Skip to content

Refactor Qdrant monitoring and performance skills: flatten architecture - #88

Open
chadha-sridi wants to merge 4 commits into
mainfrom
refactor/qdrant-monitoring-and-performance
Open

Refactor Qdrant monitoring and performance skills: flatten architecture#88
chadha-sridi wants to merge 4 commits into
mainfrom
refactor/qdrant-monitoring-and-performance

Conversation

@chadha-sridi

@chadha-sridi chadha-sridi commented Jun 29, 2026

Copy link
Copy Markdown
Contributor

What this PR does

Restructures the performance and monitoring skill hierarchy: merges the diagnostic content from qdrant-monitoring/debugging into the three performance optimization sub-skills, so each skill covers both diagnosis and optimization in one place. Eliminates the redundancy and observed double-fetch pattern where agents loaded both monitoring/debugging and a performance skill for the same query.

Type

  • new skill
  • skill improvement
  • bug fix
  • repo hygiene

Checklist

  • python3 scripts/validate_skills.py passes
  • skill answers "when?" or "why?", not "how?"
  • skill navigates to docs, does not duplicate or replace them
  • description has Use when with 5+ trigger phrases
  • leaf skills omit allowed-tools, hub skills declare them
  • ends with ## What NOT to Do section
  • no code blocks except minimal snippets when absolutely required (reference the docs instead)
  • all doc links go to skills.qdrant.tech/md/documentation/
  • tested with a realistic prompt (paste below or link to eval)

Test prompt

Tested against a 16-prompt evaluation set across Opus 4.8, Sonnet, and Haiku 4.5, comparing v1 vs v2 routing behavior. Summary: Opus and Sonnet showed fewer turns on 15/16 and 12/16 prompts.
Example prompt

Our search service peaks at roughly 800 queries/sec today and we need to sustain ~3,000 QPS for a launch. Per-query latency is fine — we just can't hold the concurrent request rate and CPU pegs out. What's the path to higher throughput?

@netlify

netlify Bot commented Jun 29, 2026

Copy link
Copy Markdown

Deploy Preview for qdrant-skills ready!

Name Link
🔨 Latest commit cf51563
🔍 Latest deploy log https://app.netlify.com/projects/qdrant-skills/deploys/6a44df27fc2be100084b9194
😎 Deploy Preview https://deploy-preview-88--qdrant-skills.netlify.app
📱 Preview on mobile
Toggle QR Code...

QR Code

Use your smartphone camera to open QR code link.

To edit notification comments on pull requests, go to your Netlify project configuration.

@szabosteve szabosteve linked an issue Jun 30, 2026 that may be closed by this pull request

@szabosteve szabosteve left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you for this PR, I think this is a valuable improvement.

I think flattening these skills surfaces an overlap the hub previously hid. Both qdrant-search-speed and qdrant-scaling (this PR in its current form does not touch it) lists throughput issues in the description:

  • search-speed: low QPS and throughput too low
  • scaling: need more throughput, cluster is slow
    As the PR flattens the skill hierarchy, now these are on the same level, so they will likely compete. Also the body of search-speed says "Add replicas to distribute read load." (line 50), but I think it belongs rather to scaling than search-speed.

To fix this, I think we should make the distinction clear between tune and scale in a way that tune comes first and then scale when tuning is exhausted.

To do that:

  1. We should get rid of "need more throughput" and "cluster is slow" from the description of scaling and add something like:

    Guides Qdrant capacity and topology decisions: adding nodes, shards, or replicas, or splitting data across machines once a single node is already optimized and still can't keep up. Use when someone asks 'how many nodes do I need', 'data doesn't fit on one node', 'too many tenants', 'vertical or horizontal', 'how to shard', or 'need to add capacity'. For tuning an under-optimized node, see qdrant-search-speed.
    

    Or something along these lines. This suggestion is based on the current description and keeps everything that is relevant.

  2. Delete the "Add replicas..." bullet in search-speed. Replace it with something like: "If the node is already optimized (segments merged, quantization on, batching) and CPU is still saturated, that's a capacity limit: refer to qdrant-scaling."

If that's out-of-the-scope for this PR, then I think we need to open an issue and address that as soon as possible. However, I think these changes can fit into this PR as it would harmonize the skills' scopes according to the flattening effort.

I'd be curious to hear other people opinions, too, as I might miss some context.

Comment thread skills/qdrant-memory-usage/SKILL.md Outdated
Comment thread skills/qdrant-memory-usage/SKILL.md Outdated
- OS page cache - memory used for caching disk reads, which can be released when needed. Original vectors are normally stored in page cache, so the service won't crash if RAM is full, but performance may degrade.

It is normal for the OS page cache to occupy all available RAM, but if resident memory is above 80% of total RAM, it is a sign of a problem.
[Memory article](https://qdrant.tech/articles/memory-consumption/)

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You might want to add a more descriptive anchor text, so the agent will know why to follow it.

Suggested change
[Memory article](https://qdrant.tech/articles/memory-consumption/)
Refer to the [Memory consumption model](https://qdrant.tech/articles/memory-consumption/) for the full breakdown.

Or something along these lines.

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for the detailed review and suggestions! I agree that flattening the skills makes this overlap more visible. I’ll take a closer look at the current qdrant-scaling and qdrant-search-speed scopes and think through the best separation between tuning vs scaling. I’ll come back with an update.

kanungle
kanungle previously approved these changes Jun 30, 2026
Co-authored-by: István Zoltán Szabó <istvan.zoltan.szabo@qdrant.com>
@github-actions

Copy link
Copy Markdown
Contributor

this PR has been inactive for 14 days. it will be closed in 7 days unless there is new activity. if you're still working on it, push an update or leave a comment.

@github-actions github-actions Bot added the Stale label Jul 20, 2026
@kanungle

Copy link
Copy Markdown
Contributor

@chadha-sridi do you have additional changes you'd like to make to this?

@chadha-sridi

Copy link
Copy Markdown
Contributor Author

@kanungle Yes

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Flatten deeply nested skills

3 participants