본문으로 건너뛰기
cccskills
무료GitHub에 공개

sn-ppt-workbench

Open an existing SenseNova HTML slide deck in PPT Workbench for browser-based preview, inspection, and visual editing. Select a deck folder or find the latest local deck, with interactive agent chat available when a supported connection is configured.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

원문원문 설명 보기

Use when the user asks to open, preview, inspect, or visually edit an existing SenseNova HTML presentation in the PPT Workbench, using an explicit deck_dir or the latest deck in the current workspace.

연동 도구Docker
설치 방법 보기

이럴 때 유용합니다

  • Preview an existing HTML presentation in a browser
  • Open a specific deck folder for visual editing
  • Find and open the latest deck in the workspace
  • Access the editor through a forwarded remote URL

포함된 파일(26)

  • SKILL.md9.9 KB
  • references/gateway-auth.md5.4 KB
  • scripts/open_workbench.py20.9 KB
  • workbench-runtime/bin/sensenova-ppt-workbench.mjs19.5 KB
  • workbench-runtime/dist-server/index.mjs1.8 MB
  • workbench-runtime/dist/assets/index-DZ8oHsQz.js504.5 KB
  • workbench-runtime/dist/assets/index-Hn-wCKPf.css123.1 KB
  • workbench-runtime/dist/assets/MarkdownArtifactViewer-DxLTmGwT.js107.9 KB
  • workbench-runtime/dist/favicon.svg9.3 KB
  • workbench-runtime/dist/index.html519 B
  • workbench-runtime/dist/sensetime-mark.png24.5 KB
  • workbench-runtime/examples/sensenova-basic/asset_plan.json2.7 KB
  • workbench-runtime/examples/sensenova-basic/assets/echarts.min.js1009.9 KB
  • workbench-runtime/examples/sensenova-basic/info_pack.json384 B
  • workbench-runtime/examples/sensenova-basic/outline.json4.6 KB
  • workbench-runtime/examples/sensenova-basic/pages/page_001.html10.7 KB
  • workbench-runtime/examples/sensenova-basic/pages/page_001.query.txt1.6 KB
  • workbench-runtime/examples/sensenova-basic/pages/page_002.html9.3 KB
  • workbench-runtime/examples/sensenova-basic/pages/page_002.query.txt1.4 KB
  • workbench-runtime/examples/sensenova-basic/pages/page_003.html15.1 KB
  • workbench-runtime/examples/sensenova-basic/pages/page_003.query.txt1.6 KB
  • workbench-runtime/examples/sensenova-basic/pages/page_004.html5.6 KB
  • workbench-runtime/examples/sensenova-basic/pages/page_004.query.txt1.7 KB
  • workbench-runtime/examples/sensenova-basic/style_spec.json560 B
  • workbench-runtime/examples/sensenova-basic/task_pack.json576 B
  • workbench-runtime/package.json422 B

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

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 task_pack.json, slides/slide_NN.html, pages/page_NNN.html, or a root-level HTML deck.
  • 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 only under $(pwd)/ppt_decks. Other roots are considered only when the caller explicitly passes --search-root; never scan home folders by default.
  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.
  7. When launched from the unified PPT flow, use the exact absolute task_pack.deck_dir; opening the Workbench must not create or switch tasks.
  8. Treat task_pack.json as progress/resume state and outline.md as the user-editable Story. Existing runtime builds may expose only part of these artifacts; report compatibility gaps instead of regenerating the deck.

Invocation

Use the helper directly:

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

On native Windows where python3 is unavailable:

python $SKILL_DIR/scripts/open_workbench.py --deck-dir "<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 $SKILL_DIR/scripts/open_workbench.py \
  --deck-dir "<deck_dir>" \
  --agent-session-id "${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:-}"

--agent-transport may be omitted: the helper auto-selects gateway when the Hermes Gateway endpoint and key resolve (environment or Hermes .env files), then webui / acp / rest when only those details exist. Explicit flags and WORKBENCH_AGENT_TRANSPORT always win. With no resolvable bridge the bottom chat stays read-only by design.

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

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

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

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

When this helper runs inside Box Agent, the exported BOX_AGENT_PYTHON or BOX_AGENT_SKILL_TOOLS_ROOT environment automatically selects box-agent, acp, and the installed box-agent-acp command. Explicit WORKBENCH_AGENT_* flags or environment variables still take precedence.

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 <launcher> start   --deck-dir "<path>" [--port 0] [--agent-managed]
node <launcher> status  --deck-dir "<path>"
node <launcher> stop    --deck-dir "<path>"

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 <launcher> stop  --deck-dir "<path>"
node <launcher> start --deck-dir "<path>" --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 <launcher> start --deck-dir "<path>" --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:<editor_url>

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. The runtime packaged beside this Skill
  4. The nearest src/ppt-editor source checkout or packaged release in the current worktree
  5. Common ~/Repository/ppt-editor fallbacks

The helper does not build the editor during an end-user launch. Packaged Skills must include workbench-runtime; source checkouts must build src/ppt-editor explicitly before using its launcher. The repository-level webui/ directory is a separate product and is not a launcher fallback for this Skill.

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, Claude Code, and Box Agent should use ACP JSON-RPC adapters, configured with --acp-command or WORKBENCH_ACP_COMMAND. Box Agent defaults to its installed box-agent-acp entry point. 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, box-agent, 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
BOX_AGENT_ACP_COMMANDBox Agent / Workbench envOptional override for the default box-agent-acp adapter command

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:<reason>

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Compare counts and shares for two categories in Excel data. The skill cleans the selected columns, calculates differences and percentages, and produces a summary spreadsheet plus bar and pie charts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Comparing counts for two categories
  • Visualizing category shares
  • Cleaning merged-cell data before counting
OpenSenseNova/SenseNova-Skills5.9천2026년 10월 9일 업데이트

Analyze Excel data using custom categories, count distributions, and compare groups with charts. Score text using its length, technical terms, numbers, and selected complex concepts, then visualize difficulty levels and the relationship between text length and scores.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Summarize Excel records using custom categories
  • Compare category distributions across groups
  • Score and grade text using adjustable rules
OpenSenseNova/SenseNova-Skills5.9천2026년 10월 9일 업데이트

Count categories in a chosen data column after removing missing values and placeholder labels. Calculate each category’s share and create high-resolution charts combining counts, percentages, pie charts, and horizontal bars for distribution reports.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Compare record counts across categories
  • Show category shares with pie and bar charts
  • Exclude placeholder labels before counting
OpenSenseNova/SenseNova-Skills5.9천2026년 10월 9일 업데이트

Clean category and numeric fields in structured data, compare groups with counts and cross-tabulations, and produce charts, Excel results, and a Markdown report. Export visuals as high-resolution PNG and SVG files for use in reports.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Compare category distributions across groups
  • Clean category labels and fill merged-cell gaps
  • Export analysis results to Excel
OpenSenseNova/SenseNova-Skills5.9천2026년 10월 9일 업데이트

Filter Excel data using candidate column names, RGB color values, text prefixes, and regular expressions, which match text patterns. Calculate totals and averages, then export results to Excel with highlighted rows and a download link.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Filtering rows by RGB values or identifier prefixes
  • Converting text to numbers and calculating totals or averages
  • Extracting matching commands with their identifiers and descriptions
OpenSenseNova/SenseNova-Skills5.9천2026년 10월 9일 업데이트

Filter rows from Excel or previously converted Parquet files, a format designed for efficient data storage. Summarize matching records by group with counts, percentages, and totals, then export the summary to Excel.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Count records containing a specified risk level by work category
  • Calculate group shares among matching records
  • Summarize large datasets already converted to Parquet
OpenSenseNova/SenseNova-Skills5.9천2026년 10월 9일 업데이트

OpenSenseNova의 스킬 모두 보기

이 스킬의 문제 신고