corrupt an analysis. Used whenever coordinates cross a format, tool, or assembly boundary - converting between BED, GFF/GTF, VCF, SAM/BAM, WIG, PSL, genePred, Picard interval_list, or region strings; reconciling 0-based half-open with 1-based inclusive; left-aligning or trimming indels; checking whether two variant records describe the same change; mapping genomic to transcript, CDS, or protein positions; auditing a BED/GTF/VCF for convention violations; or diagnosing GRCh37 vs hg19 vs GRCh38 vs T2T, chr-prefix, and liftover problems. Triggers include "off by one", "0-based", "1-based", "half-open", "coordinate system", "left-align", "normalize variant", "bcftools norm", "chr prefix", "wrong genome build", "liftover", "REF mismatch", and "HGVS".

Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists. Use when reviewing workflow files that invoke AI coding agents, auditing CI/CD pipeline security for prompt injection risks, or evaluating agentic action configurations.

Systematic code maturity assessment using Trail of Bits' 9-category framework. Analyzes codebase for arithmetic safety, auditing practices, access controls, complexity, decentralization, documentation, MEV risks, low-level code, and testing, then produces a scorecard with evidence-based ratings and a priority-ordered roadmap. Use when assessing or scoring the maturity of a smart contract or blockchain codebase, producing a maturity scorecard or evaluation, or judging how mature, well-tested, or well-documented such a project is against a rubric.

Audit-grade multi-agent orchestration for CLI coding agents (Claude Code, Codex, Gemini CLI, +40 more). HMAC-chained audit log, signed agent cards, per-artefact lineage, air-gap deploy. The orchestrator your compliance team will sign off on. https://bernstein.run

Research your competitors and build an interactive battlecard. Outputs an HTML artifact with clickable competitor cards and a comparison matrix. Trigger with "competitive intel", "research competitors", "how do we compare to [competitor]", "battlecard for [competitor]", or "what's new with [competitor]".

Use this skill to prepare affiliate-mcp's find-users marketing in prepare-and-approve mode: the weekly branded LinkedIn card and post, directory and registry listing submissions, and free lead-magnet content. It applies the voice and ship-checks and queues everything as Buffer drafts; it never publishes or queues a live post. Trigger on: "prepare this week's launch post", "draft the marketing", "queue the weekly card", "prepare directory listings", "run the marketing loop".

Use this skill to render affiliate-mcp's branded, screenshot-ready social cards (1080x1080) for the weekly launch and other marketing, from the repo design system. It produces card assets for review; the numbers on a card must be real anonymised data or clearly a demo, never invented client data presented as real. Trigger on: "make the weekly card", "render the earnings card", "build a social card", "design the launch artifact".

Operating procedure for ChatGPT Ads through Adako, the MCP server and REST API that connects this assistant to Google Ads, Meta Ads, ChatGPT Ads, TikTok Ads and LinkedIn Ads. Use it whenever the user asks about ChatGPT Ads campaigns, ad groups, chat card ads, context hints, spend limits, geo targeting, measurement pixels or review verdicts on that platform, and whenever they ask to launch, pause, resume or edit a ChatGPT Ads campaign. It lists the 23 ChatGPT Ads tools by job, the chat card limits, the account and budget rules, and the order a launch is built in.

Copy limits, asset specs and the creative fatigue playbook for Adako, the MCP server and REST API that connects this assistant to Google Ads, Meta Ads, ChatGPT Ads, TikTok Ads and LinkedIn Ads. Use it whenever the user asks to write, review, resize or refresh ad copy, headlines, descriptions, primary text, chat cards or video and image assets for those platforms, asks why an ad was rejected or is underperforming, or asks whether a creative will fit. It carries the exact character counts and image and video specs per platform, the free validator tool for each, and what to do when click-through falls while frequency rises.