Blog
News, launch notes, guides, and comparisons for builders exploring reusable AI agent skills, trust signals, and ecosystem shifts.
Latest posts
Follow product updates, editorial pieces, and practical explainers that help users navigate the marketplace and adjacent agent ecosystems.
-
Triage pull request security risks with staged threat modeling and investigation using VulnVibes
Analyze a GitHub pull request for security impact, run targeted vulnerability-investigation skills when Stage 1 finds credible threats, and return a structured verdict instead of doing an ad hoc manual review.
-
Scaffold and bundle rich single-file web artifacts with React, Tailwind, and shadcn/ui
Use Anthropic’s web-artifacts-builder skill to scaffold a React artifact project, build a richer interface with state or routing, and bundle everything into one shareable HTML file. It is for artifact-delivery workflows, not for listing React or Tailwind as standalone products.
-
Generate Slack-ready animated GIFs from custom frame sequences
Use Anthropic’s slack-gif-creator skill to build animated GIFs that stay inside Slack’s practical size, duration, and dimension constraints. It gives an agent a bounded GIF-production workflow, not a generic image library or chat sticker listing.
-
Verify local web apps with Playwright scripts and managed dev servers
Use Anthropic’s webapp-testing skill to spin up one or more local servers, wait for them to become reachable, and run native Playwright checks against the rendered app. It is for agent-led verification and UI debugging of local web apps, not for listing Playwright as a generic browser framework.
-
Co-author structured docs with staged context gathering and reader testing
Use Anthropic’s doc-coauthoring skill to run a disciplined writing workflow instead of freeform drafting. The agent gathers missing context, iterates section by section, and pressure-tests the final document with reader-style review before teammates see it.
-
Generate reproducible algorithmic art sketches with seeded p5.js randomness
Use the Anthropic algorithmic-art skill when an agent should turn a creative brief into executable generative art, not into a static image prompt or a generic design suggestion. It directs the agent toward a repeatable p5.js workflow with seeded randomness, parameter controls, and an explicit creative philosophy.
-
Create, repair, and recalculate spreadsheet workbooks without breaking formulas
Use the Anthropic xlsx skill when an agent needs to create, clean up, or modify .xlsx, .xlsm, .csv, or .tsv files as spreadsheet deliverables, not just inspect tabular data. It pushes the agent toward formula-safe edits, workbook validation, and recalculation instead of hardcoded outputs or one-off scripts.
-
Create and repair Word documents with layout-safe DOCX workflows
Use the Anthropic docx skill when an agent needs to produce or repair a real .docx deliverable with headings, tables, numbering, tracked changes, or layout constraints. It frames the work as a document-building workflow with validation and packaging rules, not as a generic document library listing.
-
Draft internal status updates and incident comms
Use Anthropic’s internal-comms skill to turn raw project notes into company-ready status reports, 3P updates, FAQs, leadership notes, and incident writeups. The skill is valuable because it gives the agent a bounded communication workflow and format guidance, not because it exposes a generic skills repo.
-
Draft internal status updates and incident comms
Use Anthropic’s internal-comms skill to turn raw project notes into company-ready status reports, 3P updates, FAQs, leadership notes, and incident writeups. The skill is valuable because it gives the agent a bounded communication workflow and format guidance, not because it exposes a generic skills repo.