install
source · Clone the upstream repo
git clone https://github.com/mdbabumiamssm/LLMs-Universal-Life-Science-and-Clinical-Skills-
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/mdbabumiamssm/LLMs-Universal-Life-Science-and-Clinical-Skills- "$T" && mkdir -p ~/.claude/skills && cp -r "$T/Skills/AI_Providers/Anthropic_Claude_Operations_2026" ~/.claude/skills/mdbabumiamssm-llms-universal-life-science-and-clinical-skills-anthropic-claude-o && rm -rf "$T"
manifest:
Skills/AI_Providers/Anthropic_Claude_Operations_2026/SKILL.mdsource content
<!--
# COPYRIGHT NOTICE
# This file is part of the "Universal Biomedical Skills" project.
# Copyright (c) 2026 MD BABU MIA, PhD <md.babu.mia@mssm.edu>
# All Rights Reserved.
#
# This code is proprietary and confidential.
# Unauthorized copying of this file, via any medium is strictly prohibited.
#
# Provenance: Authenticated by MD BABU MIA
-->
name: anthropic-claude-operations-2026 description: Integrate and operate Anthropic Claude APIs with current model lifecycle guidance. Use when implementing Claude-based assistants, tool use, long-context reasoning, or when planning model upgrades based on release notes and deprecations. measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools:
- read_file
- run_shell_command
Anthropic Claude Operations (2026)
Workflow
- Check release notes and deprecation notes in
.references/sources.md - Choose model tier based on latency, cost, and reasoning depth.
- Align tool-use strategy with official patterns before custom wrappers.
- Define retries, safety checks, and fallback behavior.
- Confirm expected behavior with a focused prompt/tool test.
Output Requirements
- State chosen Claude model and why.
- State any known deprecation risk and deadline.
- List one fallback path for service continuity.