RetentaModel APIs change faster than any agent's training data, so a coding agent asked to build on one often writes against an old version. These skills come from the model providers and tool vendors themselves and point the agent at current APIs, SDKs and patterns.
Model names and API shapes in these skills go stale quickly. Each record shows the revision it was reviewed at, so you can tell how old the guidance is.
Anthropic · Claude Code
A four-phase guide to researching, implementing, testing, and evaluating MCP servers with discoverable tools, typed schemas, focused responses, and realistic read-only evals.
Anthropic · Claude Code (plugin marketplace) · Claude.ai · Claude API (Skills API)
A four-phase process for building MCP servers in Python (FastMCP) or TypeScript (MCP SDK): research the target API and MCP best practices, implement tools with good naming, schemas and error messages, review and test, then write an evaluation of realistic questions. Reference files cover MCP best practices, per-language server guides and how to build evaluations.
Anthropic · Claude Code (plugin marketplace) · Claude.ai · Claude API (Skills API)
Guides the full loop of authoring an Agent Skill: draft it, write test prompts, run Claude with and without the skill, grade outputs with grader/comparator/analyzer sub-agent prompts, show results in a generated HTML review viewer, and iterate. It also runs trigger evals that test and rewrite the skill's description for triggering accuracy, then packages the skill.
Anthropic · Claude Code (plugin marketplace) · Claude.ai · Claude API (Skills API)
A reference skill for building on the Claude API and Anthropic SDKs: it first checks the project for other-provider markers and stops if found, detects the language, then routes to per-language docs (Python, TypeScript, Java, Go, C#, curl and more) for streaming, tool use, files, batches, caching and Managed Agents. It carries a dated table of current model IDs and migration rules and warns the agent its training prior on the API is likely stale.
Google (Gemini team) · Claude Code · OpenAI Codex · Cursor · Antigravity · any Agent Skills client via npx skills
Overrides the agent's training data with a current Gemini model list and critical rules, then guides SDK usage for text generation, chat, multimodal input, image/video/speech generation, streaming, function calling, structured output and long-running research tasks. A reference covers migrating from the older generateContent API.
Hugging Face · Claude Code · OpenAI Codex · Cursor · Gemini CLI
Guides fine-tuning language and vision models with TRL (SFT, DPO, GRPO, reward modeling) or Unsloth on Hugging Face Jobs cloud GPUs: dataset validation, hardware and cost estimation, UV scripts in PEP 723 format, Trackio monitoring, saving to the Hub, and GGUF conversion for local inference. Bundled example training scripts are submitted as jobs.
Datadog · Claude Code · OpenAI Codex · Cursor · Gemini CLI · OpenCode · Windsurf · any Agent Skills client via npx skills
Bootstraps LLM evaluators from production traces in Datadog LLM Observability: it samples traces, proposes online LLM-judge evaluators, and after explicit confirmation creates them in Datadog as disabled drafts (never auto-enabled); on request it emits Python SDK code or a framework-agnostic JSON spec instead. It auto-selects between the Datadog MCP server and the `pup` CLI as the backend.
Eligible reviewed snapshots can be added to a Thyme RAG Capsule in one click. Retenta only enables that action after a separate capsule-distribution check; other records link to the publisher's installation path.