Requirements
Triggers: requirement analysis, 기획서 분석, 요구사항 쪼개기.
Not for: a settled conversation to write down (write:spec); a spec with acceptance and tasks before code (develop:spec-driven-development).
Process
- Take the input. A requirement or a 기획서, as pasted text or a file path. Read all of it; do not ask what it is for.
- Name the actors. Each person, role or system that acts in the input, one line each.
- Collect the rules. Take every rule, including the ones stated inside screen or flow descriptions, not only those in a policy list. For each, give its place in the input (a quote or a section/line reference); a rule the input implies but never states is marked
inferred.
- Find the missing 예외 처리. Check what the input leaves out: cancel, failure, duplicate, timeout, no-stock. List each missing one as an open question.
- Write the open questions. Sources: "추후 협의", "TBD", "기획 확인 필요", an unstated rule, a missing exception from step 4. Each has an assumed default and a suggested owner. Wherever a criterion rests on one, it carries the same point as
[확인 필요] <assumed default>.
- Split into items. Name them F1, F2, ... in item order. Each has a one-sentence outcome. The independence test: each item's criteria can be checked without another item's output. An item that needs another item's result names it in a
depends on line.
- Write the criteria. Per item,
F<n>-AC-n: Given ... When ... Then .... Number F-AC-1, F-AC-2, ... unique across the whole analysis and in document order, so every full id matches /\b(?:F\d+-)?AC-\d+\b/g.
- Gap and ambiguity check. Run
write/skills/plans/SKILL.md Process step 4 ("Gap check, in-line") and step 5 ("Ambiguity check, in-line") over the items and criteria; they are not restated here. Name both checks with the count each found (0 when none) on the Checks run: line.
- Stop at the analysis. The item split is the only decomposition. Write no code, no implementation plan, no tasks and no tickets.
Output Template
In the input's language, with English section headings. Saved to the path the caller names, otherwise docs/requirements/YYYY-MM-DD-<topic>.md. Four parts and a closing Checks run: line, so a teams node can place them as one section of a findings file:
## Actors
- <actor> — <what it does in the input>
## Rules
- <rule> — <place: "quote" or section/line | inferred>
## Open questions
- <question> — assumed default: <default>; owner: <who decides>
## Items
### F1 — <one-sentence outcome>
depends on: <F<n> | none>
- F1-AC-1: Given ... When ... Then ...
- F1-AC-2: Given ... When ... Then ... [확인 필요] <assumed default>
Checks run: gap (write:plans step 4) <n> found; ambiguity (write:plans step 5) <n> found
What Claude Does / What You Do
| Claude |
You |
Reads the input, quotes where each rule sits, marks inferred ones, lists the missing exceptions |
Paste the requirement or give its path |
| Splits into items, writes the criteria, runs the plans gap and ambiguity checks |
Answer the open questions or accept the assumed defaults |
Related Skills
After this analysis:
write:prd — a PRD, design doc or RFC
write:adr — an ADR or design review
write:plans — an implementation plan, tickets, blog or feedback
1---2name: requirements3description: "Use when a requirement or 기획서 must be split into items with Given/When/Then criteria and open questions. Triggers on: \"기획서 쪼개줘\", \"split this requirement\". Not for write:spec, develop:spec-driven-development."4scenarios:5 - "이 기획서 쪼개줘"6 - "요구사항 문서에서 빠진 예외 처리 찾아서 항목으로 나눠줘"7 - "Split this requirement into checkable items with acceptance criteria"8 - "Analyze this product brief and list what is still unanswered"9compatibility:10 optional:11 - think-tool # judging which rule or exception the input leaves out12metadata:13 source: https://skillmd.com/skills/newkayak12/requirements14---1516# Requirements1718Triggers: requirement analysis, 기획서 분석, 요구사항 쪼개기.1920Not for: a settled conversation to write down (`write:spec`); a spec with acceptance and tasks before code (`develop:spec-driven-development`).2122## Process23241. **Take the input.** A requirement or a 기획서, as pasted text or a file path. Read all of it; do not ask what it is for.252. **Name the actors.** Each person, role or system that acts in the input, one line each.263. **Collect the rules.** Take every rule, including the ones stated inside screen or flow descriptions, not only those in a policy list. For each, give its place in the input (a quote or a section/line reference); a rule the input implies but never states is marked `inferred`.274. **Find the missing 예외 처리.** Check what the input leaves out: cancel, failure, duplicate, timeout, no-stock. List each missing one as an open question.285. **Write the open questions.** Sources: "추후 협의", "TBD", "기획 확인 필요", an unstated rule, a missing exception from step 4. Each has an assumed default and a suggested owner. Wherever a criterion rests on one, it carries the same point as `[확인 필요] <assumed default>`.296. **Split into items.** Name them F1, F2, ... in item order. Each has a one-sentence outcome. The independence test: each item's criteria can be checked without another item's output. An item that needs another item's result names it in a `depends on` line.307. **Write the criteria.** Per item, `F<n>-AC-n: Given ... When ... Then ...`. Number F<n>-AC-1, F<n>-AC-2, ... unique across the whole analysis and in document order, so every full id matches `/\b(?:F\d+-)?AC-\d+\b/g`.318. **Gap and ambiguity check.** Run `write/skills/plans/SKILL.md` Process step 4 ("Gap check, in-line") and step 5 ("Ambiguity check, in-line") over the items and criteria; they are not restated here. Name both checks with the count each found (`0` when none) on the `Checks run:` line.329. **Stop at the analysis.** The item split is the only decomposition. Write no code, no implementation plan, no tasks and no tickets.3334## Output Template3536In the input's language, with English section headings. Saved to the path the caller names, otherwise `docs/requirements/YYYY-MM-DD-<topic>.md`. Four parts and a closing `Checks run:` line, so a teams node can place them as one section of a findings file:3738```markdown39## Actors40- <actor> — <what it does in the input>4142## Rules43- <rule> — <place: "quote" or section/line | inferred>4445## Open questions46- <question> — assumed default: <default>; owner: <who decides>4748## Items49### F1 — <one-sentence outcome>50depends on: <F<n> | none>51- F1-AC-1: Given ... When ... Then ...52- F1-AC-2: Given ... When ... Then ... [확인 필요] <assumed default>5354Checks run: gap (write:plans step 4) <n> found; ambiguity (write:plans step 5) <n> found55```5657## What Claude Does / What You Do5859| Claude | You |60|---|---|61| Reads the input, quotes where each rule sits, marks `inferred` ones, lists the missing exceptions | Paste the requirement or give its path |62| Splits into items, writes the criteria, runs the plans gap and ambiguity checks | Answer the open questions or accept the assumed defaults |6364## Related Skills6566After this analysis:6768- `write:prd` — a PRD, design doc or RFC69- `write:adr` — an ADR or design review70- `write:plans` — an implementation plan, tickets, blog or feedback