Documents

sn-ppt-workbench

Try it

Open the AI PPT editing WebUI for previously generated SenseNova HTML slides. Use when the user asks to preview, inspect, edit, or open an existing/generated PPT deck in the WebUI/workbench without regenerating slides. Accepts an explicit deck_dir or auto-detects the newest local ppt_decks entry containing HTML pages. Does not run style/outline/page-html/export generation.

What it does

Open the AI PPT editing WebUI for previously generated SenseNova HTML slides. Use when the user asks to preview, inspect, edit, or open an existing/generated PPT deck in the WebUI/workbench without regenerating slides. Accepts an explicit deck_dir or auto-detects the newest local ppt_decks entry containing HTML pages. Does not run style/outline/page-html/export generation.

The skill document

sn-ppt-workbench

Start or reuse the AI PPT editing WebUI for an existing HTML slide deck. The helper prefers Hermes/canvas/port-forward URLs when available. Without a forwarded URL, native hosts bind to localhost by default, while Docker/WSL bind to 0.0.0.0 so remote users can reach the WebUI through the host network.

Use Cases

  • The user already generated a deck and asks to open the WebUI/editor/workbench.
  • The user provides a deck_dir containing pages/page_NNN.html or root-level .html slides.
  • The user says to inspect or edit previously generated slides without regenerating them.

Hard Rules

  1. Do not run sn-ppt-entry, sn-ppt-standard, page-html, batch-page-html, or export.
  2. Do not edit slide files directly. The WebUI handles user-visible editing.
  3. If deck_dir is missing, auto-detect the newest usable deck under:
    • $(pwd)/ppt_decks
    • ~/Downloads/ppt_decks
    • ~/Repository/ppt_decks
  4. If no usable deck is found, ask the user for the absolute deck_dir.
  5. Workbench startup is best-effort. If it skips or fails, report the reason and do not attempt generation as a fallback.
  6. Prefer a forwarded/canvas URL over localhost when the user may be on SSH, IM, or another remote device.

Invocation

Use the helper directly:

python3 $SKILL_DIR/scripts/open_workbench.py --deck-dir "" --agent-session-id "${HERMES_SESSION_KEY:-}"

On native Windows where python3 is unavailable:

python $SKILL_DIR/scripts/open_workbench.py --deck-dir "" --agent-session-id "%HERMES_SESSION_KEY%"

If the user did not provide a deck path, let the helper auto-detect:

python3 $SKILL_DIR/scripts/open_workbench.py --agent-session-id "${HERMES_SESSION_KEY:-}"

Pass same-session bridge details when available:

python3 $SKILL_DIR/scripts/open_workbench.py \
  --deck-dir "" \
  --agent-session-id "${HERMES_SESSION_KEY:-}" \
  --agent-managed 1 \
  --agent-provider hermes \
  --agent-transport gateway \
  --webui-base-url "${HERMES_WEBUI_BASE_URL:-}" \
  --gateway-base-url "${HERMES_GATEWAY_BASE_URL:-}"

For non-Hermes interactive providers, pass structured bridge details instead of scraping CLI/TUI output:

python3 $SKILL_DIR/scripts/open_workbench.py \
  --deck-dir "" \
  --agent-managed 1 \
  --agent-provider openclaw \
  --agent-transport rest \
  --agent-base-url "${WORKBENCH_AGENT_BASE_URL:-}" \
  --agent-api-key "${WORKBENCH_AGENT_API_KEY:-}"

python3 $SKILL_DIR/scripts/open_workbench.py \
  --deck-dir "" \
  --agent-managed 1 \
  --agent-provider codex \
  --agent-transport acp \
  --acp-command "${WORKBENCH_ACP_COMMAND:-codex-acp}"

For WorkBuddy, pass --agent-provider workbuddy only as provider identity. Tell the user clearly that WorkBuddy currently has no supported API or ACP interface for the interactive workbench bridge, so the WebUI can show WorkBuddy status but cannot send bottom-chat modification turns back to WorkBuddy.

CLI Subcommands (direct launch fallback)

When bypassing open_workbench.py and invoking the workbench launcher directly, use subcommands:

node  start   --deck-dir "" [--port 0] [--agent-managed]
node  status  --deck-dir ""
node  stop    --deck-dir ""

The old argument-only form (no subcommand) is deprecated — it will print a usage error.

Restart pitfall: start silently reuses an existing server instance for the same deck-dir (response contains "reused": true). If you updated the workbench code, you MUST run stop first, then start — otherwise the old process keeps serving stale code:

node  stop  --deck-dir ""
node  start --deck-dir "" --port 0

Bind Host

The workbench resolves its bind address from --host CLI flag → WORKBENCH_HOST env var → default 127.0.0.1. When the user needs remote/LAN access, set WORKBENCH_HOST=0.0.0.0:

export WORKBENCH_HOST=0.0.0.0
node  start --deck-dir "" --port 0

The response url field will then show the LAN IP instead of 127.0.0.1.

Output Handling

Parse the single JSON line from stdout.

When status == "ok", echo the returned editor_url, public_url, or workbench.editorUrl for existing-deck editing requests. The helper may also return generation_url; that URL is the generation progress page at /progress, while the editor is /editor.

PPT 编辑工作台已启动:

If workbench.reused == true, say it reused the existing server.

If bind_host is 0.0.0.0, the URL is a Docker/WSL LAN fallback. Tell the user it must be reachable from their device/network; if not, ask them to provide a Hermes/canvas/port-forward URL and rerun with --public-url, or an explicit bind host with --host.

When status == "skipped" or status == "failed", echo the reason field. If reason == "nodejs_missing", ask whether the user wants NodeJS/dependencies installed; if they decline, do not open the WebUI. Ask for a valid deck_dir only if the reason says no deck was found.

Environment

The helper locates the editor launcher in this order:

  1. SENSENOVA_PPT_WORKBENCH_CLI
  2. PPT_WORKBENCH_CLI
  3. ~/Repository/ppt-editor/src/ppt-editor/bin/sensenova-ppt-workbench.mjs
  4. ~/Repository/ppt-editor/tools/ppt-editor/bin/sensenova-ppt-workbench.mjs
  5. Legacy ~/Repository/ppt-editor/bin/sensenova-ppt-workbench.mjs
  6. Common sibling repo layouts

If the editor is not built, the helper runs npm run build in the ppt-editor repo unless --no-build is provided.

Remote URL discovery order:

  1. Explicit --public-url
  2. WORKBENCH_PUBLIC_URL, HERMES_WORKBENCH_PUBLIC_URL
  3. Hermes/canvas/forwarding env vars such as HERMES_CANVAS_URL, HERMES_PORT_FORWARD_URL, CANVAS_URL, PORT_FORWARD_URL, TUNNEL_URL
  4. Codespaces/Gitpod URL patterns
  5. Localhost on native hosts, or LAN fallback from the machine's non-loopback IPv4 address on Docker/WSL

Gateway Auth Setup

For writable interactive agent bridging (chat panel in workbench), Hermes keeps using the existing WebUI/Gateway protocol. OpenClaw should be exposed through a Gateway/REST-compatible HTTP endpoint. Codex and Claude Code should use ACP JSON-RPC adapters, configured with --acp-command or WORKBENCH_ACP_COMMAND. Never parse provider CLI/TUI output for chat synchronization.

For writable Hermes Gateway bridging, the Gateway API server and workbench must authenticate with matching API keys.

Key env vars:

VariableSet ByValue
API_SERVER_KEYGateway (.env)Shared secret
WORKBENCH_GATEWAY_API_KEYWorkbench envSame as API_SERVER_KEY; preferred explicit bridge key
HERMES_GATEWAY_BASE_URLWorkbench envhttp://127.0.0.1:8642
WORKBENCH_AGENT_PROVIDERWorkbench envhermes, openclaw, codex, claude-code, or workbuddy
WORKBENCH_AGENT_TRANSPORTWorkbench envwebui, gateway, rest, or acp
WORKBENCH_AGENT_BASE_URLWorkbench envOpenClaw/Gateway REST endpoint
WORKBENCH_AGENT_API_KEYWorkbench envREST provider bearer token
WORKBENCH_ACP_COMMANDWorkbench envACP adapter command, e.g. codex-acp

Quick steps:

  • Gateway: set API_SERVER_KEY in .env, restart gateway
  • Workbench: set WORKBENCH_GATEWAY_API_KEY to same value, set HERMES_GATEWAY_BASE_URL=http://127.0.0.1:8642
  • If no explicit bridge key is set, the Node relay falls back to API_SERVER_KEY, HERMES_GATEWAY_API_KEY, then backend-only AI_GATEWAY_API_KEY (ppt-editor-dev by default). Prefer the explicit bridge key for custom/shared gateways.

Progress Echo

Always send a short progress message before and after the helper:

WhenExample
Before helper正在启动 PPT 预览工作台,不会重新生成幻灯片...
SuccessPPT 编辑工作台已启动:http://127.0.0.1:18087
Generation progress URL available生成进度工作台:http://127.0.0.1:18087/progress
Skip/failurePPT 工作台未启动:

Related skills

Entry point for PPT generation. Asks the user to choose a mode (fast, standard, or creative), then collects role / audience / scene / page_count as needed. For standard mode, also asks how images should be sourced (AI generation, web search, or none), whether charts should use AI-generated infographics or ECharts, and whether the final deliverable should be PPTX or PDF. Parses uploaded pdf/docx/md/txt files, produces task_pack.json + info_pack.json in a new deck_dir, then dispatches to sn-ppt-creative or sn-ppt-standard. Fast mode skips optional questions and gets straight to building. Use when the user asks to make a PPT / presentation / 演示 / PPT. If the user asks to open, preview, inspect, or edit previously generated HTML slides in the WebUI/workbench without regenerating, dispatch to sn-ppt-workbench instead of this generation entry.

Creative-mode PPT pipeline. One full-page 16:9 PNG per slide. LLM / VLM calls go through sn-ppt-standard/lib/model_client.py (shared thin client). Text-to-image (the actual png rendering) goes through sn-image-base/scripts/sn_agent_runner.py. Falls back to web image search when T2I generation fails. Expects task_pack.json + info_pack.json already written by sn-ppt-entry.

Standard and fast PPT pipeline. All LLM / VLM / T2I calls are wrapped in a single CLI entry (scripts/run_stage.py). The main agent's job is simple: emit ONE shell command per stage, never write loops, never write prompts. Standard mode plans thoroughly with a three-sample deck preview checkpoint (three concatenated deck images plus a preview URL), web research, image search, and user-selected final output format (PPTX or PDF) for polished, delivery-ready presentations. Fast mode builds a complete draft immediately with autonomous decisions, then provides structured refinement suggestions so the user can iterate quickly. Supports AI-generated infographics (U1) for diagrams and flowcharts, web image search (Serper) for real photos, and ECharts for data charts.

Environment diagnostic for the PPT family. Validates sn-image-base, API keys, Node runtime, and optional deps; interactively writes .env for required vars. Runs before sn-ppt-entry; does not modify sn-image-* skills.

Environment diagnostic skill for SenseNova-Skills project. Checks that sn-image-base is properly installed and configured, validates dependencies and environment variables. Prompts user to configure missing required variables and saves them to .env file. After configuration, reloads environment and suggests agent restart if needed.

Update SenseNova Skills (the sn-* bundle) inside an OpenClaw or hermes-agent install. ALWAYS use this skill when the user says any of: "update SenseNova skills", "update SN skills", "更新 sensenova skills", "更新 sn skills", "刷新 sn-*", "升级 sn-* skills", or names a specific sn-* skill to update (e.g. "更新 sn-ppt-standard", "refresh sn-image-base"). Default scope is the whole sn-* bundle; if the user names specific skills, update ONLY those.