feat(skill): add slide reorder/remove script for agentic use#2640
Closed
nor3th wants to merge 1 commit into
Closed
feat(skill): add slide reorder/remove script for agentic use#2640nor3th wants to merge 1 commit into
nor3th wants to merge 1 commit into
Conversation
✅ Deploy Preview for slidev ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
nor3th
force-pushed
the
feat/slide-reorder-script
branch
from
June 19, 2026 21:18
9c23c32 to
e5704d8
Compare
Adds scripts/swap_slides.py to the Slidev skill with three operations: - swap N M — swap two slides by 1-based index - move N after|before M — reorder a slide relative to another - remove N — delete a slide Manually reordering slides via the Edit tool requires reading ~200 lines verbatim and constructing a large replacement — expensive in tokens and error-prone with Slidev's compound separators (---\nlayout: x\n---). The script handles both simple and compound separators correctly and runs in milliseconds. Documents usage in SKILL.md so Claude picks it up automatically and responds to natural language like "swap slides 3 and 7". Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
nor3th
force-pushed
the
feat/slide-reorder-script
branch
from
June 20, 2026 06:29
e5704d8 to
21f9148
Compare
Member
|
Thank you, I do like this idea but I would prefer to use our existing parser and the same js ecosystem, and then we might be able to do expose some tools via our cli instead of python script. I think we already have some sort of MCP support for the VS Code extension; bringing them to the CLI and the Web server might be a good idea (cc @kermanx). I am closing this PR for now but I am open for contributions around this idea. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Hi
I have found the approach quite great to develop the slides through agentic AI interaction using claude code. However for some tasks (swap slides, move slide 10 after the current slide 20 or delete slide 10) claude code used too many tokens and took too long, hence I let it develop those skill additions which make those tasks cheaper and faster.
I am not sure if it is in the project's scope to improve the claude code skills as well or a claude code skill and any other future additions should be conducted in separate repositories. Just let me know if additions like those are useful or if I should just keep them to my own fork.
I haven't written any test cases yet, but I can still work on those if necessary.
Summary
Adds scripts/slide_ops.py to the Slidev skill with three operations:
Manually reordering slides via the Edit tool requires reading ~200 lines verbatim and constructing a large replacement — expensive in tokens and error-prone with Slidev's compound separators (---\nlayout: x\n---). The script handles both simple and compound separators correctly and runs in milliseconds.
Documents usage in SKILL.md so Claude picks it up automatically and responds to natural language like "swap slides 3 and 7".