ask
Skill2 starsChanged 55 days agoMITView on GitHub
Puts a decision to the user through the client's native picker, or a lettered list when none exists. Use for any question with discrete answers, such as a push, a version bump, or which findings to fix, even when no other skill says to ask.
72 other projects use a version of this.
Adopted by
Most recently taken up by
- jskswamy/skillstheir own version, first seen Nov 8, 2026
- Yeachan-Heo/oh-my-claudecodetheir own version, first seen Nov 8, 2026
- szarkans/multitheir own version, first seen Nov 2, 2026
- Nucleify/Nucleifytheir own version, first seen Nov 2, 2026
- Tbsheff/skillstheir own version, first seen Nov 1, 2026
- Buddhilive/buddhi-clitheir own version, first seen Nov 1, 2026
Used with
Projects with it also use daily-arxiv, exp-eval and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
LambenthanSkilldaily-arxiv
每日从 arXiv 拉取新论文，过滤相关性，auto-ingest 高优先级论文，检测 SOTA 更新
Also in 5 projects that use this
- LambenthanSkill
exp-eval
实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges
Also in 5 projects that use this
skyllwtSkillexp-pilot-eval
Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.
Also in 4 projects that use this
- skyllwtSkill
exp-pilot-run
Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.
Also in 4 projects that use this
phanghonghaoSkillposter
HTML/CSS A4 海报生成。从沙龙/活动 Markdown 文件生成科技风 A4 海报 PDF/PNG。Use when user mentions: poster, 海报, 海报生成, make poster, generate poster, 活动海报, 沙龙海报.
Also in 4 projects that use this
- +6 more from Lambenthan
- +1 more from skyllwt
Other versions72 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 72
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- Yeachan-Heo/oh-my-codex★ 34ksame name
- agenticnotetaking/arscontexta★ 3.5ksame name
- acunniffe/git-ai★ 3ksame name
- git-ai-project/git-ai★ 3ksame name
- skyllwt/OmegaWiki★ 1.7ksame name
- DAIR-AutoResearch/AutoSci★ 1.7ksame name
- PKU-DAIR/AutoSci★ 1.7ksame name
- skyllwt/AutoSci★ 1.7ksame name
62 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 60 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Put a decision to the user and wait for the answer before the step it decides.
- Distinctive: line 12
Use the first one the session has.
- Distinctive: line 22
Read only the file for the tool you use: those pickers have their own limits.
- Distinctive: line 53
Never put a secret or credential in an option.
- Distinctive: line 57
Ask before the step, not after: do not write the file, commit, or push that the answer decides until it arrives.
“Common” is measured: kept by at least 6 in 10 of the 60 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Ask
Put a decision to the user and wait for the answer before the step it decides.
1. Pick the tool
Use the first one the session has. Never call a tool that is not available.
| Tool | Client | Read first |
AskUserQuestion | Claude Code, Claude Desktop | |
AskQuestion | Cursor | |
request_user_input_async | Paseo, or Codex when the mode exposes it | references/paseo.md |
request_user_input | Codex Plan mode | references/codex.md |
| None | Lettered options in chat, same order plus Other. Ask for the letter |
Read only the file for the tool you use: those pickers have their own limits.
2. Summarize in bullets
In the same reply as the picker call, and before it, write one bullet per decision: what it changes and why. The picker has no room for detail and covers the chat on mobile, so the bullets are the only place the user can judge each decision. A prose paragraph or a line such as "findings will follow" is not a summary.
- `render.tsx:14`: the comment still says "@kubb/ast pin". Reword to "Studio's Kubb pin", since
`@kubb/ast` is no longer a direct dependency. Recommend Apply.
- `render.tsx:31`: `as ApiMeta` repeats the inferred type. Remove the cast. Recommend Apply.3. Shape the questions
- Each question stands alone. Mobile clients hide the chat behind the picker, so name the thing
(
Duplicated 402 logic in billing.ts?) and never point at a number or letter only the chat defines (Fix 3?). - Offer 2 to 4 real options, likely answer first. Mark the one you think is best
(Recommended)and give the reason in its description. - One question per independent decision, sent together.
AskUserQuestiontakes four per call, so send the rest in a follow-up call rather than dropping any. Merge questions only when their answers settle one decision. - Per-item decisions, such as review findings, get one single-select question each, offering
Apply,Skip, or a concrete alternative. Never a bundle such asAll (1-7),None, orApply both. - Allow multiple selection only when several answers can be true, never for per-item decisions.
- For an open question, offer likely answers and allow custom input, unless the calling skill forbids guessed options.
- Never put a secret or credential in an option. Ask for it in prose and never echo it.
4. Wait
Ask before the step, not after: do not write the file, commit, or push that the answer decides until it arrives. When the question is skipped or unanswered, do not choose for the user, and do not guess now and report the guess later. Stop at that decision, say what is missing, and finish only the work that does not depend on it. A push or a version bump always waits.
Output
The bullets, then the picker. After the answer, one bullet per decision naming the choice, then the work it unlocked.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.