Discover, Publish & Install
AI Agent Skills
Browse agent skills crafted by the community, publish your own, and install any skill straight into Claude, Codex, Cursor and more from your terminal.
$ npm install -g skillbazaarVerified Skills
Browse all →meeting-next-steps
Turn a meeting's raw record — a video/audio transcript, the notes someone typed during the call, or both — into a short summary plus a clear list of next steps with owners. Use this whenever the user shares meeting notes or a transcript and wants to know what was decided and what happens next, OR asks for "action items", "next steps", "follow-ups", "takeaways", "who's doing what", "recap this meeting", or "what did we agree on". Trigger even when the user doesn't say the word "meeting" — a pasted transcript with speaker labels, or notes that read like a discussion, is enough of a signal.
contract-review
First-pass review and redlining of commercial contracts against a standard clause library, rapid NDA triage, and data-privacy/compliance checks. Use this skill whenever the user uploads or pastes a contract, agreement, NDA, MSA, SOW, DPA, or any set of terms and asks to review, redline, mark up, "check," "flag risks," "look over," triage, or compare it against standard positions — even if they don't use the word "review." Also use when the user asks whether specific clauses (liability, indemnity, IP, termination, confidentiality, data protection) are acceptable or "market.
finance-ops
First-pass support for recurring accounting and finance-operations work — month-end close checklists and tie-outs, AP/AR reconciliation, invoice validation (3-way match, duplicate and math checks), and financial-model review. Use this skill whenever the user uploads or pastes ledgers, trial balances, AP/AR aging, vendor statements, bank statements, invoices, POs, or a financial model (Excel/CSV/Google Sheets export) and asks to close the books, reconcile, tie out, match, validate invoices, find discrepancies or duplicates, review a model, or "check the numbers" — even if they don't use the exact accounting term. Also use for questions like "does this reconcile?", "is this invoice ok to pay?", or "review this model for errors.
status-reporting
Turn raw notes, ticket/task data, metrics, and standup updates into polished, consistent status reports and executive summaries in a reusable house format. Use this skill whenever the user wants to write, draft, generate, or clean up a weekly status report, team/project update, exec or leadership summary, stakeholder update, or "what I did this week / where things stand" report — or asks to define a house format for reports, make last week's format consistent, or summarize progress for leadership. Trigger even when the user just pastes messy notes, a task export, or last week's report and says "turn this into an update," and even if they don't use the exact word "status report.
insurance-ops
First-pass support for core insurance operations — claims intake / FNOL triage, underwriting submission checklists and risk screening, and side-by-side policy comparison. Use this skill whenever the user uploads or pastes a first notice of loss, claim file, loss run, underwriting submission/application, quote, or one or more policies/dec pages and asks to triage a claim, screen or check an underwriting submission, assess a risk, compare policies or quotes, find coverage gaps, or spot red flags — even if they don't use the exact insurance term. Also use for questions like "is this claim ready to assign?", "does this submission fit our appetite?", or "which of these quotes has better coverage?
tokslayer
Slays tokens in pasted content before Claude processes them. Targets docs, READMEs, papers, tickets, emails — where clipboard bloat lives.
See it in action
Publishing and installing a skill takes one command. Here's the whole flow.
Popular
Browse all →algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
suggest
USE FOR query autocomplete/suggestions. Fast (<100ms). Returns suggested queries as user types. Supports rich suggestions with entity info. Typo-resilient.
compare-models
Compare Replicate models by cost, speed, quality, and capabilities.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
meeting-next-steps
Turn a meeting's raw record — a video/audio transcript, the notes someone typed during the call, or both — into a short summary plus a clear list of next steps with owners. Use this whenever the user shares meeting notes or a transcript and wants to know what was decided and what happens next, OR asks for "action items", "next steps", "follow-ups", "takeaways", "who's doing what", "recap this meeting", or "what did we agree on". Trigger even when the user doesn't say the word "meeting" — a pasted transcript with speaker labels, or notes that read like a discussion, is enough of a signal.
Need a skill built for yourself or your team?
We build custom, codebase-aware AI agent skills for individuals and organizations — private to you, installable across Claude, Codex, Cursor and more. Consultations are always free.