AI skill directory

Scans a research repository and drafts a README-first reproduction plan before coding.

Requests a thorough code review when finishing features or before merge to verify requirements.

Runs structured engineering research—options, tradeoffs, and evidence—before committing to an approach.

This skill looks up the answer to a customer question across the sources you have, such as past tickets, docs, and account notes. It can check whether a bug was reported earlier or what a given account heard from you in the past. The output gives an answer, key findings, cited sources, gaps, and next steps.

This skill researches a prospect company, and a named contact if you give one. It checks your CRM first, then gathers a company summary, the latest news, what they probably care about, and a score for fit against your ideal customer. It closes with hooks you could use in outreach.

Resolves in-progress Git merge and rebase conflicts through a clear sequence of file and history checks.

This skill checks NDAs, MSAs, and vendor agreements for a small business with no lawyer on staff. It reads the contract from a file, email, cloud storage, or DocuSign, points out unusual terms, explains the risk plainly, and returns a redlined DOCX.

This skill handles payer-side review of a prior authorization request. It takes in the request and clinical notes, checks them against coverage policy through connected MCP servers, and drafts a decision and notice. It requires those servers to be set up first.

Reviews UI animations for timing, easing, and design-engineering craft (Emil Kowalski style).

This skill reviews a diff or pull request for correctness, readability, architecture, speed, and security. It works for code from a person or an agent, and also checks change size and the change description before the code is merged.

This skill starts a deep-research job through the Parallel CLI, waits for it to finish, and returns the report with citations. It is only for requests that explicitly ask for exhaustive research, because it takes longer and is pricier than an ordinary Parallel web search. Follow-up questions can reuse an earlier task.

This skill plans a program with influencers, creators, or brand ambassadors to promote a product. It walks through finding and vetting partners, reaching out, setting deal terms, writing the creative brief, and meeting disclosure rules. It ends with how to measure return and a checklist for the whole run.

This skill creates, schedules, and manages outbound calling campaigns in Vapi for a contact list. It handles CSV or API contact data, concurrency, webhooks, pre-dial checks, and per-contact outcomes. It is not meant for a single call.

Creates sales enablement assets—one-pagers, decks, and objection handling—for buyers and reps.

Creates lint-clean exercise directories with sections, problems, solutions, and explainers.

Adds and fixes schema.org structured data so pages qualify for rich results.

This skill pulls the content of a known URL with the Firecrawl CLI, as Markdown, links, or a direct answer to a question about the page. It can wait for JavaScript, keep only the main content, and process several URLs at once. It can also run a Firecrawl data tool once one is chosen.

This skill uses the Skiplagged MCP server to search flights, hotels, and cheap travel dates. It can show a fare calendar for flexible dates, suggest destinations when you have none in mind, and find hidden-city routes. Answers stick to what the Skiplagged tools return.

This skill looks up flight prices and schedules on Google Flights by driving a browser. It handles one-way and round trips, and for international routes it can compare economy with business. It only searches and does not buy tickets.

This skill runs web searches with the Firecrawl CLI, giving back matching excerpts, with full page text when needed. It can limit results to recent news or certain domains and look for datasets, listings, and transcripts. It can also find and call Firecrawl's data tools by category.