KirillSachkov/sachkov-stack

agents-best-practices

Use this skill when designing, generating an MVP blueprint for, auditing, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral agent architecture for OpenAI, Anthropic, and OpenAI-compatible APIs: agent loops, tool design,…

لغة النص الأصلي: الإنجليزية

coding-task-pipeline

Use when performing any file-changing development task in a repository, including code, tests, documentation, configuration, schemas, generated artifacts, implementation, fixes, refactors, finishing, or verification.

لغة النص الأصلي: الإنجليزية

llm-wiki

Karpathy's LLM Wiki: build/query interlinked markdown KB.

لغة النص الأصلي: الإنجليزية

project-harness-bootstrap

Use when starting work in a project repository that has no agent harness or an incomplete one (no root AGENTS.md canon, no .harness/ directory, no gates, no harness.lock), when a SessionStart hook reports a missing or outdated harness, or when the owner asks…

لغة النص الأصلي: الروسية

project-task-report

Use when finishing project-scoped work that changed project state or produced a completed audit, diagnosis, investigation, or decision, including tasks with or without a tracker.

لغة النص الأصلي: الإنجليزية

prompt-library

Use when phrasing or structuring any task for Claude Code — a vague or underspecified request that needs shaping, the user asks "как сформулировать" / "how should I ask for X", starting an unfamiliar kind of work (onboarding a repo, incident, migration,…

لغة النص الأصلي: الروسية

writing-plans

Use when writing an implementation plan for a multi-step coding task before execution: bite-sized tasks, exact paths, complete code, verification steps per task.

لغة النص الأصلي: الإنجليزية