agentmods.dev

slidesfly

slidesfly is a skill for Claude Code, Codex from rare/slidesfly-integrations. It costs 170 tokens per session (5,066 once invoked), scanned A, original, MIT.

A tool for putting an existing HTML slide deck online and returning a short sharing link. An HTML slide deck is a presentation stored as a web page rather than as a traditional presentation file.

In plain words
What is it for?
Use it to publish or share a self-contained HTML presentation, list existing published decks, or manage those decks when the required Slidesfly setup is available.
Why use it?
It avoids manually finding hosting and sharing setup for a finished local deck. It is intended for decks that already exist, not for creating the slides themselves.

Skill for Claude CodeCodex

Part of the slidesfly plugin — 1 skill, 1 MCP server shipped together

not rated 1 2d ago A scan 170 tokens original MIT
View the source file rare/slidesfly-integrations slidesfly.com
Install

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.

agentmods
npx agentmods add skills/rare/slidesfly-integrations/slidesfly
Any agent
npx skills add rare/slidesfly-integrations --skill slidesfly
Clone the repo
git clone --depth 1 https://github.com/rare/slidesfly-integrations

Made for: Claude Code, Codex.

Or install slidesfly, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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 slidesfly

README.md
[![agentmods](https://agentmods.dev/badge/skills/rare/slidesfly-integrations/slidesfly.svg)](https://agentmods.dev/skills/rare/slidesfly-integrations/slidesfly)
Your own site
<a href="https://agentmods.dev/skills/rare/slidesfly-integrations/slidesfly"><img src="https://agentmods.dev/badge/skills/rare/slidesfly-integrations/slidesfly.svg" alt="Measured on agentmods" height="20"></a>
Per session 170 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,066 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00170 $0.05066
Opus 5 $0.00085 $0.02533
Sonnet 5 $0.00034 $0.01013
Haiku 4.5 $0.00017 $0.00507

Measured 5d ago against content hash 5abb19c197ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

slidesfly 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 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/slidesfly.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

claude/slidesfly/skills/slidesfly/SKILL.md · 383 lines

How it starts

The opening of the file, as written. The whole thing — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Slidesfly Skill

Publish a local HTML deck to Slidesfly and return a shareable link on slidesfly.xyz.

Trigger conditions

Do trigger when all of the following are true:

  1. A local .html or .htm file already exists (or was just generated in this session).
  2. The user wants to publish, share, or manage an existing Slidesfly deck.

Examples that should trigger:

  • "Publish this deck and give me a link."
  • "把这个 HTML 演示稿发到网上。"
  • "Share the slides with my team."
  • "List my Slidesfly decks."
  • "Delete the deck we published yesterday."

Examples that should not trigger:

  • "Make me a 10-slide deck about RAG." (generate HTML first, then publish)
  • "Improve the typography on slide 3." (edit HTML first)
  • "What is Slidesfly?" (answer directly, no CLI)
  • "Convert this PDF to HTML." (different task)
  • "Deploy this Next.js app." (not a single HTML deck file)

Prerequisites

  1. HTML file on disk — single self-contained .html is best for v0.
  2. Node.js 22+ — required for the bundled runner, PATH CLI, and MCP.
  3. Prefer MCP when available — if the host has Slidesfly MCP configured (stdio @slidesfly/mcp or hosted https://slidesfly.com/api/mcp), use tools publish / list / versions / restore / claim / status (and set_api_key on stdio only) instead of shelling out to the CLI. Stdio shares ~/.slidesfly/config.json with the CLI; hosted uses Bearer sk_….
  4. Use the bundled runner by default — resolve the directory containing this SKILL.md as SKILL_DIR, then require $SKILL_DIR/scripts/slidesfly.mjs. It is the complete official CLI built from the same source as the PATH command, not a second API implementation. It performs no remote code download and shares ~/.slidesfly/config.json with the PATH CLI.
test -f "$SKILL_DIR/scripts/slidesfly.mjs"
node "$SKILL_DIR/scripts/slidesfly.mjs" --version   # expect 0.1.5+
node "$SKILL_DIR/scripts/slidesfly.mjs" publish ./deck.html --title "My Deck" --json

Read the full file on GitHub · 383 lines

Files

What ships with it

1 file 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. 5d ago First seen · 383 lines · 170 tokens per session scan A 5abb19c197ca

Subscribe to this mod's changes

slidesfly is a skill published in the GitHub repository rare/slidesfly-integrations (1 stars, last pushed 2d ago), licensed MIT. It adds 170 tokens to every session and 5,066 once invoked, about $0.0009 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 2026-08-31.

Creative and mediaai-agentsgithub-actionshtml-presentationsmarpmcprevealjs
Related

Other skills, from other repositories

install-loop

Install Loop Engineering into a project via the unified CLI front door (@cobusgreyling/loop). Prefer this over invoking loop-init / loop-audit separately. Week-one is report-only; never enable auto-merge or unattended fixes unless the human explicitly asks and doctor is healthy.

cobusgreyling/loop-engineering · 59 tokens

loop-verifier

Independent verification agent for loop-produced changes. Finds reasons to reject. Runs tests. Confirms diff scope. Use after minimal-fix or any implementer sub-agent — never in the same role as the implementer.

cobusgreyling/loop-engineering · 47 tokens

pr-review-triage

Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.

cobusgreyling/loop-engineering · 35 tokens

issue-triage

Scan open issues and discussions, deduplicate, prioritize, and propose labels. Provides a clean actionable queue.

cobusgreyling/loop-engineering · 26 tokens

changelog-scan

Scan merged PRs and commits since a given reference, extract titles, labels, types, and signals. Produces structured input for release notes drafting.

cobusgreyling/loop-engineering · 35 tokens

dependency-triage

Scan package manifests and lockfiles for outdated and vulnerable dependencies. Classify by severity and update type.

cobusgreyling/loop-engineering · 25 tokens