#777 by GitHub stars
volcengine/SearchCLI
Open CLI for integrating AI search, recommendation, and conversational retrieval into agent systems and business systems
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/vs-alias-mapping/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → cba429a719e3
No earlier version was observed for comparison.
skills/vs-chat/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → cba429a719e3
No earlier version was observed for comparison.
skills/vs-crawler/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → cba429a719e3
No earlier version was observed for comparison.
skills/vs-item-onboarding/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → cba429a719e3
No earlier version was observed for comparison.
skills/vs-product-qa/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → cba429a719e3
No earlier version was observed for comparison.
skills/vs-product-qa/references/volcengine-documentation/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → cba429a719e3
No earlier version was observed for comparison.
skills/vs-project/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → cba429a719e3
No earlier version was observed for comparison.
skills/vs-recommend/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → cba429a719e3
No earlier version was observed for comparison.
skills/vs-search/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → cba429a719e3
No earlier version was observed for comparison.
skills/vs-search-tuning/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → cba429a719e3
No earlier version was observed for comparison.
skills/vs-search-tuning-partial-case/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → cba429a719e3
No earlier version was observed for comparison.
skills/vs-search-tuning-specify-policy-direction/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → cba429a719e3
No earlier version was observed for comparison.
skills/vs-shared/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → cba429a719e3
No earlier version was observed for comparison.
skills/vs-user-onboarding/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → cba429a719e3
No earlier version was observed for comparison.
Heat
3.3- Star growth, last 7 daysAhead of 60% of tracked repositories
- Star growth, last 24 hoursAhead of 5% of tracked repositories
- Rank movement, last 7 daysAhead of 4% of tracked repositories
- Commits, last 30 daysAhead of 73% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- vs-alias-mapping
skills/vs-alias-mapping - vs-chat
skills/vs-chat - vs-crawler
skills/vs-crawler - vs-item-onboarding
skills/vs-item-onboarding - vs-product-qa
skills/vs-product-qa - volcengine-documentation
skills/vs-product-qa/references/volcengine-documentation - vs-project
skills/vs-project - vs-recommend
skills/vs-recommend - vs-search
skills/vs-search - vs-search-tuning
skills/vs-search-tuning - vs-search-tuning-partial-case
skills/vs-search-tuning-partial-case - vs-search-tuning-specify-policy-direction
skills/vs-search-tuning-specify-policy-direction - vs-shared
skills/vs-shared - vs-user-onboarding
skills/vs-user-onboarding
How it works
vs-alias-mapping
When your agent uses it
Provide system alias mapping for Search CLI. Invoke this skill when user mentions "Search CLI", "search_cli", or tries to execute search_cli commands.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
787 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Version Check
- Preconditions
- Commands
- Workflow
- Customer Environment Principle
- Constraints
- Examples
Scripts executed separately
../../scripts/install-skills.ps1../../scripts/install-skills.sh../../scripts/install.ps1../../scripts/install.sh
Files
../../scripts/install-skills.ps1runs4,333 bytes../../scripts/install-skills.shruns5,203 bytes../../scripts/install.ps1runs2,064 bytes../../scripts/install.shruns2,026 bytesSKILL.mdcore3,554 bytesSKILL.mdcore3,554 bytesSKILL.mdcore3,554 bytesSKILL.mdcore3,554 bytesSKILL.mdcore3,554 bytesSKILL.mdcore3,554 bytes
Read SKILL.md
# Search CLI Alias Mapping
## When to Use
Invoke this skill when the user refers to the CLI tool as "Search CLI" or "search_cli", to ensure the correct underlying binary (`vs`) is executed.
## Version Check
Before starting this skill workflow, run `vs version check --json`. Continue only when `status` is `up-to-date`. If `status` is `update-available`, stop and tell the user to update the cloned `vs` repository, then run `git pull --ff-only`, `bash ./scripts/install.sh`, and `bash ./scripts/install-skills.sh all --target auto --force` (PowerShell: `scripts/install.ps1` and `scripts/install-skills.ps1`). If the status is `unknown`, stop and report that the CLI version could not be verified.
## Preconditions
- The agent is about to execute a CLI command based on the user's "Search CLI" intent.
## Commands
- No specific commands are required; this is a conceptual mapping.View the complete source on GitHubvs-chat
When your agent uses it
Conversational search runtime: send messages, keep sessions consistent, and verify retrieval behavior and responses.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
678 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Version Check
- Preconditions
- Commands
- Workflow
- Customer Environment Principle
- Constraints
Scripts executed separately
../../scripts/install-skills.ps1../../scripts/install-skills.sh../../scripts/install.ps1../../scripts/install.sh
Files
../../scripts/install-skills.ps1runs4,333 bytes../../scripts/install-skills.shruns5,203 bytes../../scripts/install.ps1runs2,064 bytes../../scripts/install.shruns2,026 bytesSKILL.mdcore3,246 bytesSKILL.mdcore3,246 bytesSKILL.mdcore3,246 bytesSKILL.mdcore3,246 bytesSKILL.mdcore3,246 bytesSKILL.mdcore3,246 bytes
Read SKILL.md
# Viking Chat
## When to Use
Use this skill for conversational search requests, session continuity, multi-turn checks, retrieval verification, and response inspection.
## Version Check
Before starting this skill workflow, run `vs version check --json`. Continue only when `status` is `up-to-date`. If `status` is `update-available`, stop and tell the user to update the cloned `vs` repository, then run `git pull --ff-only`, `bash ./scripts/install.sh`, and `bash ./scripts/install-skills.sh all --target auto --force` (PowerShell: `scripts/install.ps1` and `scripts/install-skills.ps1`). If the status is `unknown`, stop and report that the CLI version could not be verified.
## Preconditions
- an `application-id` is available
- the application is preferably already readyView the complete source on GitHubvs-crawler
When your agent uses it
Crawl websites (news, blogs, papers, GitHub, product docs, RSS feeds) into a fixed-schema JSONL file, then create a dataset and a searchable application in Viking AI Search. Supports one-time crawl and scheduled recurring crawl with automatic incremental sync.
What it loads into context
Frontmatter
160 tokensAlways available to the agent
SKILL.md
3,728 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Version Check
- Fixed Schema
- Preconditions
- Commands
- Workflow
- Customer Environment Principle
- Constraints
- Recovery Hints
Scripts executed separately
../../scripts/install-skills.ps1../../scripts/install-skills.sh../../scripts/install.ps1../../scripts/install.sh
Files
../../scripts/install-skills.ps1runs4,333 bytes../../scripts/install-skills.shruns5,203 bytes../../scripts/install.ps1runs2,064 bytes../../scripts/install.shruns2,026 bytesSKILL.mdcore15,876 bytesSKILL.mdcore15,876 bytesSKILL.mdcore15,876 bytesSKILL.mdcore15,876 bytesSKILL.mdcore15,876 bytesSKILL.mdcore15,876 bytesSKILL.mdcore15,876 bytesSKILL.mdcore15,876 bytes
Read SKILL.md
# Viking Content Crawler
## When to Use
Use this skill when the user wants to crawl content from websites and import it into Viking AI Search to build a searchable knowledge base. This covers news sites, blogs, academic papers, GitHub repositories, product documentation, RSS feeds, and similar web content sources.
The agent writes crawler code tailored to the target sites, outputs data in a fixed JSONL schema, and then hands off to the `vs-item-onboarding` skill for dataset creation and import.
Do not use this skill when:
- The user already has a local file ready to import (use `vs-item-onboarding` directly).
- The user wants to import from a database (use `vs-item-onboarding` directly with MySQL).
## Version CheckView the complete source on GitHubvs-item-onboarding
When your agent uses it
onboarding workflow for creating datasets and applications in Viking AI Search. Supports one-time import from local files (JSON, JSONL, CSV) and MySQL databases, plus scheduled incremental sync for append-only JSONL files and MySQL. All sources are first exported to a bootstrap JSONL file; backend-driven schema inference handles detection, and optional background sync keeps the dataset up to date as new data arrives.
What it loads into context
Frontmatter
248 tokensAlways available to the agent
SKILL.md
13,196 tokensWhen the skill is activated
Reference documents
869 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Language Matching (apply throughout)
- When to Use
- Do NOT be misled by `vs --help` top-level QUICK START
- Version Check
- Preconditions
- Commands
- Workflow
- Enum Reference
- Backend-driven Primary Key
- V2 API Surface (reference)
- Customer Environment Principle
- Constraints
- Recovery Hints
- Worked Example
Scripts executed separately
../../scripts/install-skills.ps1../../scripts/install-skills.sh../../scripts/install.ps1../../scripts/install.sh
Files
../../scripts/install-skills.ps1runs4,333 bytes../../scripts/install-skills.shruns5,203 bytes../../scripts/install.ps1runs2,064 bytes../../scripts/install.shruns2,026 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesSKILL.mdcore55,445 bytesreferences/worked-example.mddoc3,078 bytes
Read SKILL.md
# Viking Item Onboarding
## Language Matching (apply throughout)
Match the language of the **user's most recent message** in every line of prose you write — confirmation prompts, status notes, hand-off summaries, questions, error explanations, **and any internal thinking / reasoning / planning output that the host may surface (e.g. `<thinking>` blocks, "thinking" panels, scratchpad notes, todo descriptions)**. If the user is writing in Chinese, every prose line and every reasoning line must also be in Chinese; if English, English; same for Japanese, etc. The fact that this skill file is written in English is for documentation only — at runtime translate all **prose and reasoning** into the user's language. Do not switch back to English mid-flow just because the surrounding skill text is English.
**Chinese-user priority (the most common case)** — when `current_query` or the most recent user message is in Chinese:
- All prose you write for the user (confirmation prompts, status notes, error explanations, final hand-off summaries) must be in Chinese.
- All internal thinking / reasoning / planning output (thinking blocks, scratchpad, todo descriptions) must also be in Chinese.
- For workspace artifacts you create, the description / comment portions (excluding CLI-contract English identifiers) should also prefer Chinese.
Do **not** translate the following — keep them verbatim so the contract stays machine-checkable:
View the complete source on GitHubvs-product-qa
When your agent uses it
Answer Viking AI Search product questions, CLI usage questions, API/auth questions, configuration questions, and troubleshooting questions by grounding every claim in either the installed `vs` CLI's own output or official Volcengine documentation. Never fabricate.
What it loads into context
Frontmatter
160 tokensAlways available to the agent
SKILL.md
4,173 tokensWhen the skill is activated
Reference documents
146,591 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Version Check
- Preconditions
- Core Principle
- Question Routing
- Knowledge Sources
- Commands
- Workflow
- Output Format
- Constraints
- Delegation
- Examples
- References
Scripts executed separately
../../scripts/install-skills.ps1../../scripts/install-skills.sh../../scripts/install.ps1../../scripts/install.sh
Files
../../scripts/install-skills.ps1runs4,333 bytes../../scripts/install-skills.shruns5,203 bytes../../scripts/install.ps1runs2,064 bytes../../scripts/install.shruns2,026 bytesSKILL.mdcore18,291 bytesSKILL.mdcore18,291 bytesSKILL.mdcore18,291 bytesSKILL.mdcore18,291 bytesSKILL.mdcore18,291 bytesSKILL.mdcore18,291 bytesSKILL.mdcore18,291 bytesSKILL.mdcore18,291 bytesSKILL.mdcore18,291 bytesSKILL.mdcore18,291 bytesSKILL.mdcore18,291 bytesSKILL.mdcore18,291 bytesSKILL.mdcore18,291 bytesSKILL.mdcore18,291 bytesSKILL.mdcore18,291 bytesSKILL.mdcore18,291 bytesreferences/aksk-notice.mddoc769 bytesreferences/api-references/README.mddoc3,688 bytesreferences/api-references/control-plane/README.mddoc2,134 bytesreferences/api-references/control-plane/application/AttachDatasetToApplicationV2.mddoc4,024 bytesreferences/api-references/control-plane/application/CreateApplicationV2.mddoc4,143 bytesreferences/api-references/control-plane/application/DeleteApplication.mddoc1,633 bytesreferences/api-references/control-plane/application/GetAppDataConfig.mddoc14,410 bytesreferences/api-references/control-plane/application/GetApplication.mddoc16,378 bytesreferences/api-references/control-plane/application/GetPersonalizedInfo.mddoc2,670 bytesreferences/api-references/control-plane/application/ListAppDataConfigs.mddoc14,609 bytesreferences/api-references/control-plane/application/ListApplications.mddoc13,441 bytesreferences/api-references/control-plane/application/ListApplicationsMeta.mddoc6,905 bytesreferences/api-references/control-plane/application/ListIndexStatusV2.mddoc3,277 bytesreferences/api-references/control-plane/application/README.mddoc3,250 bytesreferences/api-references/control-plane/application/UnBindAppDataset.mddoc14,547 bytesreferences/api-references/control-plane/application/UpdateAppDataConfig.mddoc16,257 bytesreferences/api-references/control-plane/application/UpdateAppItemFilter.mddoc1,876 bytesreferences/api-references/control-plane/application/UpdateApplication.mddoc16,755 bytesreferences/api-references/control-plane/dataset/CheckDatasetSchema.mddoc14,562 bytesreferences/api-references/control-plane/dataset/CreateDatasetV2.mddoc8,917 bytesreferences/api-references/control-plane/dataset/DeleteDataset.mddoc1,527 bytesreferences/api-references/control-plane/dataset/GetDataset.mddoc15,901 bytesreferences/api-references/control-plane/dataset/ListDatasets.mddoc14,101 bytesreferences/api-references/control-plane/dataset/README.mddoc1,644 bytesreferences/api-references/control-plane/dataset/UpdateDataset.mddoc21,334 bytesreferences/api-references/control-plane/dict/BindDictToScenes.mddoc1,936 bytesreferences/api-references/control-plane/dict/CheckDictInput.mddoc6,269 bytesreferences/api-references/control-plane/dict/CreateDict.mddoc3,261 bytesreferences/api-references/control-plane/dict/DeleteDict.mddoc1,517 bytesreferences/api-references/control-plane/dict/GetDict.mddoc2,947 bytesreferences/api-references/control-plane/dict/ListDicts.mddoc3,235 bytesreferences/api-references/control-plane/dict/ListDictsBindScene.mddoc2,626 bytesreferences/api-references/control-plane/dict/ListDictsWordNum.mddoc2,205 bytesreferences/api-references/control-plane/dict/README.mddoc1,901 bytesreferences/api-references/control-plane/dict/UpdateDict.mddoc3,124 bytesreferences/api-references/control-plane/ingestion/CloseDataSourceSubscription.mddoc1,884 bytesreferences/api-references/control-plane/ingestion/CreateDataSourceSubscription.mddoc3,721 bytesreferences/api-references/control-plane/ingestion/GetDataSourceSubscription.mddoc2,227 bytesreferences/api-references/control-plane/ingestion/ListDataSourceSubscriptions.mddoc2,171 bytesreferences/api-references/control-plane/ingestion/README.mddoc1,611 bytesreferences/api-references/control-plane/scene/CreateRecommendSceneV2.mddoc5,514 bytesreferences/api-references/control-plane/scene/CreateSearchSceneV2.mddoc17,507 bytesreferences/api-references/control-plane/scene/DeleteRecommendRuleV2.mddoc1,296 bytesreferences/api-references/control-plane/scene/DeleteRecommendSceneV2.mddoc1,227 bytesreferences/api-references/control-plane/scene/DeleteSearchSceneV2.mddoc2,331 bytesreferences/api-references/control-plane/scene/GetAppOnlineConfigV2.mddoc5,657 bytesreferences/api-references/control-plane/scene/GetRecommendRuleV2.mddoc2,642 bytesreferences/api-references/control-plane/scene/GetRecommendSceneV2.mddoc4,634 bytesreferences/api-references/control-plane/scene/GetSearchSceneV2.mddoc17,648 bytesreferences/api-references/control-plane/scene/ListRecommendRulesV2.mddoc3,532 bytesreferences/api-references/control-plane/scene/ListRecommendScenesV2.mddoc4,877 bytesreferences/api-references/control-plane/scene/ListSearchScenesV2.mddoc10,911 bytesreferences/api-references/control-plane/scene/PublishAppOnlineConfigV2.mddoc6,926 bytesreferences/api-references/control-plane/scene/PublishRecommendSceneV2.mddoc17,500 bytesreferences/api-references/control-plane/scene/PublishSearchSceneV2.mddoc36,242 bytesreferences/api-references/control-plane/scene/README.mddoc3,776 bytesreferences/api-references/control-plane/scene/UpsertRecommendRuleV2.mddoc6,368 bytesreferences/api-references/control-plane/task/AddInferDatasetSchemaTaskV2.mddoc2,187 bytesreferences/api-references/control-plane/task/CreateDatasetImageRetryTask.mddoc1,906 bytesreferences/api-references/control-plane/task/GetDatasetImageRetryTask.mddoc1,763 bytesreferences/api-references/control-plane/task/GetInferDatasetSchemaResultV2.mddoc6,840 bytesreferences/api-references/control-plane/task/GetPresignedImportUrlV2.mddoc1,751 bytesreferences/api-references/control-plane/task/README.mddoc1,704 bytesreferences/api-references/control-plane/usage/CalculateBillingOrderPrice.mddoc6,253 bytesreferences/api-references/control-plane/usage/CreateBillingOrderV2.mddoc6,712 bytesreferences/api-references/control-plane/usage/GetAppItemDataCountV2.mddoc3,356 bytesreferences/api-references/control-plane/usage/GetBillingOrderV2.mddoc3,826 bytesreferences/api-references/control-plane/usage/GetDataItemSummary.mddoc1,842 bytesreferences/api-references/control-plane/usage/GetDatasetDataCount.mddoc1,771 bytesreferences/api-references/control-plane/usage/GetDatasetStatistics.mddoc3,257 bytesreferences/api-references/control-plane/usage/GetQuota.mddoc8,899 bytesreferences/api-references/control-plane/usage/ListBillingUsageData.mddoc2,765 bytesreferences/api-references/control-plane/usage/README.mddoc2,631 bytesreferences/api-references/control-plane/usage/UpdateBillingOrderRenewSettings.mddoc3,162 bytesreferences/api-references/data-plane/README.mddoc1,616 bytesreferences/api-references/data-plane/data-api/BatchImport.mddoc1,978 bytesreferences/api-references/data-plane/data-api/CompleteBatchImportTask.mddoc1,674 bytesreferences/api-references/data-plane/data-api/CreateBatchImport.mddoc1,744 bytesreferences/api-references/data-plane/data-api/DeleteData.mddoc1,392 bytesreferences/api-references/data-plane/data-api/DeleteTerms.mddoc1,680 bytesreferences/api-references/data-plane/data-api/GetBatchImportStatus.mddoc1,841 bytesreferences/api-references/data-plane/data-api/GetItem.mddoc4,567 bytesreferences/api-references/data-plane/data-api/ListItems.mddoc6,023 bytesreferences/api-references/data-plane/data-api/ListTerms.mddoc1,597 bytesreferences/api-references/data-plane/data-api/README.mddoc2,152 bytesreferences/api-references/data-plane/data-api/WriteData.mddoc1,416 bytesreferences/api-references/data-plane/data-api/WriteTerms.mddoc1,800 bytesreferences/api-references/data-plane/online-api/BrowseIndex.mddoc5,236 bytesreferences/api-references/data-plane/online-api/Deduplicate.mddoc2,597 bytesreferences/api-references/data-plane/online-api/QueryCompletionWithScene.mddoc3,390 bytesreferences/api-references/data-plane/online-api/QueryRecommendationWithScene.mddoc4,214 bytesreferences/api-references/data-plane/online-api/QuestionSuggestions.mddoc2,434 bytesreferences/api-references/data-plane/online-api/README.mddoc2,032 bytesreferences/api-references/data-plane/online-api/Recommend.mddoc8,510 bytesreferences/api-references/data-plane/online-api/Rerank.mddoc6,027 bytesreferences/api-references/data-plane/online-api/SearchWithScene.mddoc23,343 bytesreferences/api-references/data-plane/online-api/StreamChatSearch.mddoc15,534 bytes
Read SKILL.md
# vs-product-qa
## When to Use
Use this skill when the user asks grounded questions about Viking AI Search, including:
- product concepts such as scene, dataset, hybrid search, ANN, rerank, or agentic search
- capability or configuration questions such as recommendation setup, boost/bury, or rerank enablement
- API and authentication questions such as AK/SK usage, field semantics, or error meaning
- CLI usage and local troubleshooting such as `vs item apply`, `vs auth status`, or local stack traces
- console path, billing, pricing, or quota questions
Do not use this skill for workflow execution. Delegate instead:
View the complete source on GitHubvolcengine-documentation
When your agent uses it
Volcengine official documentation lookup helper. Supports both document search and full-content fetch across Volcengine products, developer tools, support content, best practices, pricing, deployment, troubleshooting, API, SDK, and policy pages.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
1,131 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Decision Logic
- Capabilities
- Result Handling Rules
- Script Usage
Scripts executed separately
scripts/volcengine_docs.py
Files
SKILL.mdcore4,953 bytesSKILL.mdcore4,953 bytesSKILL.mdcore4,953 bytesSKILL.mdcore4,953 bytesSKILL.mdcore4,953 bytesSKILL.mdcore4,953 bytesSKILL.mdcore4,953 bytesSKILL.mdcore4,953 bytesscripts/volcengine_docs.pyruns6,577 bytes
Read SKILL.md
# volcengine-documentation
## Overview
This helper provides two core capabilities for Volcengine official documentation:
- `search`: retrieve relevant official documentation pages
- `fetch`: retrieve the full content of a known documentation page
Use official documentation as the authoritative source for Volcengine product questions.
When this helper is used by `vs-product-qa` for Viking AI Search:
- `search` must use `ServiceCodes="Universal AI Search"`
- `fetch` must use URLs under `https://www.volcengine.com/docs/85296`View the complete source on GitHubvs-project
When your agent uses it
Create Viking web projects, start and verify a local preview, or deploy a generated project to Volcengine IGA Pages when explicitly requested. Includes agent-guided feature, eligible application, dataset, scene, and authentication choices. Use only after confirming the installed CLI exposes `vs project`; otherwise stop without taking action.
What it loads into context
Frontmatter
162 tokensAlways available to the agent
SKILL.md
2,771 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Version Check
- Preconditions
- Commands
- Workflow
- Constraints
Scripts executed separately
../../scripts/install-skills.ps1../../scripts/install-skills.sh../../scripts/install.ps1../../scripts/install.sh
Files
../../scripts/install-skills.ps1runs4,333 bytes../../scripts/install-skills.shruns5,203 bytes../../scripts/install.ps1runs2,064 bytes../../scripts/install.shruns2,026 bytesSKILL.mdcore13,191 bytesSKILL.mdcore13,191 bytesSKILL.mdcore13,191 bytes
Read SKILL.md
# Viking Project Create and Deploy
## When to Use
Use this skill to create a Viking web project from existing application resources and verify its local preview, or to deploy a generated project to Volcengine IGA Pages.
## Version Check
Before starting this skill workflow, run `vs version check --json`. Continue only when `status` is `up-to-date`. If `status` is `update-available`, stop and tell the user to update the cloned `vs` repository, then run `git pull --ff-only`, `bash ./scripts/install.sh`, and `bash ./scripts/install-skills.sh all --target auto --force` (PowerShell: `scripts/install.ps1` and `scripts/install-skills.ps1`). If the status is `unknown`, stop and report that the CLI version could not be verified.
## Preconditions
- before doing anything else, run `vs project --help`; this availability check is the only command allowed before consulting `vs-product-qa`
- if the command is unavailable or reports an unknown command, stop immediately and state that project creation and deployment are unavailable; do not enumerate resources, create files, install dependencies, or deploy, and do not explain how to enable hidden functionalityView the complete source on GitHubvs-recommend
When your agent uses it
Recommend runtime and V2 scene management: run recommendation requests, manage recommend scenes and rules, and verify the deployed recommendation path.
What it loads into context
Frontmatter
162 tokensAlways available to the agent
SKILL.md
4,273 tokensWhen the skill is activated
Reference documents
20,860 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Version Check
- Preconditions
- Scope
- V2 API Semantics
- Deployment Semantics
- Commands
- Workflow
- References
- Customer Environment Principle
- Constraints
Scripts executed separately
../../scripts/install-skills.ps1../../scripts/install-skills.sh../../scripts/install.ps1../../scripts/install.sh
Files
../../scripts/install-skills.ps1runs4,333 bytes../../scripts/install-skills.shruns5,203 bytes../../scripts/install.ps1runs2,064 bytes../../scripts/install.shruns2,026 bytes../vs-product-qa/references/api-references/control-plane/scene/CreateRecommendSceneV2.mddoc5,514 bytes../vs-product-qa/references/api-references/control-plane/scene/GetRecommendSceneV2.mddoc4,634 bytes../vs-product-qa/references/api-references/control-plane/scene/PublishRecommendSceneV2.mddoc17,500 bytes../vs-product-qa/references/api-references/control-plane/scene/UpsertRecommendRuleV2.mddoc6,368 bytes../vs-product-qa/references/api-references/data-plane/online-api/Recommend.mddoc8,510 bytesSKILL.mdcore20,189 bytesSKILL.mdcore20,189 bytesSKILL.mdcore20,189 bytesSKILL.mdcore20,189 bytesSKILL.mdcore20,189 bytesSKILL.mdcore20,189 bytesSKILL.mdcore20,189 bytesreferences/recommend-scene-natural-language-routing.mddoc44,749 bytes
Read SKILL.md
# Viking Recommend
## When to Use
Use this skill for:
- recommendation runtime checks
- V2 recommend scene inspection, creation, publishing, deletion, and deployment verification
- V2 recommend rule inspection and management
- diagnosing whether bad recommendation results come from scene config, behavior-scene binding, user context, parent/item context, data readiness, or online config propagation
- separating persistent scene defaults from request-only runtime parameters
If the user asks a general product/API/auth/pricing question rather than a recommend workflow action, temporarily hand off to `vs-product-qa` and return here only after the grounded product answer is complete.
View the complete source on GitHubvs-search
When your agent uses it
Search runtime and scene management: verify queries, inspect scenes, debug app readiness, and diagnose recall or scene-config issues.
What it loads into context
Frontmatter
130 tokensAlways available to the agent
SKILL.md
2,288 tokensWhen the skill is activated
Reference documents
12,136 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Version Check
- Preconditions
- Scope
- Commands
- Workflow
- References
- Customer Environment Principle
- Constraints
Scripts executed separately
../../scripts/install-skills.ps1../../scripts/install-skills.sh../../scripts/install.ps1../../scripts/install.sh
Files
../../scripts/install-skills.ps1runs4,333 bytes../../scripts/install-skills.shruns5,203 bytes../../scripts/install.ps1runs2,064 bytes../../scripts/install.shruns2,026 bytes../vs-product-qa/references/api-references/control-plane/scene/PublishSearchSceneV2.mddoc36,242 bytesSKILL.mdcore11,007 bytesSKILL.mdcore11,007 bytesSKILL.mdcore11,007 bytesSKILL.mdcore11,007 bytesSKILL.mdcore11,007 bytesSKILL.mdcore11,007 bytesreferences/search-scene-natural-language-routing.mddoc14,205 bytes
Read SKILL.md
# Viking Search
## When to Use
Use this skill for:
- search query verification
- search scene inspection and updates
- online result checks
- recall or ranking issue diagnosis
- separating persistent scene config from request-only runtime parameters
- fine-grained operations / serving-controls updates, including query-specific search rules
If the user wants automated batch evaluation or similarity tuning across many queries and strategies, use `vs-search-tuning` instead.View the complete source on GitHubvs-search-tuning
When your agent uses it
Use when a user asks an agent to evaluate or tune text search similarity for an existing Viking AI Search application and dataset.
What it loads into context
Frontmatter
137 tokensAlways available to the agent
SKILL.md
3,268 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Version Check
- Preconditions
- Commands
- Workflow
- Customer Environment Principle
- Constraints
Scripts executed separately
../../scripts/install-skills.ps1../../scripts/install-skills.sh../../scripts/install.ps1../../scripts/install.sh
Files
../../scripts/install-skills.ps1runs4,333 bytes../../scripts/install-skills.shruns5,203 bytes../../scripts/install.ps1runs2,064 bytes../../scripts/install.shruns2,026 bytesSKILL.mdcore14,418 bytesSKILL.mdcore14,418 bytesSKILL.mdcore14,418 bytesSKILL.mdcore14,418 bytesSKILL.mdcore14,418 bytesSKILL.mdcore14,418 bytesSKILL.mdcore14,418 bytesSKILL.mdcore14,418 bytesSKILL.mdcore14,418 bytesSKILL.mdcore14,418 bytesSKILL.mdcore14,418 bytesSKILL.mdcore14,418 bytesSKILL.mdcore14,418 bytesSKILL.mdcore14,418 bytes
Read SKILL.md
# 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.
## Version Check
Before starting this skill workflow, run `vs version check --json`. Continue only when `status` is `up-to-date`. If `status` is `update-available`, stop and tell the user to update the cloned `vs` repository, then run `git pull --ff-only`, `bash ./scripts/install.sh`, and `bash ./scripts/install-skills.sh all --target auto --force` (PowerShell: `scripts/install.ps1` and `scripts/install-skills.ps1`). If the status is `unknown`, stop and report that the CLI version could not be verified.
## Preconditions
View the complete source on GitHubvs-search-tuning-partial-case
When your agent uses it
Use when the user provides 1-50 concrete bad-case search queries for one Viking Search app and wants local deterministic fixes. This skill only verifies request-level fine-operation interventions against a read-only baseline scene and delivers a console-ready configuration sheet, validated payloads, and a replay script. It must not mutate scenes, apps, dictionaries, datasets, recall core parameters, or online defaults.
What it loads into context
Frontmatter
187 tokensAlways available to the agent
SKILL.md
4,117 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Version Check
- Preconditions
- Constraints
- 3. Naming Conventions
- Commands
- 4. Known CLI Behaviors and Pitfalls
- 5. Fine-Grained Operations Action Library
- Workflow
- 7. Default Execution Summary
Scripts executed separately
../../scripts/install-skills.ps1../../scripts/install-skills.sh../../scripts/install.ps1../../scripts/install.sh
Files
../../scripts/install-skills.ps1runs4,333 bytes../../scripts/install-skills.shruns5,203 bytes../../scripts/install.ps1runs2,064 bytes../../scripts/install.shruns2,026 bytesSKILL.mdcore17,867 bytesSKILL.mdcore17,867 bytesSKILL.mdcore17,867 bytesSKILL.mdcore17,867 bytesSKILL.mdcore17,867 bytesSKILL.mdcore17,867 bytesSKILL.mdcore17,867 bytesSKILL.mdcore17,867 bytesSKILL.mdcore17,867 bytesSKILL.mdcore17,867 bytesSKILL.mdcore17,867 bytes
Read SKILL.md
# Viking Search Partial Case Tuning
## When to Use
Use this skill when the user provides a small number of concrete bad-case queries, usually 1-50, and asks to "optimize the search results for these queries."
This skill only performs local, highly deterministic, fine-grained operational fixes:
- It does not replace global relevance or recall-parameter tuning.
- It does not change online configuration; it only validates candidates through request-level payloads.
- The final deliverables are a fine-grained operations configuration sheet that can be copied into the console, validated payloads, and a replay script.
## Version Check
View the complete source on GitHubvs-search-tuning-specify-policy-direction
When your agent uses it
Viking Search tuning for specified policy directions. Use this when the user provides specific queries, a type of query, or a business policy direction, and asks to boost, suppress, or fix a class of search results through request-parameter passthrough. You must only perform read-only baseline evaluation and request-level candidate testing; do not modify search scenes, app config, dictionaries, recommend scenes, or primary recall parameters.
What it loads into context
Frontmatter
192 tokensAlways available to the agent
SKILL.md
5,410 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Version Check
- Preconditions
- Commands
- 2. Intervention Boundaries
- 3. Library of 8 Intervention Methods (Each Method Is Independent)
- 4. Failure Mode -> Candidate Method Mapping (Independent Lookup Table)
- 5. Evaluation Module (Two Decoupled Modes)
- Workflow
- 7. Report Requirements
- Constraints
Scripts executed separately
../../scripts/install-skills.ps1../../scripts/install-skills.sh../../scripts/install.ps1../../scripts/install.sh
Files
../../scripts/install-skills.ps1runs4,333 bytes../../scripts/install-skills.shruns5,203 bytes../../scripts/install.ps1runs2,064 bytes../../scripts/install.shruns2,026 bytesSKILL.mdcore23,955 bytesSKILL.mdcore23,955 bytesSKILL.mdcore23,955 bytesSKILL.mdcore23,955 bytesSKILL.mdcore23,955 bytesSKILL.mdcore23,955 bytesSKILL.mdcore23,955 bytes
Read SKILL.md
# Viking Search Tuning for Specified Policy Directions (vs-search-tuning-specify-policy-direction)
## When to Use
Use this Skill when the user provides specific queries or a type of query, and explicitly specifies an "optimization policy direction" such as boosting the weight of a product type, increasing exposure for seasonal products, or fixing a class of bad cases.
Difference from global `vs-search-tuning`:
- This Skill **does not modify primary recall parameters**.
- This Skill **does not create, modify, or derive scenes**.
- This Skill validates and recommends strategies only through **request-parameter passthrough**, within the scope of the 8 business intervention methods.
- It is suitable for small-scale targeted tuning with a clear direction; it is not suitable for global similarity-recall strategy search.
Mode selection:View the complete source on GitHubvs-shared
When your agent uses it
Shared SearchCLI setup: install, authenticate, run doctor, and verify the local environment.
What it loads into context
Frontmatter
136 tokensAlways available to the agent
SKILL.md
1,573 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Version Check
- Preconditions
- Commands
- Regions
- Workflow
- LLM Setup
- Customer Environment Principle
- Constraints
Scripts executed separately
../../scripts/install-skills.ps1../../scripts/install-skills.sh../../scripts/install.ps1../../scripts/install.sh
Files
../../scripts/install-skills.ps1runs4,333 bytes../../scripts/install-skills.shruns5,203 bytes../../scripts/install.ps1runs2,064 bytes../../scripts/install.shruns2,026 bytesSKILL.mdcore6,721 bytesSKILL.mdcore6,721 bytesSKILL.mdcore6,721 bytesSKILL.mdcore6,721 bytesSKILL.mdcore6,721 bytesSKILL.mdcore6,721 bytesSKILL.mdcore6,721 bytes
Read SKILL.md
# Viking Shared
## When to Use
Use this skill when an external agent is setting up SearchCLI for the first time, or when it needs to check authentication, profiles, and local readiness.
## Version Check
Before starting this skill workflow, run `vs version check --json`. Continue only when `status` is `up-to-date`. If `status` is `update-available`, stop and tell the user to update the cloned `vs` repository, then run `git pull --ff-only`, `bash ./scripts/install.sh`, and `bash ./scripts/install-skills.sh all --target auto --force` (PowerShell: `scripts/install.ps1` and `scripts/install-skills.ps1`). If the status is `unknown`, stop and report that the CLI version could not be verified.
## Preconditions
- `Node.js >= 20` is installed
- the repository has already been cloned, or the CLI has already been installed with `scripts/install.sh`View the complete source on GitHubvs-user-onboarding
When your agent uses it
Guide a brand-new SearchCLI/vs user from first-time usage questions to sign-up, purchase of Viking AI Search, AK/SK setup, and a working authenticated CLI. Use when the user says they downloaded or installed SearchCLI/vs and asks how to use it, how to start, sign up, buy, or onboard.
What it loads into context
Frontmatter
208 tokensAlways available to the agent
SKILL.md
4,168 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Entry Paths
- Version Check
- Preconditions
- Commands
- Workflow
- Constraints
Scripts executed separately
../../scripts/install-skills.ps1../../scripts/install-skills.sh../../scripts/install.ps1../../scripts/install.sh
Files
../../scripts/install-skills.ps1runs4,333 bytes../../scripts/install-skills.shruns5,203 bytes../../scripts/install.ps1runs2,064 bytes../../scripts/install.shruns2,026 bytesSKILL.mdcore18,184 bytesSKILL.mdcore18,184 bytesSKILL.mdcore18,184 bytesSKILL.mdcore18,184 bytesSKILL.mdcore18,184 bytes
Read SKILL.md
# vs-user-onboarding
# AI Search New User Purchase Onboarding
## When to Use
Use this skill when the agent detects that a user needs to complete AI Search purchase / order placement, recover from a missing-auth CLI error, configure local AK/SK, or start using SearchCLI/vs for the first time before continuing with later Viking AI Search workflows.
Common trigger phrases include:
- "I downloaded SearchCLI; how do I use it?"
- "I just installed vs; how do I get started?"
- "我下载了 SearchCLI,帮我看一下如何使用"
- "我刚装了 vs,怎么开始用"View the complete source on GitHubSkills included
- vs-alias-mapping
- vs-chat
- vs-crawler
- vs-item-onboarding
- vs-product-qa
- volcengine-documentation
- vs-project
- vs-recommend
- vs-search
- vs-search-tuning
- vs-search-tuning-partial-case
- vs-search-tuning-specify-policy-direction
- vs-shared
- vs-user-onboarding
Repository facts
- License
- Apache-2.0
- Created
- May 8, 2026
- Last pushed
- Oct 16, 2026
- Forks
- 39
- Open issues
- 7
- Project activity
- Active
Rank over the last 12 weeks
Now #777 · best #514 · down 161 in 30 days
- #764 on Oct 31
- #763 on Nov 1
- #768 on Nov 2
- #773 on Nov 3
- #775 on Nov 4
- #777 since Nov 5
34 earlier periods
- #534 on Aug 1
- #488 on Aug 5
- #514 on Aug 13
- #528 on Aug 21
- #514 on Aug 22
- #536 on Aug 24
- #530 on Aug 29
- #549 on Sep 2
- #556 on Sep 11
- #553 on Sep 12
- #556 on Sep 13
- #580 on Sep 14
- #569 on Sep 15
- #581 on Sep 16
- #585 on Sep 18
- #568 on Sep 19
- #578 on Sep 20
- #596 on Sep 22
- #593 on Sep 23
- #591 on Sep 27
- #594 on Sep 28
- #608 on Sep 30
- #590 on Oct 1
- #597 on Oct 4
- #616 on Oct 7
- #647 on Oct 8
- #639 on Oct 12
- #659 on Oct 16
- #663 on Oct 22
- #644 on Oct 24
- #737 on Oct 25
- #750 on Oct 28
- #754 on Oct 29
- #756 on Oct 30
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 3, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 123 notes
skills/vs-alias-mapping/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/vs-alias-mapping/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/vs-alias-mapping/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/vs-alias-mapping/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/vs-alias-mapping/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/vs-chat/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/vs-chat/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/vs-chat/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/vs-chat/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/vs-chat/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/vs-crawler/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/vs-crawler/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/vs-crawler/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/vs-crawler/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/vs-crawler/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/vs-crawler/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/vs-crawler/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/vs-item-onboarding/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/vs-item-onboarding/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/vs-item-onboarding/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 13 dangerous shell commandsin 1 file: scripts/install-skills.sh:162
- 72 network referencesin 8 files: volcengine-documentation/scripts/volcengine_docs.py:7 volcengine-documentation/SKILL.md:18 vs-product-qa/SKILL.md:113 and 5 more
- No hidden or obfuscated text
- No instruction overrides
- 53 executable scriptsin 5 files: scripts/install-skills.ps1:1 scripts/install-skills.sh:1 scripts/install.ps1:1 and 2 more
- 9 references to secretsin 5 files: vs-shared/SKILL.md:34 vs-project/SKILL.md:67 vs-search-tuning/SKILL.md:28 and 2 more
- No requests to vote in Hot
Show all 147 signals by file
scripts/install-skills.ps1
- Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Executable scriptline 1
Executable file
scripts/install-skills.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 162
rm -rf "${target_dir}" - Dangerous shell operationline 162
rm -rf "${target_dir}" - Dangerous shell operationline 162
rm -rf "${target_dir}" - Dangerous shell operationline 162
rm -rf "${target_dir}" - Dangerous shell operationline 162
rm -rf "${target_dir}" - Dangerous shell operationline 162
rm -rf "${target_dir}" - Dangerous shell operationline 162
rm -rf "${target_dir}" - Dangerous shell operationline 162
rm -rf "${target_dir}" - Dangerous shell operationline 162
rm -rf "${target_dir}" - Dangerous shell operationline 162
rm -rf "${target_dir}" - Dangerous shell operationline 162
rm -rf "${target_dir}" - Dangerous shell operationline 162
rm -rf "${target_dir}" - Dangerous shell operationline 162
rm -rf "${target_dir}"
scripts/install.ps1
- Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Executable scriptline 1
Executable file
scripts/install.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash
skills/vs-crawler/SKILL.md
- Network accessline 59
"tags": ["search", "vector database", "hybrid search"], "language": "en", "source_url": "https://viking.example.com/blog/introducing-viking-ai-search", - Network accessline 60
"language": "en", "source_url": "https://viking.example.com/blog/introducing-viking-ai-search", "metadata": { - Network accessline 61
"source_url": "https://viking.example.com/blog/introducing-viking-ai-search",
skills/vs-item-onboarding/SKILL.md
- Network accessline 71
|---|---|---| | Upload URL | `vs dataset import-url --file-name <basename>` | Request a presigned PUT URL plus `FileKey` | | PUT upload | `curl -X PUT --data-binary @<path> "<FileUrl>"` | Upload the local file to TOS (no auth header needed) - Network accessline 72
| Upload URL | `vs dataset import-url --file-name <basename>` | Request a presigned PUT URL plus `FileKey` | | PUT upload | `curl -X PUT --data-binary @<path> "<FileUrl>"` | Upload the local file to TOS (no auth header needed) | | Submit in - Network accessline 73
| PUT upload | `curl -X PUT --data-binary @<path> "<FileUrl>"` | Upload the local file to TOS (no auth header needed) | - Network accessline 145
3. **Get upload URL** — `vs dataset import-url --file-name <basename>`. Capture `Result.FileUrl` and `Result.FileKey`. Keep `FileKey` for step 5. 4. **PUT upload** — upload the raw item file to `FileUrl` (e.g. `curl -X PUT --data-binary "@< - Network accessline 146
4. **PUT upload** — upload the raw item file to `FileUrl` (e.g. `curl -X PUT --data-binary "@<local-path>" "<FileUrl>"`). Expect HTTP 200 with empty body. Do not add an `Authorization` header — `FileUrl` is already presigned. - Network accessline 347
- Host contains `volcengineapi.com` / `volces.com` → **Volc Engine**, base = `https://console.volcengine.com/aisearch/platform/region:aisearch-platform+<region>`. `<region>` is the active profile region (e.g. `cn-beijing`). - Network accessline 348
- Dataset URL: `<base>/home/dataset/<DatasetId>` - App URL: `<base>/app/<AppId>` - Host contains `byteplus.com` → **BytePlus**, base = `https://console.byteplus.com/aisearch/region:aisearch+ap-southeast-1` (BytePlus today only exp - Network accessline 349
- App URL: `<base>/app/<AppId>` - Host contains `byteplus.com` → **BytePlus**, base = `https://console.byteplus.com/aisearch/region:aisearch+ap-southeast-1` (BytePlus today only exposes the `ap-southeast-1` region; do not fabricate othe - Network accessline 350
- Host contains `byteplus.com` → **BytePlus**, base = `https://console.byteplus.com/aisearch/region:aisearch+ap-southeast-1` (BytePlus today only exposes the `ap-southeast-1` region; do not fabricate other regions).
skills/vs-item-onboarding/references/worked-example.md
skills/vs-product-qa/SKILL.md
- Network accessline 113
- base root URL: `https://www.volcengine.com/docs/85296/1544972` - Network accessline 114
- Chinese questions use `https://www.volcengine.com/docs/85296/1544972?lang=cn` - Network accessline 115
- non-Chinese questions use `https://www.volcengine.com/docs/85296/1544972?lang=en` - Network accessline 122
- product code is `Universal AI Search` - the helper script's `search` action must use `ServiceCodes="Universal AI Search"` - the helper script's `fetch` action must use URLs under `https://www.volcengine.com/docs/85296` only - Network accessline 124
- the helper script's `fetch` action must use URLs under `https://www.volcengine.com/docs/85296` only - Network accessline 143
- `https://www.volcengine.com/llms.txt` - Network accessline 144
- `https://www.volcengine.com/sitemap.xml` - Network accessline 217
11. **Bundled helper only**: use the documentation helper only inside `vs-product-qa`; do not expose it as a standalone skill. 12. **Language-aware docs**: use `?lang=cn` for Chinese questions and `?lang=en` for non-Chinese questions. 13. * - Network accessline 218
12. **Language-aware docs**: use `?lang=cn` for Chinese questions and `?lang=en` for non-Chinese questions. 13. **Strict doc scope**: only access `https://www.volcengine.com/docs/85296/1544972` and its child pages in the same subtree. 14. * - Network accessline 219
13. **Strict doc scope**: only access `https://www.volcengine.com/docs/85296/1544972` and its child pages in the same subtree. 14. **Hard source restriction**: for Viking AI Search docs, `search` must use `ServiceCodes="Universal AI Search" - Network accessline 220
14. **Hard source restriction**: for Viking AI Search docs, `search` must use `ServiceCodes="Universal AI Search"`, and `fetch` must stay under `https://www.volcengine.com/docs/85296`. - Network accessline 252
3. Choose the documentation root by user language: `?lang=cn` for Chinese, otherwise `?lang=en`. 4. Run the helper script's `search` action with `ServiceCodes="Universal AI Search"`. 5. Use the helper script's `fetch` action only if the cho - Network accessline 253
4. Run the helper script's `search` action with `ServiceCodes="Universal AI Search"`. 5. Use the helper script's `fetch` action only if the chosen page URL stays under `https://www.volcengine.com/docs/85296`. 6. Answer using only retrieved - Network accessline 254
5. Use the helper script's `fetch` action only if the chosen page URL stays under `https://www.volcengine.com/docs/85296`.
skills/vs-product-qa/references/volcengine-documentation/SKILL.md
- Network accessline 18
- `search` must use `ServiceCodes="Universal AI Search"` - `fetch` must use URLs under `https://www.volcengine.com/docs/85296` - Network accessline 19
- `fetch` must use URLs under `https://www.volcengine.com/docs/85296` - Network accessline 26
### How to combine `search` and `fetch` 1. For Viking AI Search question-style requests, start with `search` and always pass `ServiceCodes="Universal AI Search"`. 2. Reject or ignore results that do not belong to `Universal AI Search` or wh - Network accessline 27
1. For Viking AI Search question-style requests, start with `search` and always pass `ServiceCodes="Universal AI Search"`. 2. Reject or ignore results that do not belong to `Universal AI Search` or whose URL is outside `https://www.volcengi - Network accessline 28
2. Reject or ignore results that do not belong to `Universal AI Search` or whose URL is outside `https://www.volcengine.com/docs/85296`. - Network accessline 32
### 1. Document search (`search`) Search Volcengine official documentation by user question, with optional product filtering. - Endpoint: `https://docs-api.cn-beijing.volces.com/api/v1/doc/search` - Network accessline 34
- Endpoint: `https://docs-api.cn-beijing.volces.com/api/v1/doc/search` - Network accessline 54
### 2. Full-content fetch (`fetch`) - Network accessline 56
- Endpoint: `https://docs-api.cn-beijing.volces.com/api/v1/doc/fetch` - Network accessline 59
| Name | Type | Required | Description | |------|------|----------|-------------| | Url | string | Yes | Volcengine documentation URL, such as `https://www.volcengine.com/docs/6349/162514`. For Viking AI Search inside `vs-product-qa`, this - Network accessline 61
| Url | string | Yes | Volcengine documentation URL, such as `https://www.volcengine.com/docs/6349/162514`. For Viking AI Search inside `vs-product-qa`, this must stay under `https://www.volcengine.com/docs/85296`. | - Network accessline 63
Important rule: If the input URL contains query parameters, such as `https://www.volcengine.com/docs/6396/624853?lang=zh`, strip all query parameters before sending the request and keep only the clean page URL. - Network accessline 64
If the input URL contains query parameters, such as `https://www.volcengine.com/docs/6396/624853?lang=zh`, strip all query parameters before sending the request and keep only the clean page URL. - Network accessline 76
2. If multiple results are returned, show the most relevant ones first and limit the answer to at most 3 items. 3. Always use the script-returned `CleanUrl` as the citation URL. Do not cite URLs with query parameters such as `?lang=zh`. 4. - Network accessline 78
4. For Viking AI Search inside `vs-product-qa`, reject results unless the page URL starts with `https://www.volcengine.com/docs/85296`. - Network accessline 104
python {skill_dir}/scripts/volcengine_docs.py fetch "https://www.volcengine.com/docs/85296/1544972?lang=en"
skills/vs-product-qa/references/volcengine-documentation/scripts/volcengine_docs.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 7
API_BASE = "https://docs-api.cn-beijing.volces.com/api/v1/doc" - Network accessline 59
} try: response = requests.post(url, headers=headers, json=payload, timeout=REQUEST_TIMEOUT) - Network accessline 60
try: response = requests.post(url, headers=headers, json=payload, timeout=REQUEST_TIMEOUT) response.raise_for_status() - Network accessline 61
response = requests.post(url, headers=headers, json=payload, timeout=REQUEST_TIMEOUT) - Network accessline 72
result["Result"]["FilteredBy"] = { "ServiceCodes": [UNIVERSAL_AI_SEARCH_SERVICE_CODE], "UrlPrefix": f"https://{ALLOWED_DOC_HOST}{ALLOWED_DOC_PREFIX}" - Network accessline 73
"ServiceCodes": [UNIVERSAL_AI_SEARCH_SERVICE_CODE], "UrlPrefix": f"https://{ALLOWED_DOC_HOST}{ALLOWED_DOC_PREFIX}" } - Network accessline 74
"UrlPrefix": f"https://{ALLOWED_DOC_HOST}{ALLOWED_DOC_PREFIX}" - Network accessline 80
def fetch(doc_url): - Network accessline 84
clean_url = f"{parsed.scheme}://{parsed.netloc}{parsed.path}" if not is_allowed_universal_ai_search_url(clean_url): return {"error": f"Fetch is only allowed for URLs under https://{ALLOWED_DOC_HOST}{ALLOWED_DOC_PREFIX}"} - Network accessline 86
return {"error": f"Fetch is only allowed for URLs under https://{ALLOWED_DOC_HOST}{ALLOWED_DOC_PREFIX}"} - Network accessline 94
} try: response = requests.post(url, headers=headers, json=payload, timeout=REQUEST_TIMEOUT) - Network accessline 95
try: response = requests.post(url, headers=headers, json=payload, timeout=REQUEST_TIMEOUT) response.raise_for_status() - Network accessline 96
response = requests.post(url, headers=headers, json=payload, timeout=REQUEST_TIMEOUT) - Network accessline 118
"desc": "Fetch full page content from a Volcengine documentation URL", "params": "<volcengine_documentation_url>", "example": 'python volcengine_docs.py fetch "https://www.volcengine.com/docs/85296/1544972?la - Network accessline 119
"params": "<volcengine_documentation_url>", "example": 'python volcengine_docs.py fetch "https://www.volcengine.com/docs/85296/1544972?lang=zh"' } - Network accessline 120
"example": 'python volcengine_docs.py fetch "https://www.volcengine.com/docs/85296/1544972?lang=zh"' - Network accessline 123
"constraints": { "service_code": UNIVERSAL_AI_SEARCH_SERVICE_CODE, "url_prefix": f"https://{ALLOWED_DOC_HOST}{ALLOWED_DOC_PREFIX}" - Network accessline 124
"service_code": UNIVERSAL_AI_SEARCH_SERVICE_CODE, "url_prefix": f"https://{ALLOWED_DOC_HOST}{ALLOWED_DOC_PREFIX}" } - Network accessline 125
"url_prefix": f"https://{ALLOWED_DOC_HOST}{ALLOWED_DOC_PREFIX}" - Network accessline 156
elif action == "fetch": if len(sys.argv) < 3: result = {"error": "Missing document URL", "help": "Usage: python volcengine_docs.py fetch <volcengine_documentation_url>; URL must stay under https://www.volcengine.com/docs - Network accessline 157
if len(sys.argv) < 3: result = {"error": "Missing document URL", "help": "Usage: python volcengine_docs.py fetch <volcengine_documentation_url>; URL must stay under https://www.volcengine.com/docs/85296"} else: - Network accessline 158
result = {"error": "Missing document URL", "help": "Usage: python volcengine_docs.py fetch <volcengine_documentation_url>; URL must stay under https://www.volcengine.com/docs/85296"} - Network accessline 159
else: doc_url = sys.argv[2] result = fetch(doc_url) - Network accessline 161
result = fetch(doc_url)
skills/vs-project/SKILL.md
- Access to secretsline 67
[Credential-related source omitted] - Network accessline 76
11. Read the generated `projectDir` from the command result. Run `npm install` in that directory unless its `node_modules` directory already exists. Stop and report the install failure if dependencies cannot be installed; do not claim that - Network accessline 77
12. Run `npm run dev` in the generated directory using a persistent terminal or background session that remains alive after the response. Watch the live output until the Next.js server reports that it is ready. Treat an early process exit, - Network accessline 78
13. Extract the preview URL from Next.js's actual `Local:` output instead of assuming port 3000. Next.js may select another port when its default is occupied. Normalize its origin without a trailing slash, then run `curl -fsS -o /dev/null < - Access to secretsline 97
[Credential-related source omitted]
skills/vs-search-tuning-specify-policy-direction/SKILL.md
- Access to secretsline 128
[Credential-related source omitted]
skills/vs-search-tuning/SKILL.md
skills/vs-shared/SKILL.md
skills/vs-user-onboarding/SKILL.md
- Network accessline 136
- **Root account**: send the key management link `https://console.volcengine.com/iam/keymanage`, then ask the user to create or retrieve AK/SK there. Tell the user not to paste AK/SK into chat.
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
No combined signals at this commit.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/vs-alias-mapping/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/vs-alias-mapping/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/vs-alias-mapping/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/vs-alias-mapping/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/vs-alias-mapping/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/vs-alias-mapping/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/volcengine-searchcli/)