Anthropic updated its best practices for building Claude skills, changing guidance on six issues including contents lists for reference files over 100 lines, variable "degrees of freedom," model-speci…
Anthropic's updated guidance for Claude Projects advises one project per workstream, brief instructions instead of exhaustive rule lists, and letting Claude interview users to build instruction sets, …
A developer argues that the "one-shot" AI coding benchmark is misleading, citing a livestream test in which a coding agent repeatedly asked for missing context and made wrong assumptions about scope r…
Claude Skills are integrated into coding pipelines by passing a tools array in the API request with each skill's name, description, and JSON Schema input_schema, which makes Claude return a tool_use b…
Combining Claude Projects, which pin a permanent knowledge base of documentation and code to a workspace, with Skills implemented via the Model Context Protocol (MCP) lets developers manage an autonom…
Anthropic's open-source repository for Claude Skills has surpassed 173,000 stars on GitHub, offering predefined instruction sets for specialized tasks that load on demand to optimize memory usage. The…
Menlo Ventures partner Matt Murphy says AI startups must focus on building platforms, not just models, citing Anthropic's leap to a $47 billion revenue run rate by May from $9 billion in 2025 as unpre…
A developer built Skillerr, an open-source protocol and CLI that adds trust and verification to AI skills before execution. The tool uses cryptographic hashes and optional Sigstore transparency logs t…
A downloadable Claude skill integrates with ProductAI to transform glossy AI portraits and product renders into camera-like images with pores, sensor grain, and unretouched texture while preserving pr…