一键导入
viewer
Use when the user asks to open the SCC Artifact Viewer, show artifacts, inspect PDCA pipeline outputs, or after a PDCA pipeline run completes.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Use when the user asks to open the SCC Artifact Viewer, show artifacts, inspect PDCA pipeline outputs, or after a PDCA pipeline run completes.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when a vague idea needs Socratic requirements discovery, topology confirmation, ambiguity scoring, and an approval-gated spec before execution
Use when a prompt asset keeps causing the same PDCA gate failure and you want to evolve it against a maintainer-authored structural check
Use when running a PDCA cycle across research, production, review, and refinement
Use when iteratively improving a draft until it meets a review target
Use when reviewing content, strategy, or code with parallel specialized reviewers
Use when a fetched URL returns 4xx/blocked, hits a WAF or captcha, or when a JS-heavy SPA returns no usable body. Escalates through public APIs, Jina Reader, header-diverse curl, TLS impersonation, headless browsers, and free archive mirrors until validated content is returned. Zero API keys.
| name | viewer |
| description | Use when the user asks to open the SCC Artifact Viewer, show artifacts, inspect PDCA pipeline outputs, or after a PDCA pipeline run completes. |
| effort | low |
Always verify the artifact renders locally before sharing the URL.
server-info exists and the port responds before giving the user a URL — dead links erode trust.state.json and artifacts/*.json in the session directory — starting without them produces a blank page.server.pid or re-start before sharing.Opens a local web UI to view PDCA pipeline results as interactive artifacts.
Start the viewer for the current PDCA session:
bash ${CLAUDE_PLUGIN_ROOT}/ui/scripts/start-server.sh \
--session-dir "${SESSION_DIR}" \
--dist-dir "${CLAUDE_PLUGIN_ROOT}/ui/dist"
The script outputs JSON with the URL. Tell the user to open it in their browser.
state.json and artifacts/*.json to the session directory.scc/sessions/{session-id}/
├── state.json ← PDCA state (phases, current phase, durations)
├── artifacts/
│ ├── 001-research.json
│ ├── 002-draft.json
│ └── 003-analysis.json
└── state/
├── server-info ← Port, PID
└── server.pid
Each artifact file must have: id, type, phase, title, plus type-specific fields.
Markdown: { "type": "markdown", "content": "# Hello" }
Chart: { "type": "chart", "chartType": "bar|line|pie|radar", "data": { "labels": [], "datasets": [{ "values": [] }] } }
Code: { "type": "code", "language": "typescript", "code": "..." }
Flow: { "type": "flow", "nodes": [{ "id", "label", "x", "y" }], "edges": [{ "from", "to" }] }
bash ${CLAUDE_PLUGIN_ROOT}/ui/scripts/stop-server.sh --session-dir "${SESSION_DIR}"
The server also auto-stops after 30 minutes of inactivity.
cd ${CLAUDE_PLUGIN_ROOT}/ui
npm install
npm run dev # Vite dev server
npm test # Run tests
npm run build # Build dist/ for production