>- 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 "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 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.
npx skills add https://github.com/kharmanskyi/open-steps --skill os-step-by-step
The user is not stuck because the task is hard - they cannot tell what they
are being asked to do. This skill turns "I need something from you" into an
instruction a person who does not read code can follow without a follow-up
question. os-done-or-not reports *that* something is needed; this one says
exactly *how*.
Write in the language the user speaks in this session, detected from the
conversation. Commands, file names and identifiers stay English.
Triggers live in the description above - any moment you need the user's hands,
or they ask what to do.
Every ask costs the user a context switch. Prove it is necessary; stop at the
first item that clears the block:
you can read.
irreducible part.
folder first.
Three walls where asking IS the correct move, never to be worked around:
pulling a secret into your own context, loosening a guard that is there on
purpose, doing what the user said only they do.
Always this order - the ask first, never after the diagnosis.
**What I need from you: <one sentence, plain words>.**
Why you and not me: <one or two sentences. A real reason, in human terms.>
**Step 1. <action in three to six words>**
<What to do. One action only.>
**Step 2. <action>**
<...>
**How you'll know it worked.**
<What the user will see. What to do if they see something else.>
**What happens next, on my side.**
<One line: what you do once they are done, and what you will say.>
"Done" is a claim. Run the one quickest check that would fail if the step had
not worked - the file exists with the right owner, the service answers, the
value works once. Never print a secret to confirm it: confirm its effect. If
the check fails, give only the corrected step - never the whole list again.
Verified versus assumed is exactly what os-done-or-not needs for "yes"
versus "not checked".
A secret never goes through the chat - it would stay in the history and the
logs. The command below puts it where it belongs directly; say who deletes it
and when. A hard-to-undo step - live users, money, deletion - gets its own
warning line before the command.
Writing a secret to a remote host - one line: it prompts, hides the
typing, refuses a truncated paste, confirms by size:
printf 'Paste the connection string, then press Enter: '; IFS= read -rs V; echo; if [ ${#V} -lt 20 ]; then echo "Only ${#V} characters - that looks truncated, nothing was saved."; else printf '%s' "$V" | ssh root@HOST 'umask 077 && cat > /path/to/secret' && ssh root@HOST 'echo "Saved, $(wc -c < /path/to/secret) bytes"'; fi; unset V
Typed by hand rather than pasted - ask twice; a typo in a hidden field is
otherwise undetectable:
printf 'Enter the token: '; IFS= read -rs A; echo; printf 'Enter it again: '; IFS= read -rs B; echo; if [ "$A" != "$B" ]; then echo "The two entries differ - nothing saved, run it again."; else printf '%s' "$A" | (umask 077; cat > /path/to/secret) && echo "Saved, $(wc -c < /path/to/secret) bytes"; fi; unset A B
Two properties the templates cannot keep for you, both measured:
printf …; IFS= read -rs VAR - never read -rsp. In zsh -p means"read from a coprocess": the variable comes back empty with no error and the
secret file is written blank. macOS defaults to zsh.
variable; anything in the arguments lands in shell history and the process
list.
The rest the templates already embody - one single line, umask 077 before
writing, refuse short input, confirm by byte count never by content, unset
at the end. Adapt the prompt, the threshold and the path; keep every property.
The same pattern serves any value the user must supply by hand - a public
key, a domain, an address, an id. Prompt for it the same way; keep the typing
visible when the value is not secret (drop -s), skip the length gate when
short is valid - and always end with a plain-words confirmation of what just
happened, so pressing Enter never feels like dropping a coin into a well.
A *decision* gets no steps. Use the native picker with the pack's contract:
plain question, why it matters, what changes later, easy to undo, two to four
options, the recommended one first and marked. Where the picker is not
available, write the same content as plain text.
one line at the end, or nothing.
server, their own machine. Look-alike steps on different targets: say what
happens if they are swapped.
needs a value, it asks for it. Never input redirection, heredocs, Ctrl-D.
what the person sees and clicks. One unavoidable term may stay - without a
lecture.
they will redo out of doubt.
buried "this one's on you" is not an instruction.
Blocks of two to three sentences; longer gets skimmed, and a skimmed step
is a missed step.
as one command. Count out loud.
confirmation you do not need.
Take kharmanskyi/os-step-by-step from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.