More screenshots
Works with the AI Agents you already use
slideops
Generate a slide deck or Markdown docs from your code, then check in milliseconds whether they still match the repo.
Free
slideops
Example session with this skill installed
Make a deck about how this repo's citation mechanism works. Use the Ledger Light theme, then check that every cited snippet still matches the code.
- Read your context and instructions
- Compiled the slideops
- Generated the document
Summary
Built a self-contained HTML deck about the citation mechanism, rendered every slide in headless Chrome to catch overflow, then ran the freshness check against the repository.
What the agent delivered
docs/slides/citations.html: one HTML file, no dependencies, arrow-key navigation, Esc for the overview grid- Every quoted snippet carries
data-src="path/file.py:40-58"and adata-sha256written bycite.py, never typed by hand - The
<head>records the build:<meta name="slideops-build" content="commit=... date=... repo=...">
Verification output (real check.py run on the demo deck shipped with the skill)
Deck: skill-demo.html
Built: commit=179bbdb date=2026-08-28 repo=slideops
Repo: /Users/gleb/software/slideops @ 8bcb425
slide 9 THEMING skills/slideops/assets/template.html:22-45 CURRENT
slide 14 MERMAID skills/slideops/references/diagrams.md:55-59 CURRENT
2 current, 0 stale, 2 cited in total.
| Status | Meaning |
|---|---|
| CURRENT | Same lines, same content |
| MOVED | Content is intact but the line range shifted |
| CHANGED | The code at that range was edited |
| MISSING | The file or snippet is gone |
| UNVERIFIED | Could not be checked |
Next steps
- Later, run
python3 scripts/check.py docs/slides/citations.html --repo .to see which slides drifted - Add
--jsonto get a repair brief (diff, causing commits, corrected attributes) so the agent rebuilds only the stale slides - Wire the same command into CI to fail the build when the deck stops matching the code
- Ask for a PDF export and the companion
slides-to-pdfskill does it
citations.html
PDF · document
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Technical documentation and presentations often become obsolete the moment the code changes. SlideOps solves this by generating HTML slide decks and Markdown docs grounded in the actual repository, using a citation system to verify accuracy. It eliminates the guesswork of "is this still true" by linking every code snippet and claim to specific file hashes and line ranges.
What it does
- Grounded generation Creates self-contained HTML slide decks or Markdown docs based on real repository code, logs, and architecture.
- Automated verification Uses a citation mechanism to check if documentation matches the current state of the repo in milliseconds.
- Drift detection Identifies moved, changed, or missing code references and provides a diff-based repair brief for stale slides.
- Visual consistency Offers four professional theme presets (Ledger, Midnight, Graphite) with responsive layouts and navigation.
- CI/CD integration Provides scripts to fail builds or annotate pull requests when documentation stops matching the code.
How it works
- Research The agent scans the repository, git history, and existing docs to propose concrete topics and an outline.
- Build The agent populates a self-contained HTML template with cited code snippets and Mermaid diagrams.
- Verify Headless Chrome renders each slide to ensure no text overlaps or layout breaks, while a Python script validates all citations.
- Sync You run
check.pyto identify drift; the agent then repairs only the specific slides that no longer match the code.
Frameworks & tools
This skill requires a headless Chrome or Chromium binary (system install or Playwright). It uses Python 3 for the verification scripts and interacts with repositories via standard git commands.
Why this beats prompting it yourself
Generic prompts often hallucinate code structure or produce layouts that break when rendered. SlideOps enforces a strict citation-and-hash system that makes documentation provably accurate and provides automated visual QA that manual prompting cannot replicate.
Use cases
- Onboarding decks Create a "project in one picture" overview for new hires that stays current.
- Deep-dive architecture Document complex subsystems with diagrams and snippets that link to real source files.
- Release summaries Generate "what's new" decks for stakeholders by analyzing recent git commits and diffs.
- Doc-to-code syncing Ensure Markdown design docs in the repo never drift from the implementation.
Known limitations
Requires a local Chrome/Chromium installation for visual verification. Mermaid diagrams and brand color extraction require optional network access. Designed for repository-based technical decks.
Requires headless Chrome/Chromium for visual QA. Citations only track file-based code; they cannot verify abstract prose claims not tied to snippets. Works best with Python 3 environments.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
1 use
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 1 month ago
- Free with an Agensi account
Requires