sn-ppt-standard
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 t
npx skills add OpenSenseNova/SenseNova-Skills --skill sn-ppt-standard --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Implements a standardized PPT production flow with a single CLI entry to orchestrate LLM/VLM/T2I calls. In standard mode, it plans with a three-sample deck preview (three concatenated deck images plus a preview URL), conducts web research and image search, and lets the user pick the final format (PPTX or PDF). In fast mode, it builds a complete draft immediately, then provides structured refinement suggestions for rapid iteration. Supports AI-generated infographics (U1), web image search, and ECharts for data charts.
How it works
- Invoked via /skill sn-ppt-entry; SNELL pipeline uses run_stage.py to execute per-stage shell commands and outputs one-line JSON status per stage.
- Preconditions require <deck_dir>/task_pack.json with ppt_mode in {"standard", "fast"} and <deck_dir>/info_pack.json; otherwise, the process stops and instructs entry through sn-ppt-entry.
- In standard mode: perform preflight, then style-samples, then style (selected sample), then outline, asset-plan, and per-item gen-image/page-html steps. After three-sample deck previews, user selects A/B/C and the agent promotes the chosen sample to style_spec.json before proceeding. A final export generates PPTX or PDF.
- In fast mode: skip the three-sample checkpoint, build the deck with autonomous defaults, then provide structured refinement suggestions (Quick wins, Standard-mode gaps, and Next actions) after generating the PPTX.
- All steps are deterministic: one input set → one output artifact → one-line JSON status. The final format is produced only via run_stage.py export.
When to use it
- Use standard mode when you want a user-backed, research-informed, three-sample deck preview before building the full presentation.
- Use fast mode when you need a quick draft and structured refinement guidance to iterate rapidly.
What it can touch
- Commands and scripts: emits one shell command per stage via scripts/run_stage.py; uses run_stage_with_progress.py as a WebUI progress wrapper.
- Tools declared: claude-code.
Caveats
- The skill must be invoked through /skill sn-ppt-entry and relies on deck_dir task and info packs existing.
- It does not write loops or prompts directly; generation logic resides in scripts/run_stage.py.
- The export must be done with run_stage.py export; other converters are not allowed.
- If data sources are missing, the process instructs to proceed with provided data or mocks and informs the user accordingly.
# sn-ppt-standard > **⚠️ This skill must be invoked through `/skill sn-ppt-entry`.** Never start here directly — the entry skill collects parameters, parses uploaded files, and writes `task_pack.json` + `info_pack.json` that this skill requires. If you arrived here without those files, stop and tell the user to enter via `/skill sn-ppt-entry` or "生成 PPT". This skill is **self-contained** — no dependency on `sn-image-base` for LLM/VLM (T2I still goes through `sn-image-base`). Generation logic stays in `$SKILL_DIR/scripts/run_stage.py`; use `run_stage_with_progress.py` only as a WebUI progress wrapper. Every subcommand is deterministic: one input set → one output artifact → one-line JSON status. ## Preconditions - `<deck_dir>/task_pack.json` exists and `ppt_mode in {"standard", "fast"}` - `<deck_dir>/info_pack.json` exists Any missing → stop and tell user to enter via `/skill sn-ppt-entry`. When `ppt_mode == "fast"`: **build first, then iterate.** Make decisions autonomously — do not ask the user about colors, fonts, page count, or layout preferences. Infer reasonable defaults from the query and start building immediately. Skip optional web search and image search. Run the full pipel
- Preconditions
- Post-generation (fast mode only)
- 🚫 Hard rules (the main agent MUST NOT)
- Visual quality standards
- Image sourcing
- Infographic slots (U1-generated diagrams)
- Image search as fallback
- No junk — hard constraint
- External research
- Pipeline
- Three-sample deck preview checkpoint (standard mode only)
- Generation progress WebUI launch
- How page-html works (two LLM calls per page)
- SN API model pitfall
sn-ppt-entry should already have started the generation progress WebUI after task_pack.json / info_pack.json were written. Run this only as an idempotent reuse/fallback check for resumed or direct-invocation sessions. Per-item forms — one progress line per item. PREFERRED for visibility: each exec returns quickly with status, keeping the user informed. Batch (concurrent) equivalents. Use when individual execs would exceed time budget. Batch commands block until ALL items complete. Concurrency for batch-page-html: 1 (≤4 pages), 2 (5-8 pages), 4 (9+ pages). Concurrency for batch-gen-image: default 4. For large decks, split into ranges to stay within the 300s execution limit:
What does the sn-ppt-standard skill do?
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 t
How do I install it?
Run `npx skills add OpenSenseNova/SenseNova-Skills --skill sn-ppt-standard --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From OpenSenseNova/SenseNova-Skills, a repository with 4,855 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.