All authors
Claude Skills by mdbabumiamssm
github.com/mdbabumiamssm1,578 skills3 installs3,530 views
- Matrix Operations--> --- name: bio-hi-c-analysis-matrix-operations description: Balance, normalize, and transform Hi-C contact matrices using cooler and cooltools. Apply iterative correction (ICE), compute expected values, and generate observed/expected matrices. Use when normalizing or transforming Hi-C matrices. tool_type: python primary_tool: cooltools measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- Balance, nor...Votes: 0GitHub stars: 6
- Tad Detection--> --- name: bio-hi-c-analysis-tad-detection description: Call topologically associating domains (TADs) from Hi-C data using insulation score, HiCExplorer, and other methods. Identify domain boundaries and hierarchical domain structure. Use when calling TADs from Hi-C insulation scores. tool_type: mixed primary_tool: cooltools measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- Call topologically asso...Votes: 0GitHub stars: 6
- AI Provider GitHub Maintainers 2026--> --- name: ai-provider-github-maintainers-2026 description: Track official AI provider GitHub repositories and release health for reliable integrations. Use when auditing SDK freshness, selecting maintained repos, or planning upgrades based on release cadence and issue velocity. measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- AWS Bedrock Operations 2026--> --- name: aws-bedrock-operations-2026 description: Build and run production workloads on Amazon Bedrock with current model access, IAM controls, and reliability guardrails. Use when implementing Bedrock inference pipelines, agent workflows, or model upgrades. measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Anthropic Claude Operations 2026--> --- 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 ---Votes: 0GitHub stars: 6
- Azure AI Foundry Operations 2026--> --- name: azure-ai-foundry-operations-2026 description: Implement and operate Azure AI Foundry and Azure OpenAI workloads with enterprise auth, networking, and deployment controls. Use when deploying model endpoints, migrating model versions, or setting up production guardrails on Azure. measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Claude Code Operations 2026--> --- name: claude-code-operations-2026 description: Operate Anthropic Claude Code across terminal use, agent teams, Agent SDK, GitHub Actions, plugins, and CI-based repository automation. Use when the main task is coding-agent execution, developer workflow acceleration, or repository-native automation with Anthropic tooling. measurable_outcome: Select and configure a Claude Code operating path with explicit install, instruction-file, and automation choices within 20 minutes. allowed-tools:...Votes: 0GitHub stars: 6
- Cloud AI Operations AWS Azure 2026--> --- name: cloud-ai-operations-aws-azure-2026 description: Operate AI workloads on AWS Bedrock and Azure AI/Azure OpenAI with production-focused cloud controls. Use when selecting managed model providers, implementing enterprise auth, and designing resilient cloud-native inference pipelines. measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Cohere Platform Operations 2026--> --- name: cohere-platform-operations-2026 description: Integrate and operate Cohere APIs with current model and SDK guidance. Use when selecting Cohere models, implementing generation or embed/rerank pipelines, or planning migration across Cohere API updates. measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- DeepSeek API Operations 2026--> --- name: deepseek-api-operations-2026 description: Integrate and operate DeepSeek APIs using current docs and compatibility guidance. Use when implementing DeepSeek-powered chat or reasoning workloads, selecting models, or validating OpenAI-compatible client behavior. measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Frontier OSS Models 2026--> --- name: frontier-oss-models-2026 description: Work with leading open or openly available model ecosystems from Meta, Mistral, DeepSeek, and xAI. Use when evaluating self-hosted or hybrid deployment paths, model tradeoffs, and integration patterns across non-single-vendor stacks. measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Gemini CLI Operations 2026--> --- name: gemini-cli-operations-2026 description: Operate Google's Gemini CLI for terminal-native coding, MCP integration, grounding, checkpointing, and headless automation. Use when the main task is developer workflow acceleration through Gemini CLI rather than a general Gemini API integration. measurable_outcome: Select and configure a Gemini CLI execution mode with explicit auth, context-file, and automation assumptions within 20 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Google Gemini Operations 2026--> --- name: google-gemini-operations-2026 description: Build and maintain Google Gemini API workflows using current docs and model catalog. Use when selecting Gemini models, implementing multimodal calls, or migrating code to the latest Google GenAI SDK patterns. measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Mistral Platform Operations 2026--> --- name: mistral-platform-operations-2026 description: Integrate and operate Mistral APIs with current model catalog and SDK guidance. Use when implementing Mistral chat or embedding workflows, selecting models, or migrating between API and SDK versions. measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- OpenAI Agents SDK 2026--> --- name: openai-agents-sdk-2026 description: Build production agents on OpenAI using the Responses API, Agents SDK, guardrails, built-in tools, tracing, and evals. Use when OpenAI is the primary runtime and you need a modern agent stack rather than legacy Assistants-era patterns. measurable_outcome: Select an OpenAI agent runtime pattern, tool surface, guardrail path, and validation plan for a concrete workload within 30 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- OpenAI Apps SDK 2026--> --- name: openai-apps-sdk-2026 description: Build ChatGPT-native apps with the OpenAI Apps SDK, MCP-backed tool servers, widgets, app metadata, and submission-ready integration patterns. Use when the main task is building an app surface inside ChatGPT rather than a raw API-only workflow. measurable_outcome: Design or update an Apps SDK integration with a clear MCP server plan, widget strategy, metadata posture, and test path within 25 minutes. allowed-tools: - read_file - run_shell_comman...Votes: 0GitHub stars: 6
- OpenAI Codex Operations 2026--> --- name: openai-codex-operations-2026 description: Use OpenAI Codex as a coding-agent surface across the app, CLI, IDE extension, SDK, MCP, plugins, skills, subagents, and GitHub automation. Use when the main task is repository automation, code understanding, code changes, or developer workflow acceleration rather than a generic API integration. measurable_outcome: Select and configure a Codex operating surface with clear security assumptions, repository instruction files, and a minimal ...Votes: 0GitHub stars: 6
- OpenAI Platform Operations 2026--> --- name: openai-platform-operations-2026 description: Operate and integrate OpenAI APIs with current model, modality, and migration workflows. Use when building or updating OpenAI-based chat, reasoning, transcription, speech, image, or video pipelines, and when replacing deprecated models. measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- XAI Grok Operations 2026--> --- name: xai-grok-operations-2026 description: Integrate and operate xAI Grok APIs with current documentation and SDK guidance. Use when implementing xAI model calls, selecting Grok variants, or planning safe upgrades around API changes. measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- A2A Protocol 2026--> --- name: a2a-protocol-2026 description: Design interoperable agent services using the Agent2Agent protocol. Use when independently hosted agents need to discover each other, exchange tasks, and collaborate without sharing a framework runtime. measurable_outcome: Define an A2A-compatible agent surface, task exchange pattern, and security posture for a concrete workflow within 30 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- AI Framework GitHub Maintainers 2026--> --- name: ai-framework-github-maintainers-2026 description: Track maintenance health of major AI framework repositories and choose reliable dependencies. Use when selecting orchestration stacks, planning upgrades, or reducing integration risk across fast-moving OSS ecosystems. measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- AgentSandboxCheckpointRestore Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'agent-sandbox-checkpoint-restore' description: 'Plan turn-aware, host-side checkpoint/restore for sandboxed agents by classifying OS-visible side effects and recovery-relevant state.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- Plan And Solve--> --- name: 'plan-and-solve-agent' description: 'Breaks down complex queries into a step-by-step plan before execution, improving performance on multi-hop reasoning tasks.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- The **Plan-and-Solve Agent** separates high-level planning from low-level execution. It is ideal for complex scientific inquiries that require multiple distinct steps (e.g., "Fin...Votes: 0GitHub stars: 6
- Agent Evals Observability 2026Evaluate and observe agent systems with traced runs, curated datasets, rollout gates, and regression loops. Use when an agent workflow is moving beyond prototype and needs measurable reliability before broader autonomy or production rollout.Votes: 0GitHub stars: 6
- Agno Operations 2026--> --- name: agno-operations-2026 description: Build and operate Agno agents, teams, and workflows with state, tools, memory, knowledge, approvals, and production runtime patterns. Use when you want a Python-first agent runtime that tightly connects build-time orchestration to production serving. measurable_outcome: Select an Agno agent, team, or workflow pattern plus a deployment and governance stance for a concrete workload within 30 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- CherryStudioAgentWorkbench Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'cherry-studio-agent-workbench' description: 'Operate Cherry Studio as a multi-provider AI workbench for assistants, autonomous agents, coding-agent integrations, local model routing, credentials, and guardrails.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- ClaudeCodeDeliveryLifecycleSkills Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'claude-code-delivery-lifecycle-skills' description: 'Operate the claude-code-skills delivery lifecycle suite for agile workflows, AI review, bootstrapping, docs, audits, optimization, MCP editing, graphs, and SSH.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- CollaborativeAgentReasoningEngineering Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'collaborative-agent-reasoning-engineering' description: 'Design domain AI agents through CARE stage gates with SMEs, developers, helper agents, reviewable specs, reasoning policies, tools, and evaluations.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- ContextWindowOptimizationAgents Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'context-window-optimization-agents' description: 'Optimize AI coding-agent context by sandboxing verbose tool output, preserving useful summaries, and managing transcript hygiene across agent runtimes.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch --- **Overview** This skill helps AI coding and research age...Votes: 0GitHub stars: 6
- CrewAI Production 2026--> --- name: crewai-production-2026 description: Build production-oriented CrewAI systems using agents, crews, and flows with memory, knowledge, guardrails, and tracing. Use when role-based multi-agent automation is central and you want a dedicated Python framework for crews plus event-driven flow control. measurable_outcome: Select a CrewAI crew or flow pattern, observability path, and rollout guardrails for a concrete workload within 30 minutes. allowed-tools: - read_file - run_shell_comma...Votes: 0GitHub stars: 6
- DSPy 2026--> --- name: dspy-2026 description: Build and optimize modular LM programs with DSPy. Use when evaluation, compilation, prompt optimization, and metric-driven improvement matter more than adopting a full agent hosting runtime. measurable_outcome: Select a DSPy module graph, optimization strategy, and evaluation metric for a concrete workload within 30 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- DeepResearch Swarm--> --- name: deep-research-swarm description: Multi-agent research literature analysis keywords: - research - literature - swarm - multi-agent - hypothesis measurable_outcome: Generates comprehensive literature review with >50 citations in <5 minutes. license: MIT metadata: author: AI Agentic Skills Team version: "1.0.0" compatibility: - system: Python 3.10+ allowed-tools: - run_shell_command - read_file - google_web_search --- A coordinated swarm of agents designed to perform deep, parallel...Votes: 0GitHub stars: 6
- DeerFlowSuperagentHarness Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'deer-flow-superagent-harness' description: 'Use Deer Flow, ByteDance''s open-source long-horizon SuperAgent harness, to research, code, and create with sandboxes, memories, tools, skills, subagents, and a message gateway.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- Claude 3 7 AgentReference older Anthropic model-specific reasoning patterns and migrate them to the current Anthropic operations skill. Use when maintaining a legacy Claude 3.7-specific example or translating it to current Claude model selection guidance.Votes: 0GitHub stars: 6
- DeepSeek R1 AgentReference older DeepSeek R1-specific reasoning examples and migrate them to current DeepSeek API operations guidance. Use when preserving an open-model reasoning example without treating raw chain-of-thought exposure as a stable product contract.Votes: 0GitHub stars: 6
- Gemini 2 0 Flash AgentReference older Gemini Flash multimodal examples and migrate them to current Gemini operations guidance. Use when a pinned Gemini 2.0 example needs to be translated into the active Google GenAI SDK and model-selection path.Votes: 0GitHub stars: 6
- GitagentProtocol Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'gitagent-protocol' description: 'Use GitAgent Protocol to define, inspect, and package framework-agnostic, git-native AI agent specifications for repository-based agent workflows.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- Google ADK 2026--> --- name: google-adk-2026 description: Build code-first agents with Google Agent Development Kit (ADK). Use when you need explicit orchestration, evaluation, and Google ecosystem alignment without giving up model flexibility. measurable_outcome: Select an ADK agent pattern, evaluation path, and deployment direction for a concrete workload within 30 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- LangGraph Production 2026--> --- name: langgraph-production-2026 description: Build durable LangGraph-based agents with checkpoints, interrupts, human review, and observability. Use when agent state, resumability, or long-running orchestration matter more than lightweight demos. measurable_outcome: Design or update a production LangGraph workflow with persistence, interrupt points, and a minimal smoke-test plan within 30 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- LatentAdversarialMultiturnDetector Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'latent-adversarial-multiturn-detector' description: 'Detect covert multi-turn prompt injection by probing residual-stream activations for "adversarial restlessness" trajectory signatures that text-level filters miss.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- LlamaIndex Workflows 2026--> --- name: llamaindex-workflows-2026 description: Build event-driven LlamaIndex workflows for document and data agents with serving, human-in-the-loop checkpoints, and workflow observability. Use when retrieval-heavy or document-centric systems need explicit workflow control. measurable_outcome: Select a LlamaIndex workflow pattern, data boundary, and serving path for a concrete workload within 30 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- LlmRlPosttrainingOptimization Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'llm-rl-posttraining-optimization' description: 'Optimize LLM RL post-training for efficient reasoning with GRPO variants, latent constraints, advantage estimation, cost controls, and verification gates.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- MCP Registry--> --- name: mcp-registry-2026 description: Design and curate Model Context Protocol tool surfaces, server registries, and shared resource access. Use when agents need portable tool/resource interoperability across clients, runtimes, or providers. measurable_outcome: Define an MCP server strategy, transport choice, and validation path for a concrete tool surface within 30 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Mastra Production 2026--> --- name: mastra-production-2026 description: Build production-oriented Mastra agents and workflows with memory, MCP, evals, observability, and TypeScript-first application integration. Use when product teams want one TypeScript stack for agent runtime, workflows, and operational tooling. measurable_outcome: Select a Mastra agent or workflow pattern, runtime boundary, and observability path for a concrete workload within 30 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Microsoft Agent Framework 2026--> --- name: microsoft-agent-framework-2026 description: Build and operate Microsoft Agent Framework workflows across Python and .NET. Use when enterprise hosting, workflow graphs, or migration from older Microsoft agent stacks matters. measurable_outcome: Select a Microsoft Agent Framework workflow pattern, hosting direction, and migration stance for a concrete workload within 30 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- MoaiSpecFirstAgenticDevkit Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'moai-spec-first-agentic-devkit' description: 'Use MOAI ADK SPEC-first agentic workflows to turn requirements into specs, TDD checks, DDD models, agent-team plans, and multilingual delivery.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- Multi Agent Systems--> --- name: 'swarm-orchestrator' description: 'Run Agent Swarms' keywords: - swarm - orchestration - multi-agent - parallel-execution - routing measurable_outcome: Successfully coordinates 3+ specialized agents to resolve complex queries with 100% completion rate. allowed-tools: - read_file - run_shell_command --- This skill activates a multi-agent system where a central "Overmind" routes tasks to specialized agents. It is designed for complex queries requiring multiple perspectives (search...Votes: 0GitHub stars: 6
- Swarm CoordinatorDesign a supervisor-worker or debate-style multi-agent coordinator with explicit delegation and synthesis boundaries. Use when a task genuinely benefits from controlled specialization rather than a single-agent loop.Votes: 0GitHub stars: 6
- Memory Management--> --- name: memory-management description: Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. CLAUDE.md for working memory, memory/ directory for the full knowledge base. keywords: - memory - context - decoding - glossary - collaboration measurable_outcome: Correctly identifies and decodes 90% of user-specific shorthands and acronyms in conversation. allo...Votes: 0GitHub stars: 6
- Task Management--> --- name: task-management description: Simple task management using a shared TASKS.md file. Reference this when the user asks about their tasks, wants to add/complete tasks, or needs help tracking commitments. keywords: - tasks - todo - tracking - active - dashboard measurable_outcome: Maintains an up-to-date TASKS.md reflecting all active user commitments and deadlines. allowed-tools: - read_file - run_shell_command --- Tasks are tracked in a simple `TASKS.md` file that both you and the ...Votes: 0GitHub stars: 6