메뉴
Use when comparing solution candidates or prototypes to reduce uncertainty before locking requirements or design; use UX-specification after the chosen interaction direction is approved.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/peterbamuhigire/srs-skills --skill 10-prototyping-and-solution-discovery명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | 10-prototyping-and-solution-discovery |
| description | Use when comparing solution candidates or prototypes to reduce uncertainty before locking requirements or design; use UX-specification after the chosen interaction direction is approved. |
| metadata | {"portable":true,"compatible_with":["claude-code","codex"]} |
Prototype plan, evaluation evidence, and decision record is the next lifecycle deliverable.ux-specification when that neighbouring route owns the decision or deliverable.| Artefact | Source or provider | Required? | Behaviour when missing |
|---|---|---|---|
| Discovery question, candidate options, constraints, users, risks, and success criteria | Product owner, users, architecture, and research evidence | Yes | Stop the affected step, name the missing source, and return only a qualified gap record. |
Prototype plan, evaluation evidence, and decision record| Artefact | Consumer | Acceptance condition |
|---|---|---|
| Prototype plan, evaluation evidence, and decision record | Requirements, product, design, and architecture owners | Required sections are populated, source links resolve, and every material requirement or decision has an observable review or test oracle. |
| Evidence | Reviewer | Acceptance condition |
|---|---|---|
Source, decision, trace, and validation record for Prototype plan, evaluation evidence, and decision record | Requirements quality reviewer | Inputs used, decisions made, checks run, failures, and unassessed items are explicit. |
Read and search are required. Editing is allowed only when the request authorises creation or repair of the named requirements artefact. Publishing, production mutation, destructive action, spending, and certification require explicit authority.
Fallback: if a required file, reviewer, standard source, network check, renderer, or execution capability is unavailable, return the narrowest useful qualified result and mark the affected check not assessed; never convert an unassessed check into a pass.
| Choice or condition | Action | Failure or risk avoided |
|---|---|---|
| A prototype has no falsifiable question or decision threshold | Rewrite the experiment before building it. | Prototype theatre with no decision value. |
| Required inputs and test oracles are complete | Continue through the existing workflow and record evidence. | A deliverable whose acceptance cannot be reproduced. |
| A mandatory source or owner is missing | Stop the affected branch and issue a qualified gap record. | Fabricated context or unauthorised decisions. |
Prototype plan, evaluation evidence, and decision record and its acceptance checks.Prototype plan, evaluation evidence, and decision record from assumed context. Fix: cite the project source or mark the scope blocked.ux-specification without routing the decision. Fix: hand off the named input and preserve trace links.not assessed and state the release consequence.Choose the cheapest prototype that can answer the uncertainty, but escalate evidence with risk: problem/market and alternative review, user research or observation, concept/landing test, click-through flow, workflow/concierge simulation, technical spike, and (where justified) a pilot or real commitment. For each stage record the hypothesis, target users, observable behaviour, threshold, guardrail, time box, decision, and remaining unknowns. A prototype, portfolio example, or stakeholder enthusiasm is not evidence of approval or product-market fit.
If AI assists research, synthesis, requirements, or prototyping, preserve the source context, ask it to surface questions/options before generating, verify summaries and competitor claims against originals, keep a decision log, and review scoped deltas rather than accepting broad regeneration. Human owners retain product, requirements, accessibility, and release judgement.
Practitioner cross-checks: Eleken product-idea validation, AI design workflow; corroborating practice: GOV.UK making prototypes.
This skill creates structured candidate solutions and prototype-driven learning before the project commits to a detailed design. It supports sacrificial prototypes, ready-made solution evaluation, comparison matrices, and explicit learning loops so the engine reduces requirement and design risk early.
| Attribute | Value |
|---|---|
| Inputs | projects/<ProjectName>/_context/vision.md, projects/<ProjectName>/_context/features.md, projects/<ProjectName>/<phase>/<document>/stakeholder_register.md (recommended), projects/<ProjectName>/<phase>/<document>/requirements_analysis_report.md (optional) |
| Output | projects/<ProjectName>/<phase>/<document>/solution_discovery_report.md |
| Tone | Exploratory but disciplined, evidence-seeking |
| Standards | Volere discovery and prototype-driven requirements practices |
State:
Produce at least three candidate solution directions when feasible:
For each candidate, define intended benefits, risks, and major constraints.
Choose the smallest prototype type that can answer the question:
Evaluate candidates against:
For each prototype or experiment, document:
Write projects/<ProjectName>/<phase>/<document>/solution_discovery_report.md including candidates, prototype strategy, evaluation matrix, learnings, and recommendation.