qdrant-search-quality-diagnosis

A troubleshooting guide for Qdrant, a database used to search stored vectors such as text embeddings. It helps compare exact search with faster approximate search and check why results are missing or irrelevant.

In plain words
What is it for?
Use it to measure recall, test approximate search against exact results, investigate quality regressions, and choose fixes such as HNSW tuning or result grouping.
Why use it?
It gives a structured way to separate problems in the embedding model, filters, index settings, quantization, or duplicate document chunks.

Skill for Claude CodeCodex

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/secondlifes/code-intel/diagnosis
Any agent
npx skills add SecondLifes/code-intel --skill diagnosis
Clone the repo
git clone --depth 1 https://github.com/SecondLifes/code-intel

Made for: Claude Code, Codex.

Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,272 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00104 $0.01272
Opus 5 $0.00052 $0.00636
Sonnet 5 $0.00021 $0.00254
Haiku 4.5 $0.00010 $0.00127

Measured yesterday against content hash d752c3df5004, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qdrant-search-quality-diagnosis 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 yesterday.

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.

Origin

This is a copy

100% identical to qdrant-search-quality-diagnosis — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/qdrant-search-quality/diagnosis/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

How to Diagnose Bad Search Quality

Before tuning, establish baselines. Use exact KNN as ground truth, compare against approximate HNSW. Target >95% recall@K for production.

Don't Know What's Wrong Yet

Use when: results are irrelevant or missing expected matches and you need to isolate the cause.

  • For a no-code quick check, use the Web UI's ANN Recall tab to compare approximate vs exact recall@k Web UI ANN Recall
  • For the same comparison in code (CI gating, regression tests), run each query twice — once approximate, once with exact=true — and compute recall@k from the overlap ANN recall in CI
  • Exact search bad = model or search pipeline problem. Exact good, approximate bad = tune HNSW.
  • Check if quantization degrades quality (compare with and without)
  • Check if filters are too restrictive (then you might need to use ACORN)
  • If duplicate results from chunked documents, use Grouping API to deduplicate Grouping

Payload filtering and sparse vector search are different things. Metadata (dates, categories, tags) goes in payload for filtering. Text content goes in sparse vectors for search.

Approximate Search Worse Than Exact

Use when: exact search returns good results but HNSW approximation misses them.

Read the full file on GitHub · 66 lines

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. yesterday First seen · 66 lines · 104 tokens per session scan A d752c3df5004

Subscribe to this mod's changes

qdrant-search-quality-diagnosis is a skill published in the GitHub repository SecondLifes/code-intel (2 stars, last pushed 21d ago), licensed Apache-2.0. It adds 104 tokens to every session and 1,272 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to qdrant-search-quality-diagnosis, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens