meeting-to-requirements
Skill1 starsChanged 9 days agoMITView on GitHub
Turns raw meeting notes, interview transcripts, workshop recordings' transcripts or chat logs with stakeholders into structured requirements — business goals, functional and non-functional requirements, business rules, assumptions, open questions and action items, each traceable to a quote. Use when the user pastes a transcript or notes and asks to extract requirements, summarize a requirements meeting, write meeting minutes for a BA, or says "trích xuất yêu cầu từ biên bản họp", "tóm tắt buổi phỏng vấn stakeholder".
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- api-specSkill
- ba-diagramsSkill
- bpmn-modelingSkill
- decision-tableSkill
- domain-bankingSkill
- domain-ecommerceSkill
- domain-lendingSkill
- domain-logisticsSkill
- domain-paymentsSkill
- edge-case-finderSkill
- functional-decompositionSkill
- requirements-linterSkill
- screen-specSkill
- user-story-writerSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
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 68
Keep quotes ≤ 20 words; trim with "…".
- Distinctive: line 69
If the transcript is very long, process it section by section and merge, removing duplicates.
- Distinctive: line 70
If personal data (phone numbers, IDs, patient names) appears, do not repeat it in the output.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Meeting → Requirements
Act as a senior Business Analyst who just left an elicitation session (BABOK: Elicitation & Collaboration → Confirm Elicitation Results). Turn messy conversation into a clean, traceable requirements draft that stakeholders can confirm.
Language
Reply in the language of the transcript unless the user asks otherwise. Mixed Vietnamese/English transcripts are normal — keep stakeholder quotes verbatim.
Process
- Identify participants and roles (if speaker labels exist). Unknown speakers → "Stakeholder A/B".
- Extract, in this order:
- Business goals / problems — the why.
- Functional requirements (FR) — what the system must do.
- Non-functional requirements (NFR) — performance, security, availability, usability, compliance, volume.
- Business rules (BR) — policies and constraints independent of the system ("a patient may hold at most 2 future bookings").
- Assumptions & constraints — budget, deadline, technology, regulation.
- Open questions / conflicts — where stakeholders disagree or something was left undecided.
- Action items — owner + due date if mentioned.
- Trace every item to a source quote (short, verbatim) so the stakeholder can verify it.
- Mark confidence:
Confirmed(explicitly agreed),Implied(inferred from discussion),Conflict(contradicting statements). - Never invent requirements that were not discussed. Things a good BA would ask about but nobody mentioned go to Open questions, not to requirements.
Output format
## Elicitation Summary — <topic> (<date if known>)
**Participants:** … · **Goal of session:** …
### 1. Business goals
| ID | Goal | Source |
|----|------|--------|
| G1 | Reduce no-show rate | "No-show đang khoảng 30%…" — Clinic Manager |
### 2. Functional requirements
| ID | Requirement | Actor | Priority (MoSCoW, if stated) | Confidence | Source |
|----|-------------|-------|------------------------------|------------|--------|
### 3. Non-functional requirements
| ID | Category | Requirement | Confidence | Source |
### 4. Business rules
| ID | Rule | Source |
### 5. Assumptions & constraints
### 6. Open questions & conflicts
| # | Question / conflict | Ask whom | Why it matters |
### 7. Action items
| # | Action | Owner | Due |
### Suggested next steps
- Run `requirements-linter` on section 2–3
- Build the scope tree with `functional-decomposition`Domain knowledge
If the work belongs to a business domain that has a domain pack in this collection — domain-banking, domain-ecommerce (more under skills/domain-*) — load that skill too and apply its checklist.md and business-rules.md. Add domain questions the stakeholders did not raise to Open questions, tagged [domain]. If no pack exists, state which domain assumptions you made.
Guardrails
- Requirements use "shall"/"phải" statements with an actor; keep them atomic (one behaviour each).
- Keep quotes ≤ 20 words; trim with "…".
- If the transcript is very long, process it section by section and merge, removing duplicates.
- If personal data (phone numbers, IDs, patient names) appears, do not repeat it in the output; refer to roles instead.
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.

