Skills for Real Engineers. Straight from my .agents directory.
os-step-by-step
Agent skill fromkharmanskyi/open-steps
ALWAYS invoke this skill when you need the user to act - run a command, paste a secret, click, approve - and whenever they ask how to do something or say they do not know what to do: "step by step", "walk me through it", "what do I do", "what should I do", "I don't understand what to do", "explain what I need to do", in any language. Picking which task comes next is os-whats-next; this skill is for doing the thing in front of you. First earn the ask: try it yourself, find another route, shrink it to the part only they can do. Then one action per step, commands labelled by what they touch, no jargon. Commands are single lines that prompt for any value - typing hidden for secrets - and confirm in plain words. Afterwards verify their step.
How to install os-step-by-step
npx skills add kharmanskyi/open-steps# or add only this skill to Claude Code: copy the folder
skills/os-step-by-step/
# into
~/.claude/skills/os-step-by-step/ (all projects)
.claude/skills/os-step-by-step/ (one project)
1# os-step-by-step23The user is not stuck because the task is hard - they cannot tell what they4are being asked to do. This skill turns "I need something from you" into an5instruction a person who does not read code can follow without a follow-up6question. `os-done-or-not` reports *that* something is needed; this one says7exactly *how*.89## Language1011Write in the language the user speaks in this session, detected from the12conversation. Commands, file names and identifiers stay English.1314## When to use1516Triggers live in the description above - any moment you need the user's hands,17or they ask what to do.1819## Step 0 - earn the right to ask2021Every ask costs the user a context switch. Prove it is necessary; stop at the22first item that clears the block:23241. **Try it.** A real 403 is a finding; "I probably lack permission" is a guess.252. **Find another route.** Another tool, a value already on the host, a file26 you can read.273. **Shrink the ask.** Obtain what you can yourself; hand over only the28 irreducible part.294. **Check you are not asking twice** - search the session and the reports30 folder first.3132Three walls where asking IS the correct move, never to be worked around:33pulling a secret into your own context, loosening a guard that is there on34purpose, doing what the user said only they do.3536## The shape3738Always this order - the ask first, never after the diagnosis.3940```41**What I need from you: <one sentence, plain words>.**42…
Excerpt shown under the repository's MIT license.
More skills in open-steps
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
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
