Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add aileron-platform/aileron --skill ppt-design-flowgit clone --depth 1 https://github.com/aileron-platform/aileronWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aileron-platform/aileron/ppt-design-flow)<a href="https://agentmods.dev/skills/aileron-platform/aileron/ppt-design-flow"><img src="https://agentmods.dev/badge/skills/aileron-platform/aileron/ppt-design-flow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aileron-platform/aileron/ppt-design-flow"><img src="https://agentmods.dev/badge/skills/aileron-platform/aileron/ppt-design-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00114 | $0.04050 |
| Opus 5.5 | $0.00046 | $0.01620 |
| Sonnet 5.5 | $0.00023 | $0.00810 |
| Haiku 4.5 | $0.00011 | $0.00405 |
Grade A, and why
ppt-design-flow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PPT Design Flow
A phase-driven design workflow that turns a vague PPT request into a generation-ready, preview-confirmed new deck. State is tracked by scripts/stage.py; canvas surfaces are built by assets/canvas/build.py. Both refuse to advance when phase preconditions are unmet.
This skill is the new deck entrance. If the user wants to revise an already completed deck, route them to $ppt-revision-flow instead of expanding this creation flow. $ppt-revision-flow uses the same runtime state under /workspace/.aileron/canvases/ppt-design-flow/<session-id>/.
I/O Contract
- Input: a PPT topic, rough goal, existing notes/materials, or complete report-like narrative for a new deck.
- Optional anchors: audience, page count or duration, school/company/lab/course/brand identity, use occasion, source files, and style constraints.
- Output: confirmed content basis, visual style previews or fast-mode style defaults, deck planning files, generated page visuals, review surface, and final
.pptxand/or standalone.htmldeck after approval. - Confirmation gates (in order): 需求確認 (
needs_confirmed), 風格確認 (style_locked), 風格拆解確認 (style_breakdown_confirmed), 產生前確認 (pre_generation_confirmed), 審閱確認 (review_approved). The bracketed snake_case is the gate id used bystage.py pass <gate_id>. - Default ratio: generate preview images and final page visuals in
16:9unless the user explicitly requests another ratio.
State-First Directive
State is the single source of truth. Every stage.py and build.py invocation MUST include --workspace /workspace explicitly; do not rely on WORKSPACE_DIR or implicit cwd. Always inspect state when entering a phase or when state is uncertain.
When entering a new conversation, or when the active session id is unknown, resume discovery is the first action:
python3 scripts/stage.py resume --workspace /workspace
Use python3 scripts/stage.py resume <query> --workspace /workspace when the user gives a title slug or partial session id. Use python3 scripts/stage.py list --workspace /workspace to inspect unfinished sessions and python3 scripts/stage.py list --all --workspace /workspace when completed sessions may be relevant. If resume returns exactly one session, continue with that session_id, current_phase, and phase_file. If it returns multiple candidates, use ppt-session-selection from phases/00-overview.md so the user chooses the exact session_id; do not guess.
What ships with it
55 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .gitignore 90 B
- assets/canvas_protocol.py 6.5 KB runs code
- assets/canvas/build.py 8.5 KB runs code
- assets/canvas/candidate_picker_shell/index.html 39 KB
- assets/canvas/preview_shell/index.html 58 KB
- assets/canvas/review_shell/index.html 64 KB
- assets/html_export/present.js 4.2 KB runs code
- assets/html_export/styles.css 3.2 KB
- assets/html_export/template.html 828 B
- assets/stage_state.py 35 KB runs code
- LICENSE 10 KB
- phases/00-overview.md 6.2 KB
- phases/10-intake.md 9.1 KB
- phases/20-content-basis.md 3.5 KB
- phases/30-style.md 18 KB
- phases/40-planning.md 3.9 KB
- phases/50-generation.md 9.9 KB
- phases/60-review.md 11 KB
- README.en.md 6.3 KB
- README.md 5.9 KB
- references/conversation_framework.md 11 KB
- references/fast_style_defaults.md 2.7 KB
- references/preview-flow.md 11 KB
- references/runtime-quickstart.md 5.5 KB
- references/style-system.md 4.5 KB
- references/subagent-generation-runtime.md 12 KB
- scripts/adopt_imagegen_output.py 7.3 KB runs code
- scripts/build_html_deck.py 5.7 KB runs code
- scripts/build_pptx_deck.py 2.3 KB runs code
- scripts/deck_builder_common.py 9.0 KB runs code
- scripts/find_imagegen_output.py 4.0 KB runs code
- scripts/render_review_markup.py 9.6 KB runs code
- scripts/stage.py 6.6 KB runs code
- templates/content_report_reference.md 3.4 KB
- templates/design_spec_reference.md 3.6 KB
- templates/slide_blueprint_reference.md 3.2 KB
- templates/spec_lock_reference.md 3.3 KB
- tests/conftest.py 1.3 KB runs code
- tests/deck_test_helpers.py 2.2 KB runs code
- tests/requirements.txt 33 B
- tests/test_adopt_imagegen_output.py 6.8 KB runs code
- tests/test_build_html_deck.py 5.6 KB runs code
- tests/test_build_pptx_deck.py 2.1 KB runs code
- tests/test_canvas_builders.py 16 KB runs code
- tests/test_fast_flow_e2e.py 1.6 KB runs code
- tests/test_fast_flow_recovery.py 704 B runs code
- tests/test_fast_mode_flag.py 2.2 KB runs code
- tests/test_find_imagegen_output.py 1.9 KB runs code
- tests/test_gate_enforcement.py 2.5 KB runs code
- tests/test_output_formats_flag.py 1.8 KB runs code
- tests/test_resume_discovery.py 8.9 KB runs code
- tests/test_run_output_folder.py 3.7 KB runs code
- tests/test_runtime_documentation.py 16 KB runs code
- tests/test_show_includes_new_flags.py 571 B runs code
- tests/test_stage_state.py 15 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 230 lines · 114 tokens per session scan A d18b9c1f40c5
ppt-design-flow is a skill published in the GitHub repository aileron-platform/aileron (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 114 tokens to every session and 4,050 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
apify-youtube-transcript-scraper
Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.