Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use when planning a royal inspection tour or standardizing governance across regions. Structures a five-year inspection cycle covering four cardinal directions with ritual obligations, measurement standardization, and audience protocols.
Interview the user relentlessly, one question at a time, to stress-test a plan, spec, or design until every open decision is resolved — recommended answer per question, answers cross-checked against the codebase and the @carbon/glossary domain terms, resolutions written back to the artifact as they land. Use when the user says "grill me", wants to stress-test a design or plan, or a spec-in-design's open questions need resolving (spec-writing Step 5 invokes this BEFORE the spec is written). SUPERVISED ONLY — never invoke from an automated loop (conductor, headless/outer-loop runs); autonomous flows use spec-writing's autonomous mode instead. Do not use to author the artifact itself — use /spec-writing for specs, /plan for implementation plans.
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
Take a GitHub issue or proposal, research it against this repo, frame 2-3 options, and help the user decide — then emit a plan and optionally launch the mega-pipeline. This skill should be used to turn an incoming proposal (e.g. a pathfinding.cloud privesc path) into a decided, planned, ready-to-execute change.
Create comprehensive feature implementation plan with codebase analysis and research. Also wires bidirectional back/forward references between existing plans (the update-references workflow). Use when the user wants to plan a feature, turn a PRD into an implementation plan, "link two plans", "add a back/forward reference", "connect related plans", or invokes /prp-plan.
Defines repository-wide issue discovery, lead-vetted issue publication, per-push CI cancellation during implementation waves, and post-campaign cleanup for nestia. Use when the user asks for a broad audit, many issue candidates, or a repeated issue-to-pull-request campaign; do not use for one already-defined issue or an ordinary pull request.
Process conversations or chat logs to identify reported bugs, search for existing GitHub issues, update existing issues when new undocumented details are discovered, and create new issues for untracked problems.
Prepare the CHANGELOG.md for a Damus release by running the changelog script, curating the output, and committing the result. Covers prerequisites, known pitfalls (duplicate entries, reverted commits, truncated annotations, wrong version label), and the editing/commit steps.
标记任务为阻塞状态并记录阻塞原因，移动到 blocked 目录。当用户报告任务被阻塞、遇到无法解决的问题、需要等待外部依赖时触发。参数为 task-id 和可选的阻塞原因。