3.2K skills · sorted by relevance
Build and search a project knowledge graph, a map of information and its relationships. Check matching entries, relationship confidence, graph freshness, and changes since the previous build to understand the project's recorded structure.
Start a new development milestone for an existing project. The skill gathers goals, updates project documents, optionally researches new features, and creates scoped requirements and a phased roadmap for the next cycle of work.
Retrieve past decisions, recurring patterns, and unexpected issues from MemPalace before planning a phase. The skill produces a concise file with source references for the planner and falls back to GSD’s native memory when MemPalace is unavailable.
Coordinate paid advertising work across twelve platforms, from account audits and budget planning to creative briefs, experiments, monitoring, and reports. Ground recommendations in evidence and execute account changes only when explicit approval and required safeguards are in place.
Start planning hiring in a new country by gathering requirements, comparing an employer of record with a local entity, identifying questions for different teams and country-specific concerns, and creating a tracker for ongoing follow-up.
Find and load the appropriate skill for an agent working inside OpenRig. This index maps situations such as recovery, handover, debugging, and planning to relevant guidance, with commands that retrieve content matching the installed CLI.
Guide a team from product positioning and customer problem research to prioritized initiatives and a roadmap. Coordinate validation, stakeholder feedback, and execution planning so the team can connect its strategic direction to concrete work.
Plan the early stages of a browser game by choosing suitable technology and coordinating gameplay, interface, assets, and playtesting. It defaults to Phaser for 2D games and routes more specific work to the relevant specialist skills.
Create an evidence-based plan for modernizing an existing system. Analyze code and dependencies, research technology choices, and produce domain-specific migration plans with testing, rollback steps, and a consolidated roadmap for developers to execute.
Turn a feature request into an implementation plan before coding. Five planning phases cover requirements, interface design, technical choices, research, and metrics, producing ordered tasks, a test plan, and records explaining major decisions.
Coordinate feature development from product direction through architecture, planning, validation, and implementation. Run the whole workflow or start at a selected stage, with saved decisions, review checkpoints, and a final pull request.
Create VS Code custom agents for roles such as planning or code review. It builds .agent.md files with role instructions, permitted tools, and optional handoffs that let users move work to another agent.
Draft daily or weekly schedules from tasks, deadlines, availability, and stated energy patterns. Include fixed commitments, breaks, and buffers, flag work that will not fit, and review supplied activity logs to suggest practical adjustments.
Compare qualitative research designs for studying experiences, stories, cultures, or developing theory. Receive three options matched to the research question and available resources, plus a plan for participant selection, data collection, analysis, and quality checks.
Develop questionnaires and measurement scales for social science research, from drafting questions to planning pilot studies. Organize checks of whether scores measure the intended concept consistently, and prepare scoring guidance and reports.
Compare research methods before planning implementation. The skill examines project context, data constraints, required assumptions, computational costs, and available software, then documents two or three approaches with a recommendation and reasons for choosing it.
Run a research task through five ordered stages: brainstorming, planning, implementation, review, and documentation. The workflow checks that brainstorming and planning files exist before proceeding, then reviews and documents what the implementation stage produced.
Plan philosophy and interdisciplinary papers by comparing preprint platforms, searching literature, identifying unanswered questions, and assessing originality. Receive a detailed outline with section word counts, key citations, and improvements based on a reviewer-style assessment.
Estimate software development effort by breaking requirements into tasks and choosing three-point estimates, relative T-shirt sizes, or function points that measure functional scope. Produce workload reports with uncertainty ranges and relevant risk adjustments.
Manage GitHub issues, synchronize project boards, and plan sprints, short development cycles. Coordinate multiple AI agents to break work into tasks, assign responsibilities, update progress, and produce reports on completion and blockers.
Maintain a structured planning document tree made of roadmap/status files, implementation status or handoff TODO files, topic notes, decision records, open questions, ideas/inspiration pools, and repository/file-structure hygiene plans. Use when Codex needs to create, reorganize, audit, or update a multi-file plan, design-doc folder, roadmap tree, active implementation-status file, repo cleanup/filesystem plan, ADR/decision log, ideas inbox, or linked planning knowledge base; reconcile Done/In Progress/Next state; resume work from TODO/handoff state; move resolved questions into decisions; promote ideas into formal plan artifacts; or keep plan documents and file-structure planning internally consistent without making this project-specific.
The English summary is being prepared. Showing the original description.
[omh] Uncertain technical choice for a spike: bounded decision prototype workflow: resolve one uncertain interaction, API, performance, or integration choice with a disposable, isolated experiment whose observed result feeds planning. Use when the user says: decision-prototype, decision prototype, prototype this uncertain choice before planning, prototype before planning, prototype the uncertain choice, run a small spike, small spike, spike solution.
The English summary is being prepared. Showing the original description.
Implement load testing, auto-scaling, and capacity planning for Claude API. Use when running performance benchmarks, planning for traffic spikes, or configuring horizontal scaling for Claude-powered services. Trigger with phrases like "anthropic load test", "claude scaling", "anthropic capacity planning", "scale claude api".
The English summary is being prepared. Showing the original description.
Build production-ready systems with stability patterns: circuit breakers, bulkheads, timeouts, and retry logic. Use when the user mentions "production outage", "circuit breaker", "deployment pipeline", "chaos engineering", "retry storm", "health checks", "my service keeps crashing", "prevent cascading failures", or "make it resilient". Also trigger when designing resilient microservices, planning zero-downtime deployments, or capacity-planning for peak load. Covers stability patterns, capacity planning, deploy/release decoupling, and observability. For data systems, see ddia-systems. For system architecture, see system-design.
The English summary is being prepared. Showing the original description.