vs-search-tuning

vs-search-tuning is a skill for Claude Code, Codex from volcengine/SearchCLI. It costs 29 tokens per session (3,144 once invoked), scanned A, original, Apache-2.0.

A process for evaluating and tuning text-search similarity in an existing Viking AI Search application and dataset. It compares search queries with items and adjusts the configured recall strategy using relevance judgments.

In plain words
What is it for?
Use it to tune user-defined recall mode, text and image retrieval weights, keyword matching, and the maximum number of retrieved results.
Why use it?
It helps improve which results are retrieved for a query when the current matches are not relevant enough. It limits its scope to similarity and recall settings, rather than ranking or business rules.

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/volcengine/searchcli/vs-search-tuning
Any agent
npx skills add volcengine/SearchCLI --skill vs-search-tuning
Clone the repo
git clone --depth 1 https://github.com/volcengine/SearchCLI

Made for: Claude Code, Codex.

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 vs-search-tuning

README.md
[![agentmods](https://agentmods.dev/badge/skills/volcengine/searchcli/vs-search-tuning.svg)](https://agentmods.dev/skills/volcengine/searchcli/vs-search-tuning)
Your own site
<a href="https://agentmods.dev/skills/volcengine/searchcli/vs-search-tuning"><img src="https://agentmods.dev/badge/skills/volcengine/searchcli/vs-search-tuning.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,144 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 $0.00029 $0.03144
Opus 5 $0.00015 $0.01572
Sonnet 5 $0.00006 $0.00629
Haiku 4.5 $0.00003 $0.00314

Measured 4d ago against content hash a9955c045fec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vs-search-tuning 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 4d ago.

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.

skills/vs-search-tuning/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Viking Search Tuning

When to Use

Use this skill when the user wants an external agent to evaluate and tune text search similarity for an existing AI Search application and dataset.

This first version is for similarity tuning. It defaults to text-query/text-item judging, fixes mode=UserDefined, and tunes the user-defined recall strategy, recall weights, keyword match ratio, and max retrieved count. It can optionally use text+image LLM judging when visual relevance matters; image fields are taken only from GetAppDataConfig.ImageIndexFields. It does not tune rerank, personalization, hotness, boost/bury, sort rules, serving controls, or business operating rules.

Preconditions

  • an application-id is available
  • a dataset-id is preferred; if omitted, the CLI can try to infer a unique search dataset from the application
  • Viking auth is configured with vs auth status
  • LLM config is available through vs llm login, vs llm import-env, or VIKING_LLM_BASE_URL / VIKING_LLM_API_KEY / VIKING_LLM_MODEL when generating queries or using LLM relevance labels
  • a query file with sourceItemIds can be evaluated with --label-source source-item for a fast first-pass silver-label run without LLM relevance judging
  • the user understands that LLM relevance labels are silver labels and should be reviewed before high-risk production changes

Commands

  • llm login / llm import-env / llm status: configure and verify OpenAI-compatible LLM credentials without exposing API keys in chat or plain config
  • search tune llm-check: verify CLI-managed LLM configuration
  • search tune validate: validate a query set locally before planning or running; reports schema issues, duplicate ids/text, sourceItemIds coverage, query type skew, and a label-source recommendation
  • search tune query-generate: generate a reusable synthetic query set from paged dataset samples with batched concurrent LLM calls when the user has no query set; add --retrievable-field-only when the user wants generation constrained to text IndexFields from app dataset config, excluding ImageIndexFields
  • search tune plan: show query source, candidate strategies, estimated requests/labels, parameter coverage, source-item coverage, warnings, and suggested first-pass size before running
  • search tune run: generate or load queries, run candidate search strategies, label top results, compute metrics, and write artifacts; supports --label-source llm|source-item|auto, --judge-input text|text-image, --max-judge-images, --llm-retries, --max-label-failure-rate, and --verbose; use --resume-run-id <run-id> to continue an interrupted run
  • search tune report: read a previous tuning report
  • search tune compare: compare completed tuning runs with --run-ids, or compare existing scenes online with --scene-ids --queries using source-item silver labels
  • search tune apply: create a new candidate search scene from a completed tuning report recommendation
  • app status / doctor: verify app and local environment readiness

Read the full file on GitHub · 125 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. 4d ago First seen · 125 lines · 29 tokens per session scan A a9955c045fec

Subscribe to this mod's changes

vs-search-tuning is a skill published in the GitHub repository volcengine/SearchCLI (1,176 stars, last pushed 8d ago), licensed Apache-2.0. It adds 29 tokens to every session and 3,144 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

xerj-code

Reference-coding with XERJ. Clone the libraries that already solved your problem, index them locally, and retrieve the exact implementation before writing code — so the agent reads passages instead of re-deriving algorithms across retry loops. Use when starting a task in an unfamiliar API, porting an algorithm, or…

xerj-org/xerj · 79 tokens

xerj-security-audit

Coverage-guaranteed whitebox security audit of a codebase using XERJ + tree-sitter AST. Use when the user wants to security-review PHP (or other-language) code with a provable "we enumerated every dangerous call" guarantee, or asks to run the WordPress-style sink census / audit. Drives an index-once, query-read-reason…

xerj-org/xerj · 97 tokens

linkly-ai

Search, browse, read, and take notes across the user's documents indexed by Linkly AI — local files and linked cloud libraries. Use when the user asks to 'search my documents', 'find files about a topic', 'read a local document', 'what's in this folder', 'list the files in that library', 'browse document outlines'…

LinklyAI/linkly-ai-skills · 221 tokens

youtube-content

YouTube Data API — search, video details, channel info, transcripts.

furkangonel/cowrangler · 18 tokens

zero-api-key-web-search

OpenClaw skill for source-backed web search, page reading, and evidence-aware claim checking. No API keys required by default; optional providers can be enabled for stronger coverage. v23: multi-engine SERP (7 engines), Web Unlocker for blocked pages, auto-fallback on 403/429.

wd041216-bit/zero-api-key-web-search · 68 tokens

zero-api-key-web-search

Claude Code-compatible skill for source-backed web search, page reading, and evidence-aware claim checking. Use it when an answer depends on current facts, live sources, or explicit support/conflict handling. v23: multi-engine SERP (7 engines), Web Unlocker for blocked pages, auto-fallback on 403/429.

wd041216-bit/zero-api-key-web-search · 72 tokens