analyze
免费Risk analysis and approach selection before planning. Use when requirements are ambiguous, approaches vary, or work touches hub/bridge nodes. Skip for typo fixes.
中文简介正在准备中。当前显示原文说明。
Convert current conversation context into a structured Product Requirements Document (PRD) and optionally post it to GitHub Issues. Use before /supergraph:plan when requirements came from a conversation, user story, or feature discussion rather than a formal spec.
中文简介正在准备中。当前显示原文说明。
安装前可以查看交给 AI 代理的指令内容。
Turn conversation into a machine-readable PRD. Gives /supergraph:plan a concrete spec to work from.
Announce: "📋 /supergraph:prd — extracting requirements..."
head -60 CONTEXT.md 2>/dev/null || echo "No CONTEXT.md"
Use domain vocabulary from CONTEXT.md in the PRD — never invent new terms for existing concepts.
Gather from current conversation context:
Ask one clarifying question if a critical piece is missing. Do not ask multiple questions at once.
# PRD: [Feature/Fix Name]
## Problem
[One paragraph: what is broken or missing, and why it matters]
## Solution
[One paragraph: the approach — what will be built]
## User Stories
- As a [role], I want [action] so that [outcome]
- (2-5 stories max)
## Acceptance Criteria
- [ ] [Observable, testable condition]
- [ ] [Observable, testable condition]
- (Each maps to a test in /supergraph:plan)
## Implementation Decisions
- [Technology/pattern chosen and why]
- [What was explicitly ruled out and why]
## Testing Decisions
- [Unit: what gets unit tested]
- [Integration: what needs integration tests]
- [E2E: what needs Playwright coverage, if any]
## Out of Scope
- [Explicitly not included in this work]
## Notes
- [Domain terms: add to CONTEXT.md if new]
- [Dependencies on other work]
- [Security considerations]
Show PRD to user. Ask: "Does this capture what you need? [yes / adjust]"
Incorporate feedback, re-present if needed.
If user confirms and repo has GitHub remote:
gh issue create \
--title "[PRD] <feature name>" \
--body "$(cat <<'EOF'
[PRD content]
EOF
)" \
--label "enhancement,ready-for-agent"
Report issue URL.
Save to docs/supergraph/plans/YYYY-MM-DD-prd-<slug>.md.
If the PRD introduced new domain terms:
# Append to CONTEXT.md
printf '\n## <term>\n[definition from PRD]\n' >> CONTEXT.md
✅ /supergraph:prd complete
- PRD: docs/supergraph/plans/YYYY-MM-DD-prd-<slug>.md
- Issue: #N (if posted)
- Acceptance criteria: N
- Next: /supergraph:plan
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Risk analysis and approach selection before planning. Use when requirements are ambiguous, approaches vary, or work touches hub/bridge nodes. Skip for typo fixes.
中文简介正在准备中。当前显示原文说明。
Proactive architecture review — explore codebase structure, generate a self-contained HTML report with Mermaid diagrams and candidate improvements, then grill the findings. Use when planning a large refactor, onboarding to an unfamiliar codebase, or before a major architectural change.
中文简介正在准备中。当前显示原文说明。
Autonomous human-like browser control and professional QA/QC testing. Powered by agent-browser (Rust native CDP, zero Playwright) with ISTQB test matrix generation, automated testcase execution, console/network error tracing, and defect reporting.
中文简介正在准备中。当前显示原文说明。
Persistent token-compression mode (~75% reduction) — now always-on by default. Strips filler while keeping code exact.
中文简介正在准备中。当前显示原文说明。
Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs (Prisma, Drizzle, Kysely, Django, TypeORM, golang-migrate).
中文简介正在准备中。当前显示原文说明。
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
中文简介正在准备中。当前显示原文说明。