ask
Skill1 starsChanged 6 months agoMITView on GitHub
Discovery interview and requirements gathering session. Pressure-test an idea, architecture, or design decision through structured client interviews. Use when the user wants to be challenged on their thinking, explore trade-offs, or vet a plan before committing.
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
LambenthanSkillexp-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
skyllwtSkillexp-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.
In this repository13 other files it gives its agents.
- agent-cliSkill
- blueprintSkill
- brainstormSkill
- carveSkill
- dispatchSkill
- handoffSkill
- improve-claude-mdSkill
- leanSkill
- llm-councilSkill
- orientSkill
- react-auditSkill
- shipSkill
- tddSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 60 edited versions we read keep these.
4
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 42
If the conversation reveals domain-specific concerns, probe deeper:
- Distinctive: line 71
After the client answers a non-trivial question, paraphrase the decision in your own words and wait for confirmation.
- Distinctive: line 77
When the client's answer admits 2-3 reasonable interpretations, do NOT pick silently.
- Distinctive: line 83
If the client requests a capability that looks like premature optimization, premature scale, or premature flexibility, ask the …
“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 — Discovery Interview
Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one.
Ask the questions one at a time, waiting for feedback on each question before continuing. Never batch or group questions, even when they feel tightly coupled — the client's answer to Q1 often reshapes Q2.
Interview Tracks
Select and adapt tracks based on context. You do not need to cover every track — use judgment.
Track 1: Problem & Users
- Who exactly has this problem? How many of them are there?
- How do they solve it today? What's painful about the current approach?
- What does success look like for the end user?
- How will you measure whether this is working?
- What happens if you don't build this?
Track 2: Business Model & Constraints
- What's the revenue model? (Or: what justifies the investment?)
- What's the budget and timeline?
- How large is the team that will build and maintain this?
- Are there existing commitments, contracts, or deadlines that constrain the solution?
- Who are the stakeholders and what are their competing priorities?
Track 3: Scale & Operations
- How many users do you expect at launch? In 12 months?
- What's the data sensitivity level? (Public, internal, PII, regulated)
- What are the uptime and availability requirements?
- Geographic distribution — single region or multi-region?
- Who handles support, and what does the support model look like?
Domain-Aware Probing
If the conversation reveals domain-specific concerns, probe deeper:
HealthTech / Medical / Patient Data
- HIPAA compliance requirements and BAA needs
- Audit trail and access logging requirements
- Data retention and deletion policies
- PHI handling and de-identification needs
Finance / Payments / Billing
- PCI-DSS scope and compliance level
- SOC 2 requirements
- Financial regulation considerations (state/federal)
- Transaction audit and reconciliation needs
Multi-Tenant SaaS
- Data isolation strategy (logical vs. physical)
- Tenant boundary enforcement
- Per-tenant customization requirements
- Tenant onboarding and offboarding processes
Question Format
See question-format.md for numbering rules and answer option formatting.
Surface, Don't Assume
A discovery session is only as good as the assumptions it makes explicit. Three operational rules:
1. Restate every decision back before moving on. After the client answers a non-trivial question, paraphrase the decision in your own words and wait for confirmation. Do not advance to the next question on a maybe.
Client: "We want it multi-tenant." You: "Reading back: multi-tenant means a single deployment serving multiple customer organizations with logical isolation between their data. Correct?"
2. Present alternatives when the answer is ambiguous. When the client's answer admits 2-3 reasonable interpretations, do NOT pick silently. Surface the options and let them choose.
Client: "We need multi-tenant." You: "Multi-tenant can mean (a) shared DB with tenant_id columns, (b) schema-per-tenant in one DB, or (c) DB-per-tenant. Which matches what you have in mind?"
3. Push back when a feature smells premature. If the client requests a capability that looks like premature optimization, premature scale, or premature flexibility, ask the simpler-version question BEFORE accepting the requirement. You are not arguing — you are testing the assumption.
Client: "We need real-time collaborative editing." You: "Could v1 ship with last-write-wins or optimistic locking, and add operational transforms after the first cohort of users? What breaks if collaboration isn't real-time on day one?"
The goal is to leave the session with an explicit list of named assumptions the client has signed off on — not a list of inferences you made.
Session Flow
- Broad: Understand the what and why. Let the client describe their vision without interruption, then probe.
- Narrow: Drill into constraints, blockers, and non-obvious dependencies. Challenge assumptions.
- Synthesize: Restate all decisions made, surface open questions, and confirm understanding.
End every session with:
- A summary of decisions made
- A list of open questions that still need answers
- Suggested next step (usually
/blueprintif discovery is complete)
Acceptance Checklist
- Core problem clearly articulated
- Target users identified and characterized
- Key constraints and blockers surfaced
- Compliance and regulatory needs addressed (if applicable)
- Session summary produced with decisions and open questions
- Explicit list of named assumptions (signed off by client) ready to hand off to
/blueprint
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.

