Image to Editable PPT Skill converts slide images, PDFs, and image-based PowerPoint files into editable PowerPoint decks by separating recoverable text, simple shapes, and visual assets. It is for people who need to revise slides that originally exist only as screenshots or other flattened pages.
Borrowing it
Nothing to install: this file belongs to ningzimu/image-to-editable-ppt-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ningzimu/image-to-editable-ppt-skill/main/AGENTS.mdgit clone --depth 1 https://github.com/ningzimu/image-to-editable-ppt-skillWrote 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/instructions/ningzimu/image-to-editable-ppt-skill/agents-md)<a href="https://agentmods.dev/instructions/ningzimu/image-to-editable-ppt-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/ningzimu/image-to-editable-ppt-skill/agents-md/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/instructions/ningzimu/image-to-editable-ppt-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/ningzimu/image-to-editable-ppt-skill/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01772 | $0.01772 |
| Opus 5 | $0.00886 | $0.00886 |
| Sonnet 5 | $0.00354 | $0.00354 |
| Haiku 4.5 | $0.00177 | $0.00177 |
Grade A, and why
image-to-editable-ppt-skill AGENTS.md 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 9d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Scope
This repository packages the image-to-editable-ppt skill.
- Repository-level docs, examples, CI, and release metadata live at the repository root.
- The installable skill lives under
skills/image-to-editable-ppt/. - Generated conversion outputs belong in
output/and must not be committed. - Curated images or decks used by README/docs belong in
assets/.
Editing Rules
- Do not edit files under
skills/image-to-editable-ppt/unless the task explicitly asks to change the skill itself. - Keep public docs focused on user-facing facts: what the skill does, how to install it, how to use it, and its real limits.
- Documentation changes must update all existing language versions in sync, including repository README files and the usage documentation site. Keep headings, examples, capabilities, limitations, install steps, and output structure equivalent across languages.
- Do not copy internal discussion notes, temporary decisions, or unpublished release plans into README files.
Skill Documentation Architecture
The skill documentation under skills/image-to-editable-ppt/ follows a strict ownership model. Future edits must preserve it.
Design Principles
- One authoritative home per rule. Every requirement lives in exactly one file. Other files may carry at most a one-line pointer ("see
page-decision-tree.mdsection 3.1") — never a restated list, enumeration, or procedure. Duplicated statements drift apart and inflate the token cost of every run. - Reader-role split.
SKILL.mdis read by the parent/orchestrator agent; the references and the worker prompt are read by page workers. Parent-level rules (orchestration, dispatch, state machine, user interaction) belong inSKILL.md; page-level rules (object decisions, field contracts, QA) belong in the references. Do not let worker-level detail leak back intoSKILL.md. - Every rule is a recorded failure. Each requirement in these documents encodes a real past failure mode. Never delete a requirement during refactoring; when condensing or moving text, map every criterion to its new home first and verify nothing is lost. Tightening wording is welcome; dropping constraints is not.
- Explain why, not bare musts. Where a rule has a rationale (over-rounding is a common visible failure; nativizing text first locks in wrong object-source choices), state it briefly. Agents follow rules better when the failure they prevent is named.
- Reminders, not replacements. The worker prompt may carry a short hard-rules block (about five lines) restating the highest-risk red lines, each ending with a pointer to its authoritative home. This is the only sanctioned form of duplication.
- Docs and CLI move together. All run/page state transitions go through
editpptcommands. If a documented flow changes (for example: every page, including single-page input, is dispatched to a worker), the CLI behavior incli/and the tests intests/must change in the same PR. Docs must never describe a flow the CLI does not enforce. - Stable cross-references. Files refer to each other by section name and number (
page-decision-tree.mdsection 2.2, "Fix versus Warning"). When renaming or renumbering a section, grep the whole skill directory and update every referrer in the same change. - A reference file over ~300 lines gets a table of contents at the top.
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.
- 9d ago First seen · 95 lines · 1,772 tokens per session scan A 3ea224ecc58f
image-to-editable-ppt-skill AGENTS.md is an instructions file published in the GitHub repository ningzimu/image-to-editable-ppt-skill (2,412 stars, last pushed 1mo ago), licensed MIT. It adds 1,772 tokens to every session, about $0.0089 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.