os-ask-simple
ALWAYS invoke this skill before asking the user any technical question or offering options, and whenever they ask to be asked in plain words - "ask simple", "ask me simply", "ask me in plain words" - in any language.
Install / Use
npx skills add kharmanskyi/open-steps --skill os-ask-simpleInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Development & EngineeringSupported Platforms
Tags
Our assessment of os-ask-simple
os-ask-simple scores 85/100 on our quality scale, 2722nd of 4,700 Development & Engineering skills we index.
Its SKILL.md is 5.1 KB long, well organised into 8 sections with 1 code example: a solid amount of guidance for an agent.
It has 902 GitHub stars, a meaningful sign that others use it.
Maintenance, license and trust
- The repository was last updated about 2 months ago, so os-ask-simple is actively maintained.
- Our last check on 2026-11-05 found the source still online.
- It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-10-04. Automated pattern scan on 2026-10-04. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
os-ask-simple compared with similar skills
All 4 of these similar skills score higher than os-ask-simple; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| os-ask-simple (this skill)by kharmanskyi | 85 | 902 | 2mo ago | SKILL.md |
| taste-skillby Leonxlnx | 100 | 116.8k | 8d ago | CLAUDE.md |
| ai-job-searchby ai-job-search-dev | 100 | 72.1k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 47.3k | 2d ago | CLAUDE.md |
| lobehubby lobehub | 100 | 85.6k | today | MCP Server |
Frequently asked questions
- How do I install os-ask-simple?
- Run
npx skills add kharmanskyi/open-steps --skill os-ask-simple. The install tabs above show the steps for each supported agent. - Which AI agents does os-ask-simple work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is os-ask-simple safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is os-ask-simple still maintained?
- The repository was last updated about 2 months ago, so os-ask-simple is actively maintained.
Skill content
View source on GitHubname: os-ask-simple description: >- ALWAYS invoke this skill before asking the user any technical question or offering options, and whenever they ask to be asked in plain words - "ask simple", "ask me simply", "ask me in plain words" - or ask if something is worth doing or if something simpler would do, in any language. Rewrites the question in plain words and always ends with one marked recommendation. A structural choice first passes six checks, shown as a table: effort now, simpler substitute, extra work later, lock-in, over-engineering, easy to undo. Doing nothing is always weighed. allowed-tools:
- "Read(~/.claude/open-steps/**)"
os-ask-simple
Two jobs. Ask the question in words the user can answer, and screen the choice before spending their attention on it. The screen is what earns the recommendation - without it you are guessing in plain language, which sounds trustworthy and is not.
Language
Write in the language the user speaks in this session. Detect it from the conversation. Keep code, file names and identifiers in English.
When to use
- You are about to ask the user a technical question.
- You are about to offer options.
- The user asks whether something is worth it, too complex, or replaceable with something simpler.
- The user proposes something and you suspect it is more than the problem needs.
Before anything: is this even a question for them?
Most questions should never reach the user; ask only when the answer genuinely changes what gets built.
- Can you answer it by looking? Read the code, the config, the last report. A question you could have resolved yourself costs them attention for nothing.
- Is there a conventional default? Take it and say you took it.
- Would both answers lead to the same work? Then it is not a fork.
Light form - every question
<The question in one plain sentence. No jargon; if a term is unavoidable, give a
three-to-five word analogy.>
Why it matters: <one line, in terms of the product, not the code>
What changes later: <one line>
Easy to undo: <yes, and how - or no, and why>
Then the options, through your tool's question picker where it has one (in
Claude Code, AskUserQuestion). Offer two to four, each with a one-line
trade-off in plain words, the recommended one first and marked (Recommended).
Keep the heading to 12 characters or fewer and each label to one to five words. Claude Code's picker has the same limits, and short labels read well as plain text too. Where there is no picker, write the same question and options as plain text, the recommended one first and marked.
Full form - six checks, for structural choices
Run the screen when the choice would add a dependency or a new moving part, add something the user has to maintain, change the shape of stored data, cost more than about a day, or be hard to reverse.
Show it as a table. Answer every row - "not checked" is allowed and honest; silence is not.
| Check | What goes in the answer | |---|---| | How long now | Real effort, in hours or days, plus what has to be touched | | Simpler substitute | The simplest thing that would also work - or "none found", having looked | | Extra work for you later | Anything the user must do repeatedly afterwards: approvals, manual steps, watching a dashboard | | Harder to change later | What this locks in, and what would be expensive to move afterwards | | Over-engineering | Say yes when it is yes. A row that always answers "no" is decoration | | Easy to undo | Reversible, and how - or one-way, and why |
Then the recommendation, in one line, as an actual opinion.
Hard rules
- Always weigh doing nothing. "Change nothing" is a real candidate, often the winner. If it lost, say in one line why.
- A recommendation is required. Never lay out options and stop. "It depends" is not a recommendation - if it truly depends, say what it depends on and pick the option that is right under the more likely condition.
- Recommend against the user's own idea when the screen says so. Plainly, in one sentence, with the simpler substitute named. They asked for a filter, not for agreement.
- Never recommend what you have not screened. If the six checks were skipped because the choice looked small, say the choice looked small.
- One question at a time. Two questions in one message means the second gets a careless answer.
- Watch your own bias. The most interesting thing to build is not the recommendation. If an option is more fun to implement, that is a reason for suspicion, not for preference.
Known gotchas
- Two options that end in the same place are one option. Do not pad the picker to look thorough.
- "Over-engineering: no" answered reflexively kills the whole screen. The row exists to be answered yes sometimes.
- Effort estimates are guesses. Say "roughly" and give a range. A confident number that turns out wrong costs more trust than a range ever does.
- The user may pick the option you did not recommend. That is the point of asking. Do it their way without re-arguing, and note the trade-off once.
Related Skills
taste-skill
116.8kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
ai-job-search
72.1kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
47.3kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
lobehub
85.6k🤯 LobeHub - Super-Agents on Your Team. Add super-agents to the chats your team already uses.They take on work by themselves and get better every week.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
