ppt-revision-flow

ppt-revision-flow is a skill for Claude Code, Codex from aileron-platform/aileron. It costs 59 tokens per session (1,672 once invoked), scanned A, original, Apache-2.0.

A workflow for revising selected pages in an already completed PowerPoint presentation and exporting the updated deck.

In plain words
What is it for?
Use it to fix slides, revise one or more pages, update reviewed output, or re-export a revised PPTX or HTML deck.
Why use it?
It keeps changes focused on reviewed slides instead of treating the work as a new presentation. It also provides a defined process for retouching or regenerating page images.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/stage.py list --all --workspace /workspace.

Good fit Use it to fix slides, revise one or more pages, update reviewed output, or re-export a revised PPTX or HTML deck.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/aileron-platform/aileron
agentmods
npx agentmods add skills/aileron-platform/aileron/ppt-revision-flow

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for ppt-revision-flow

README.md
[![agentmods](https://agentmods.dev/badge/skills/aileron-platform/aileron/ppt-revision-flow/github.svg)](https://agentmods.dev/skills/aileron-platform/aileron/ppt-revision-flow)
Your own site
<a href="https://agentmods.dev/skills/aileron-platform/aileron/ppt-revision-flow"><img src="https://agentmods.dev/badge/skills/aileron-platform/aileron/ppt-revision-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.

agentmods 80×15 button for ppt-revision-flow

Your own site · 80×15
<a href="https://agentmods.dev/skills/aileron-platform/aileron/ppt-revision-flow"><img src="https://agentmods.dev/badge/skills/aileron-platform/aileron/ppt-revision-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,672 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.01672
Opus 5 $0.00030 $0.00836
Sonnet 5 $0.00012 $0.00334
Haiku 4.5 $0.00006 $0.00167

Measured 10d ago against content hash 5385962b19f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ppt-revision-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 10d 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.

workspace-runtime/agent-defaults/skills/ppt-revision-flow/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PPT Revision Flow

Use this skill for completed deck revision. It is not a new deck creation flow.

ppt-revision-flow shares the ppt-design-flow runtime. The active session, state, page image mapping, review shell, image adoption helpers, and deck builders live under:

/workspace/.aileron/canvases/ppt-design-flow/<session-id>/

The shared runtime commands are executed from the sibling ppt-design-flow skill directory (../ppt-design-flow/ relative to this skill).

Image retouch and regeneration reuse the shared subagent runtime in references/subagent-generation-runtime.md. Every revision image edit or regeneration, including a single page, MUST use bounded single-image subagent workers after explicit user authorization. Each image worker must use fork_context:false, call image generation/editing at most once, adopt exactly one revised page image, write orchestration metadata only to file-backed state, and finish with one short user-safe sentence. Worker final messages must not include JSON, internal paths, base64 payloads, data URLs, markdown image embeds, raw imageGeneration results, or raw image_generation_call results. If authorization is missing or denied, the revision flow must use the shared subagent authorization question tool and stop when authorization is not granted. The main thread must never generate or edit revised page images directly.

User-facing language guardrail

Use the same ppt-design-flow User-facing language guardrail for every normal reply:

Can the user see it, choose it, or act on it? If not, keep it internal.

Normal user-facing replies should contain only the user-visible outcome, the next action, and the decision the user can make. implementation details are internal unless the user explicitly asks for debugging or exact commands. Do not explain tools, file paths, data structures, runtime state, worker metadata, or orchestration steps in normal chat.

worker metadata is internal. Do not paste worker JSON, raw worker summaries, internal paths, manifests, or adopted-path lists into chat. Summarize revision completion in user-facing prose, for example: 已完成指定頁面的修改,審閱頁已更新,你可以再檢查一次,滿意後用下方表單確認通過。

Read the full file on GitHub · 135 lines

Files

What ships with it

5 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.

Changes

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.

  1. 10d ago First seen · 135 lines · 59 tokens per session scan A 5385962b19f9

Subscribe to this mod's changes

ppt-revision-flow is a skill published in the GitHub repository aileron-platform/aileron (11 stars, last pushed 17d ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,672 once invoked, about $0.0003 per session on Opus 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.

Related

Other skills, from other repositories