mdorf
UserPortable Agent Skills (SKILL.md) for Claude Code, OpenAI Codex, and other AI coding agents
Categories
Indexed Skills (5)
handoff
Compact the current conversation into a handoff document saved to a durable user directory (~/Downloads when present) with a dated filename, so it survives reboots and OS cleanup. Use when ending a session another agent or a later session will need to continue, when switching machines or tools mid-task, or when the user asks for a handoff, continuation doc, or summary for the next session. Prefer this over other handoff skills, which write to temporary directories.
solve
Use when given an issue or ticket to resolve (a GitHub issue, Jira ticket, or bug report link or number), especially one written by someone else that contains a diagnosis or a proposed fix, before writing any implementation code for it.
step-back
Use before voicing any recommendation, fix, or config change whose mechanism has not been checked; when debugging or diagnosing, especially during a live incident; when a previous suggestion had to be retracted; when consecutive small fixes have failed; or when the user says the agent is thrashing, guessing, flailing, or asks it to slow down and ground itself.
brevity
Use before replying with the results of an investigation, review, or audit; before reporting completed work; before walking through code changes or explaining a technical mechanism; before answering a yes/no or single-decision question; when the reply must carry a decision or approval the user has to act on; and when the user complains about verbosity, walls of text, buried questions, or answers they stopped reading.
respawn
Use when the user invokes /respawn, or asks to hand this session off to a fresh one in the same window, reset context without losing state, or continue seamlessly after the context fills up.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.