Plan and review PufferLib reinforcement learning workflows, where agents learn through rewards. Covers version-specific environment checks, parallel execution, training and evaluation plans, plus checkpoint inspection before loading saved models.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Choose APIs for a specific PufferLib version
- Check environment behavior before training
- Create training and evaluation plans with separate seeds
K-Dense-AI/scientific-agent-skills☆ 5.3만2026년 10월 19일 업데이트
Prepare and check research documents for clinical decision-support evaluation, including evidence profiles, cohort tables, survival plans, and model assessments. Work with aggregate or synthetic inputs, record sources and review status, and keep outputs outside patient care.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Preparing research model evaluation documents
- Checking evidence profiles and source links
- Reviewing survival analysis plans
K-Dense-AI/scientific-agent-skills☆ 5.3만2026년 10월 19일 업데이트
Manage Hindsight memory for coding sessions: retrieve past decisions, store documents and initiative plans, correct outdated information, and configure memory by project. It also explains automatic conversation capture and helps investigate memory configuration problems.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Retrieving past project decisions and conventions
- Saving external notes and initiative plans
- Correcting outdated or inaccurate memory
vectorize-io/hindsight☆ 5.2만2026년 10월 20일 업데이트
Draft, revise, or review research proposals and plans using supporting evidence. The skill organizes claims and evidence before writing, checks feasibility and citations, and provides targeted revisions with quality scores and remaining risks.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Drafting a research plan from an initial idea
- Revising a research funding proposal
- Checking claims against supporting evidence
Yuan1z0825/nature-skills☆ 5만2026년 10월 20일 업데이트
Guide reviews of Linux Kernel patches for memory safety, Terraform plans for costly resource changes, and Kubernetes configurations for restricted permissions. A separately installed tool and configured AI model produce advisory findings and candidate manifests for validation.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Review Linux Kernel patches for memory safety issues
- Check Terraform plans for potentially costly resource changes
- Draft Kubernetes permission settings from security requirements
sickn33/agentic-awesome-skills☆ 4.8만2026년 10월 19일 업데이트
Create an implementation plan grounded in code relationships and verified source files, with proposed changes, test scenarios, risks, and a structured handoff for an implementation agent. It can also revisit and strengthen an existing plan.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Planning a new feature
- Assessing a shared API change before implementation
- Strengthening and rechecking an existing plan
abhigyanpatwari/GitNexus☆ 4.8만2026년 10월 20일 업데이트
Match identified security threats with controls that prevent, detect, or help recover from attacks. Use the mappings to find coverage gaps, prioritize security spending, and create remediation plans with multiple layers of protection.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Prioritizing security investments
- Creating a security remediation roadmap
- Checking gaps in existing security controls
wshobson/agents☆ 4.1만2026년 10월 20일 업데이트
Investigate slow SQL using execution plans, which show how a database processes a query. Review indexes, filters, joins, and maintenance practices through PostgreSQL examples to identify bottlenecks and plan changes to queries or database structure.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Investigating slow SQL queries
- Reviewing index choices and column order
- Reading EXPLAIN execution plans
wshobson/agents☆ 4.1만2026년 10월 20일 업데이트
Organize features, bug fixes, and refactors as Conductor tracks, units of related work. Create specifications and task plans, maintain status and dependency records, and preserve completed work with verification details and commit references.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Creating a work unit for a feature or bug fix
- Writing and reviewing specifications and task plans
- Recording task status, dependencies, and commits
wshobson/agents☆ 4.1만2026년 10월 20일 업데이트
Guide multi-step coding tasks with deepseek-v4-pro or deepseek-v4-flash in thinking mode. Verify files and symbols, write plans with confirmed file paths and line numbers, and use a verifier agent before changes spanning three or more files.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Verify that files and functions exist before editing
- Write plans with confirmed file paths and line numbers
- Check assumptions before changes spanning three or more files
codewhale-hq/Codewhale☆ 4.1만2026년 10월 19일 업데이트
Plan complex enterprise sales by mapping stakeholders, checking qualification with MEDDICC, a framework for assessing deals, and building shared action plans. Review buyer alignment, purchasing steps, and customer participation to identify stalled opportunities and next actions.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Planning a long enterprise sales cycle
- Mapping decision makers and stakeholder motivations
- Building a shared action plan with customer owners and deadlines
github/awesome-copilot☆ 4만2026년 10월 20일 업데이트
Structure board meetings and investor updates around business progress, risks, and decisions. Use clear narrative frameworks, consistent metrics, and advance briefings to explain missed targets, present recovery plans, and make specific requests for support.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Prepare a board meeting agenda and advance reading materials
- Draft a monthly investor update
- Explain missed targets and recovery plans
github/awesome-copilot☆ 4만2026년 10월 20일 업데이트
Design and review infrastructure and release workflows with checks tailored to the environment. Covers automated build and deployment pipelines, containers, health checks, rollback plans, feature flags, and mobile releases to help assess readiness before deployment.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Reviewing deployment and rollback plans
- Designing automated build and deployment pipelines
- Checking Docker and Kubernetes configurations
github/awesome-copilot☆ 4만2026년 10월 20일 업데이트
Convert feature requirements and implementation plans into a test strategy, task checklist, and quality assurance plan for GitHub projects. Define test coverage, priorities, dependencies, estimates, and quality checkpoints using established testing and software quality frameworks.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Plan testing from feature requirements and implementation documents
- Break testing work into tasks for GitHub issue management
- Prioritize performance, security, and accessibility checks
github/awesome-copilot☆ 4만2026년 10월 20일 업데이트
Turn feature requirements and technical plans into a structured GitHub project plan. Break work into linked issues, define acceptance criteria, dependencies, priorities, and estimates, and outline board settings and automated progress tracking.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Breaking feature requirements into GitHub Issues
- Mapping dependencies and setting work priorities
- Preparing sprint estimates and completion criteria
github/awesome-copilot☆ 4만2026년 10월 20일 업데이트
Design an AI agent around its requirements, or audit an existing agent for architectural problems. Deliver justified decisions, verification plans, and a PDF report with a diagram, covering budgets, permissions, stopping rules, and failure handling.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Design an agent from an idea or specification
- Audit an existing agent’s architecture
- Diagnose errors and false completion reports
github/awesome-copilot☆ 4만2026년 10월 20일 업데이트
Turn a development idea into an actionable plan with implementation steps, testable acceptance criteria, and risk mitigations. Gather requirements through focused questions, generate plans directly from detailed requests, or review proposals from multiple perspectives.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Clarifying requirements for a vague development idea
- Planning implementation from detailed requirements
- Comparing design options from multiple perspectives
Yeachan-Heo/oh-my-claudecode☆ 4만2026년 10월 20일 업데이트
Break a large development brief into ordered goals and save plans, progress events, blockers, and evidence in the repository. Coordinate Claude Code sessions through handoff instructions, with final completion requiring cleanup, verification, and code review evidence.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Tracking development work across Claude Code sessions
- Managing ordered goals with attempts and evidence
- Requiring cleanup, verification, and review before completion
Yeachan-Heo/oh-my-claudecode☆ 4만2026년 10월 20일 업데이트
Prepare for CMMC Level 2, a cybersecurity certification for defense contractors. Define the systems handling controlled information, review security requirements, calculate the SPRS assessment score, and organize remediation plans and evidence into a readiness report.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Define the assessment scope for systems handling controlled information
- Calculate an SPRS score and prioritize unmet security requirements
- Prepare security plans, remediation milestones, and assessment evidence
mukul975/Anthropic-Cybersecurity-Skills☆ 3.5만2026년 8월 31일 업데이트
Turns implementation requests into concise work plans with file references, testable acceptance criteria, risks, and verification steps. It can clarify vague requirements through focused questions, generate a plan directly, or review an existing plan.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Clarifying vague requirements before implementation
- Creating a plan with testable acceptance criteria
- Reviewing an existing work plan
Yeachan-Heo/oh-my-codex☆ 3.4만2026년 10월 20일 업데이트
Turn a feature idea into a design document through focused dialogue. The skill clarifies goals and constraints, compares two or three approaches, and reviews the design in sections before documenting architecture, data flow, errors, and testing.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Clarifying requirements for a new feature
- Comparing alternative implementation approaches
- Reviewing a design section by section
davila7/claude-code-templates☆ 3.3만2026년 10월 20일 업데이트
Turn feature requirements into test plans, step-by-step manual tests, regression suites for checking existing features, and reproducible bug reports. The skill also supports comparing implemented interfaces with Figma designs and documenting visual differences.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Plan tests for a new feature
- Write manual checkout test cases
- Organize regression checks before a release
davila7/claude-code-templates☆ 3.3만2026년 10월 20일 업데이트
Run Gemini CLI to review code, assess technical plans, and analyze large collections of files. Choose a model and execution settings for the task, then capture findings about security, maintainability, architecture, or technical debt.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Reviewing security and quality across multiple files
- Checking architecture plans for missing components
- Analyzing the structure of a large codebase
davila7/claude-code-templates☆ 3.3만2026년 10월 20일 업데이트
Prepare SOX 404 internal control testing, including sample selection, evidence requirements, and audit workpapers. Organize findings about controls over financial reporting, assess deficiencies, and outline remediation plans for review by qualified financial professionals.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
- Prepare workpapers for internal control testing
- Choose audit samples based on control frequency and risk
- Organize control deficiencies and remediation plans
anthropics/knowledge-work-plugins☆ 3.1만2026년 10월 20일 업데이트