Memmy is a local memory hub that gives multiple AI agents one shared, persistent context about their user. It helps people continue work across agents such as Claude Code, Codex, OpenClaw, and Hermes Agent. The catalogue entries are skills for using Memmy with supported agents.
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 MemTensor/memmy-agent --skill pptxgit clone --depth 1 https://github.com/MemTensor/memmy-agentWrote 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/memtensor/memmy-agent/pptx)<a href="https://agentmods.dev/skills/memtensor/memmy-agent/pptx"><img src="https://agentmods.dev/badge/skills/memtensor/memmy-agent/pptx/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/memtensor/memmy-agent/pptx"><img src="https://agentmods.dev/badge/skills/memtensor/memmy-agent/pptx.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 | $0.00029 | $0.00813 |
| Opus 5.5 | $0.00012 | $0.00325 |
| Sonnet 5.5 | $0.00006 | $0.00163 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
pptx 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 25d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PPTX workflow
Use this skill whenever the input or requested output is a .pptx or .potx
presentation, slide deck, template, slide layout, speaker notes, comments, or
slide conversion. It is not a replacement for ordinary document or image
editing.
Decide the operation
- For a new deck, create one
pptxgenjspresentation, set its layout before adding slides, and keep charts and tables editable. - For an existing deck, copy it to a private temporary directory first. Use
scripts/inspect-style OOXML inspection through the checkers, then edit only requested parts withjszipand XML parsing. - To duplicate a slide use
scripts/clone_slide.mjs; do not copy one XML file by hand. To remove unused parts usescripts/prune_orphans.mjsonly after the final slide order is established. - For
.pptinput, convert a temporary copy withscripts/render_with_office.mjs --headless --convert-to pptxwhen the bundled Office payload supports it. Conversion failure is a hard failure.
Required quality sequence
- Work in a unique temporary directory and leave the source unchanged.
- Make all slide additions, deletions, and ordering changes.
- Fill content while preserving theme, notes, comments, media, charts, embedded objects, hidden slides, and user metadata.
- Run
scripts/check_deck.mjs <deck-or-directory> --json; pass--baseline <template>only for a template baseline. Use--auto-repaironly for the safe ID/relationship repairs reported by the checker. - Render with
scripts/render_with_office.mjs --headless --convert-to pdf <deck> --output-dir <dir>and inspect every page. Create a grid withscripts/make_contact_sheet.mjs --input <deck> --output-dir <dir> --prefix <unique-name>when a compact review is useful. - Reopen the output with the checker and confirm page count, notes, media, charts, hidden slides, and metadata before delivery.
Design and content checks
Set a deliberate 16:9 or standard layout before adding slides. Use six-digit hex colors without alpha in the color field, native bullets, speaker notes, and editable charts. Keep text left aligned, provide at least 0.5 inch safe margins, and avoid overflow, overlap, low contrast, placeholder text, and decorative edge bars. Typical sizes are 36–44 pt titles, 20–24 pt section titles, 14–16 pt body, and 10–12 pt notes. Font choice and any cross-platform rendering difference must be recorded in the QA report.
What ships with it
16 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.
- references/deck-workflow.md 1.0 KB
- references/ooxml-editing.md 738 B
- references/validation-and-rendering.md 967 B
- schemas/presentationml.xsd 585 B
- schemas/README.md 707 B
- schemas/SCHEMA-MANIFEST.json 334 B
- scripts/check_deck.mjs 4.0 KB runs code
- scripts/clone_slide.mjs 8.0 KB runs code
- scripts/make_contact_sheet.mjs 8.7 KB runs code
- scripts/office/check_chart_rules.mjs 4.7 KB runs code
- scripts/office/check_ooxml_package.mjs 6.9 KB runs code
- scripts/office/check_pptx_schema.mjs 5.0 KB runs code
- scripts/office/check_slide_rules.mjs 6.0 KB runs code
- scripts/office/check_theme_rules.mjs 5.6 KB runs code
- scripts/prune_orphans.mjs 7.5 KB runs code
- scripts/render_with_office.mjs 7.7 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.
- 25d ago First seen · 69 lines · 29 tokens per session scan A 0602ea7ab4a2
pptx is a skill published in the GitHub repository MemTensor/memmy-agent (2,102 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 813 once invoked, about $0.0001 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 2026-09-21.
Other skills, from other repositories
browserwing-executor
Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.
dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…
ask-user-question
Ask users questions via the UI. Use when you need clarification, user preferences, or confirmation before proceeding. The user CANNOT see CLI output - this tool is the ONLY way to communicate with them.
memos-memory-guide
Use the MemOS Local memory system to search and use the user's past conversations. Use this skill whenever the user refers to past chats, their own preferences or history, or when you need to answer from prior context. When auto-recall returns nothing (long or unclear user query), generate your own short search query…
pptagent
Create and revise editable PowerPoint presentations from a brief using HTML slide sources, rendering, and visual review. Use when the requested deliverable is a PPTX deck. The host authors the slides; text-only hosts can use an external visual reviewer.
awm-rsi-toolkit
Run AWM (Agent Workflow Memory, Wang et al. 2024) on an agent - induce reusable workflows from its successful trajectories, online over a training stream or offline from supplied experiences, then freeze the workflow memory and measure it on a published Benchmark.