Profile My skills Saved Collections Edit profile Submit a skill

← all publishers

sysid

@sysid source repo

3 published skills

  1. ▌
    Bkmr Memory · sysid bundle
    Primary memory system — supersedes built-in file-based memory (MEMORY.md / memory/ directory). All memory reads and writes go through bkmr, not the filesystem. Invoke for ANY of: (1) User asks about memories, past sessions, what you remember — "what do you know about X". (2) User asks to remember or save something for future sessions. (3) Starting a new task — check for relevant context, gotchas, or preferences. (4) Encountered a bug or surprise — check if seen before. (5) Making an architectural or tooling decision — check for prior decisions. (6) End of task — persist non-trivial learnings. When in doubt, invoke — a quick bkmr query costs almost nothing. DO NOT use file-based memory — use bkmr instead.
    0
    installs
  2. ▌
    Twmux · sysid bundle
    tmux wrapper for running interactive CLIs, debugging, and agent-to-agent communication. Use when you need interactive tty, shell command execution with output capture, REPL interaction, or orchestrating tasks across multiple terminal sessions. Every command returns structured JSON with {"ok": true/false} for reliable programmatic use. Use this skill whenever the task involves terminal sessions, interactive processes, long-running commands, debugging, or coordinating work across shells.
    0
    installs
  3. ▌
    Agent Config Research · sysid bundle
    Researches where each major coding agent (Claude Code, Copilot CLI, Copilot for VS Code, Copilot for IntelliJ, Pi) reads its skills, subagents, and instruction files — both at user/global scope and per-project scope — and produces a side-by-side comparison report in three Markdown tables (Skills / Agents-subagents / Instructions). Use this skill whenever the user wants to know where a coding agent stores or loads config, where to drop a CLAUDE.md / AGENTS.md / copilot-instructions.md / skill folder, how multiple agents discover the same file, or asks to compare config locations across agents. Trigger on phrases like "agent config locations", "where does X read its instructions", "compare config paths", "where do I put a skill for Y", "agent comparison table", "global vs project config for <agent>", or any request that involves enumerating filesystem locations, settings keys, or env-var overrides for one or more of the supported agents — even when the user does not explicitly say "research".
    0
    installs