메뉴
Extract a validated problem brief through user interview and codebase exploration. Activate ONLY when the user says "new PRD", "plan a feature", or "write a PRD". Not for implementation specs, bug triage, or general feature discussion.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | prd-discover |
| description | Extract a validated problem brief through user interview and codebase exploration. Activate ONLY when the user says "new PRD", "plan a feature", or "write a PRD". Not for implementation specs, bug triage, or general feature discussion. |
Extract the real problem before anyone talks about solutions. This skill produces one artifact: a problem brief that grounds every downstream decision.
Activation guard: Only run this skill when the user explicitly requests a PRD. Do not activate on general feature discussions, bug reports, or implementation questions.
Ask these five questions. Do NOT proceed until all five have answers.
[SOLUTION IDEA].If the user leads with a solution ("build feature X"), redirect:
"Before we go there — what user problem does X solve? Who experiences it? What do they do today without it?"
Do not accept "users want X" as a problem statement. Probe: "What evidence do we have that this solves a real problem?"
Scan the repository for context relevant to the problem:
Report findings to the user. If greenfield with no codebase, skip to Step 3.
Create the output directory and write the artifact:
mkdir -p /tmp/prd-{name}
Copy the template from assets/problem-brief-template.md and fill every section from the interview and codebase exploration.
The problem brief is NOT complete unless ALL of these are true:
[SOLUTION IDEA]/tmp/prd-{name}/problem-brief.mdprd-interviewScaffold or repair `etc/http/` OpenCollection trees for Bruno. Use for new collections, brownfield standardization, or Bruno/Postman migration.
Control herdr (a terminal-native agent multiplexer) from inside it. Manage workspaces and tabs, split panes, spawn sibling agents, read pane output, and wait for state changes — all via CLI commands that talk to the running herdr instance over a local unix socket. Use when running inside herdr (HERDR_ENV=1). Do not use outside herdr.
Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub, GitLab, fp, or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `fp-plan`, `fp-implement`, `fp-review`, `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
Build a throwaway prototype to flush out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".