Skills for Real Engineers. Straight from my .agents directory.
39 skills
reimagine-work
Agent skill from
Use when someone asks to find the "stupid human steps" in how work gets done, where a person is the bottleneck for a team of agents, how to redesign a process from zero, or to run the weekly "Elon algorithm" pass (question, delete, simplify, speed up, automate) over an agent fleet. Also use as a routine: weekly full pass with an outside reviewer, plus weekday incremental runs that propose at most one new change or stay silent. Also use when work arrives "one drop at a time" (batch waits, daily-only runs, per-item human review) and should become a continuous stream, or when deciding how much autonomy an ask type has earned, what threshold makes an input worth acting on, or which lanes cost too much per real outcome. It proposes and builds only internal, reversible checks. It never sends, posts, spends, enrolls, deletes, merges or changes a routine.
How to install reimagine-work
install reimagine-work
# install the ai-marketing-skills pack with the skills CLI
npx skills add ericosiu/ai-marketing-skills# or add only this skill to Claude Code: copy the folder
reimagine-work/skills/reimagine-work/
# into
~/.claude/skills/reimagine-work/ (all projects)
.claude/skills/reimagine-work/ (one project)
1# Reimagine work (v3.3 template: weekly Elon loop + continuous stream + escalation ladder + earned autonomy)23> Template. Replace every `<PLACEHOLDER>` with your own values. Nothing in this skill sends, posts, spends or approves anything; it only proposes. The judge it refers to ships in shadow mode (log only) with hard gates on.45Find every place a human is what work waits on, remove that wait, and do it6again next week. The deliverable is a short ranked list and exact yes lines,7not a long report.8910## Asks that are already answered (never re-ask)1112Before any yes line reaches the human, check these in order. If any one is true, the work proceeds with no new ask, and it gets logged with what authorized it:131. **The human already said it.** If the owner's own words in this conversation asked for this exact action ("send these follow-ups, by email and chat"), that is the yes. A copy tweak they asked for ("keep it simple like the outbound") is still inside that yes. Do not send a confirm line for the same batch.142. **A lane owner approved it.** If the person who owns the lane (for example, the content lead for publishing) approved, proceed under their conditions. Don't ask the top owner for a second yes.153. **A standing approval with a cap covers it.** Check the approval ledger. A matching row with owner_bots, a cap and a scope is the yes.164. **It's reversible or read-only.** No yes at all.17…
Excerpt shown under the repository's MIT license.
More skills in ai-marketing-skills
Keep exploring
Similar skill repositories
An agentic skills framework & software development methodology that works.
15 skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
CC1 skill
Public repository for Agent Skills
20 skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
CCCU6 skills
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
CCCXGHGM+135 skills