← all publishers

DenisSergeevitch

@denissergeevitch source repo

Report this profile Claim this profile

• 5 skills
• 0 followers
• 719 repo stars
• last month last updated

1. ▌
   Game Sensitivity Coach · denissergeevitch bundle

   Discover a gamer's mouse settings, transfer sensitivity between games, and refine aim from passive gameplay video and mouse logs. Use for mouse sensitivity calibration, scoped or ADS tuning, cm/360 conversion, or applying and restoring game sensitivity settings. The agent handles settings discovery, image review, and evidence logging; the gamer plays normally.
   719 repo stars
2. ▌
   Pm As Code · denissergeevitch bundle

   Strict Markdown project management with status.md as the canonical entrypoint: checkbox-only tasks with IDs, acceptance criteria, evidence, and append-only pulse history. Includes no-dependency Bash and Windows (PowerShell/CMD) ticket and collab wrappers for long-running and multi-agent repos.
   719 repo stars
3. ▌
   Youtube Poop Video Maker · denissergeevitch bundle

   Use this skill when the user wants a short YouTube poop, cursed trailer, glitch-poetry montage, absurd supercut, reflective meme edit, or FFmpeg-rendered remix video from text, webpages, code, documents, media, or from scratch. Activate for prompts like “make this weirder,” “give it a personal spin,” “what it feels like,” “render with ffmpeg,” or self-aware AI / LLM montage requests. The skill plans and renders a dense, aesthetically pleasing 20–60 second video with many micro-scenes, readable typography, restrained neon or analog treatments, controlled audio, optional TTS fragments, and a default seeded-remix blueprint that samples the bundled styles at runtime.
   719 repo stars
4. ▌
   Agents Best Practices · denissergeevitch bundle

   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, record provenance, interactive presentation, user-memory lifecycles, environment-adaptive tools, speculative tool execution, late-bound capabilities, permissions, system prompts, planning, goals, context compaction, memory, skills, MCP/external connectors, public-board communications, self-refining recursive harnesses, programmable context, continual refinement, observability, evals, prompt caching, agent-legible environments, feedback loops, and safety.
   719 repo stars
5. ▌
   Repo Task Proof Loop · denissergeevitch bundle

   Provides a repeatable, auditable workflow for large coding tasks by initializing repo-local task artifacts, installing subagent templates, and running a spec-freeze → build → evidence → verify → fix loop with fresh-session verification.
   719 repo stars