New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Vss Search Index

by open-edge-platform in open-edge-platform/edge-ai-libraries

Search a video library with natural language via the VSS Pipeline Manager - upload a video (POST /videos), generate its embeddings (POST /videos/search-embeddings/{id}), then run a query (POST…

Apache-2.0Auto-check passedAI & LLM Engineering

Install Vss Search Index

skills CLI
$ npx skills add open-edge-platform/edge-ai-libraries --skill vss-search-index -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install open-edge-platform/edge-ai-libraries vss-search-index --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/open-edge-platform/edge-ai-libraries.git skills-src && mkdir -p .claude/skills && cp -r skills-src/sample-applications/video-search-and-summarization/.github/skills/vss-search-index .claude/skills/vss-search-index && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
vss-search-index
GitHub stars
171
Token cost
~2.2k tokens
SKILL.md length
800 words
Files
14 (incl. scripts, references)
Skills in repo
29
Repo updated
First seen
Licence
Apache-2.0

At a glance

Search a video library with natural language via the VSS Pipeline Manager - upload a video (POST /videos), generate its embeddings (POST /videos/search-embeddings/{id}), then run a query (POST…

  • Works in 4 steps: Upload a video (if not already ingested) → Generate search embeddings → Query → …
  • The user says search my videos
  • SKILL.md covers Answer contract when VSS is…, Environment setup (run first), Preconditions and 1. Upload a video (if not…, plus 4 more sections
  • Runs Shell scripts from its folder; calls curl, jq and bash

What it does

Vss Search Index is an agent skill from open-edge-platform/edge-ai-libraries. Search a video library with natural language via the VSS Pipeline Manager - upload a video (POST /videos), generate its embeddings (POST /videos/search-embeddings/{id}), then run a query (POST /search/query) with optional tag and time filters and read the ranked clip results. Use when the user says "search my videos", "find something in the videos", "when did X happen", or wants to ingest/index a video for search. Requires a search-capable deployment (--search, --dual, or --unified).

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 18 other files, including scripts and reference files (for example `benchmark/benchmark.json`, `benchmark/benchmark.md` and `evals/evals.json`).

It sits in AI & LLM Engineering, covering Embeddings. The repository describes itself as: Libraries, microservices, tools, and other reference software, supporting development of performance-optimized Edge AI applications. The licence is Apache-2.0.

When your agent uses it

  • The user says search my videos
  • Find something in the videos
  • Wants to ingest/index a video for search

Example prompts

  • “search my videos”
  • “find something in the videos”
  • “when did X happen”
  • “/vss-search-index”

Requirements

  • A Bash shell
  • Docker

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Upload a video (if not already ingested)
  2. Generate search embeddings
  3. Query
  4. Saved / managed queries (optional)

What it can do on your machine

Read from SKILL.md and the folder at commit 0ed0479. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • curl
    • jq
    • bash
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use curl and git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Vss Search Index loads about 2.2k tokens when it runs, and up to ~3.1k if it reads all its reference files. Until then it costs about 126 tokens; SKILL.md has 800 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~126
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from open-edge-platform/edge-ai-libraries at commit 0ed0479, republished under its Apache-2.0 licence (© open-edge-platform). 800 words, ~2,209 tokens.

Download SKILL.mdSave it as .claude/skills/vss-search-index/SKILL.md (or your agent's skills folder). This skill also uses 13 other files; get the full folder from GitHub.
name
vss-search-index
description
Search a video library with natural language via the VSS Pipeline Manager - upload a video (POST /videos), generate its embeddings (POST /videos/search-embeddings/{id}), then run a query (POST /search/query) with optional tag and time filters and read the ranked clip results. Use when the user says "search my videos", "find something in the videos", "when did X happen", or wants to ingest/index a video for search. Requires a search-capable deployment (--search, --dual, or --unified).
license
Apache-2.0
metadata.version
1.0.0
metadata.tags
vss operational search
<!--
SPDX-FileCopyrightText: (C) 2026 Intel Corporation
SPDX-License-Identifier: Apache-2.0
-->

Natural-language search over the indexed video library. Call the documented API yourself and report only observed responses. Endpoints use the nginx /manager prefix.

Set HOST=http://${HOST_IP:-localhost}:${APP_HOST_PORT:-12345}.

Answer contract when VSS is not reachable

The user may be away from the deployment, or $HOST may refuse connections. In that case do not stall and do not invent responses. Answer with the exact call sequence instead: full endpoint paths, request bodies / form fields, the field each step carries over from the previous response, and the condition that says a step is finished. State plainly that the commands were not executed. Never end the answer by asking whether to run them.

Environment setup (run first)

This skill drives the Video Search & Summarization app through its real source files, so the VSS application must be present and you must run commands from its app root. Do this before anything else, and it works whether or not the VSS source is already in your workspace.

Run the bundled bootstrap. It resolves the app root in this order and prints it as the only line on stdout:

  1. Walk up from the current directory looking for a VSS app root - a directory carrying all three markers setup.sh, docker/, and pipeline-manager/.
  2. Ask git for the enclosing repository (git rev-parse --show-toplevel) and check whether it holds sample-applications/video-search-and-summarization, or is itself a VSS app root. This is what makes your own clone - or a fork - work unchanged.
  3. Reuse a checkout a previous bootstrap already placed in ${XDG_CACHE_HOME:-$HOME/.cache}/vss-src/edge-ai-libraries.

If any of those hit, that checkout is reused and NO clone is performed. Only when all three miss does it clone - and then only a shallow (--depth 1), single-branch, sparse checkout of just sample-applications/video-search-and-summarization from main:

bash
# SKILL_DIR is THIS skill's own directory (shown to you when the skill loads);
# in-repo it is .github/skills/vss-search-index. Works the same if the skill is installed standalone.
SKILL_DIR=".github/skills/vss-search-index"
APP_ROOT="$(bash "$SKILL_DIR/scripts/vss-bootstrap.sh")"
cd "$APP_ROOT"

Every command below assumes the working directory is this APP_ROOT. To pull from a fork/branch or reuse a specific checkout dir, override VSS_REPO_URL, VSS_REPO_BRANCH, or VSS_CLONE_DIR before running it. The bootstrap refuses to overwrite an existing non-VSS clone destination.

Preconditions

Backend healthy and search enabled - probe first; if not, use the installed vss-troubleshoot or vss-deploy skill by name:

bash
curl -sf "$HOST/manager/health" >/dev/null && \
curl -s "$HOST/manager/app/features" | jq -e '(.search // .) == "FEATURE_ON"'

1. Upload a video (if not already ingested)

POST /manager/videos - multipart/form-data, field name video, optional comma-separated tags. File must be a streamable MP4 (server rejects otherwise).

bash
curl -s -X POST "$HOST/manager/videos" \
  -F "video=@/path/to/clip.mp4" \
  -F "tags=outdoor,daytime" | jq .
# → { "videoId": "<VIDEO_ID>" }

When the user says a video is already uploaded or just uploaded, list videos first and match the exact real filename. Reuse that record's videoId; do not search the local filesystem and upload another copy. Upload only when no exact filename match exists and the user actually supplied a local file to ingest.

The list response is an object { "videos": [...] }, not a bare array; name is a generated hash, so use url / dataStore.fileName for the real filename:

bash
curl -s "$HOST/manager/videos" | jq '.videos[] | {videoId, file: .dataStore.fileName}'
curl -s "$HOST/manager/videos/<VIDEO_ID>" | jq '.video'   # single record is wrapped under .video

2. Generate search embeddings

A video is not searchable until embeddings exist. Trigger them after upload (or to retry a failed run):

bash
curl -s -X POST "$HOST/manager/videos/search-embeddings/<VIDEO_ID>" | jq .

Wait for completion (re-check the video record) before querying.

Show full SKILL.md (320 more words)Show less

3. Query

One-off query - POST /manager/search/query. The response is an object { "results": [ { "query_id", "results": [ … ] } ] } - wrapped, NOT a bare array - so the ranked clips are at .results[].results[]:

bash
curl -s -X POST "$HOST/manager/search/query" \
  -H 'Content-Type: application/json' \
  -d '{
    "query": "person wearing a hat",
    "tags": "indoor",
    "timeFilter": { "value": 7, "unit": "days" }
  }' | jq -r '.results[].results[]
      | "score=\(.metadata.relevance_score)  clip=\(.metadata.segment_start)-\(.metadata.segment_end)s  seek=\(.metadata.seek_timestamp)s  video_id=\(.metadata.video_id)"'
  • query (required): natural language.
  • tags (optional): comma-separated, intersected with the query.
  • timeFilter (optional): either relative (value + unit = minutes|hours|days|weeks) or absolute (start/end ISO-8601). See references/search-request.md.

Each clip's metadata carries relevance_score (0..1; top hit can be exactly 1), video_id, video_url, segment_start/segment_end, seek_timestamp, tags, and video_metadata (duration/fps). In search mode page_content is a segment locator ("Video segment from Ns to Ms…"), not a caption.

Filename is NOT in the result - metadata has video_id but no video / file_name. To show the clip's filename, join video_id against the video list (.videos[].dataStore.fileName):

bash
curl -s "$HOST/manager/videos" \
  | jq '[.videos[] | {key:.videoId, value:.dataStore.fileName}] | from_entries' > /tmp/idmap.json
curl -s -X POST "$HOST/manager/search/query" -H 'Content-Type: application/json' \
  -d '{ "query": "person wearing a hat" }' \
  | jq --slurpfile m /tmp/idmap.json -r '.results[].results[]
      | "score=\(.metadata.relevance_score)  file=\($m[0][.metadata.video_id] // "?")  clip=\(.metadata.segment_start)-\(.metadata.segment_end)s"'

Present top hits with their filename + clip window + seek time.

If a filtered query returns no results, report the empty result as valid. Then inspect the Manager video list for the requested tags and indexing readiness, explain only what the observed state supports, and give a Manager-based next step that preserves the same filters. To merge missing tags into an existing record, use the documented embedding operation with a body such as POST /manager/videos/search-embeddings/<VIDEO_ID> plus {"tags":"indoor"}, then rerun the same filtered query. Never present an unfiltered hit as though it satisfied the requested filter.

Final answer audit trail

Tool arguments may not be visible to the user or evaluator. The final answer must therefore name the public Pipeline Manager operations used (method and /manager/... path), the important request fields, the observed status or response, and any carried identifier such as videoId. Include the bootstrap outcome (resolved app root and whether an existing checkout was reused) plus the observed health and feature-preflight result. For searches, identify the exact query/filter payload and say that ranked hits came from POST /manager/search/query; for filename joins, say that the mapping came from GET /manager/videos. If an id cannot be resolved, label it unresolved rather than inventing a filename.

4. Saved / managed queries (optional)

bash
curl -s -X POST "$HOST/manager/search" -H 'Content-Type: application/json' \
  -d '{"query":"forklift"}' | jq .          # create a persistent query → queryId
curl -s "$HOST/manager/search/<QUERY_ID>" | jq .          # fetch results
curl -s -X POST "$HOST/manager/search/<QUERY_ID>/refetch" | jq .   # re-run
curl -s --request PATCH --json '{"watch":true}' \
  "$HOST/manager/search/<QUERY_ID>/watch" | jq .             # auto-refresh
curl -s "$HOST/manager/search/watched" | jq .
curl -s -X DELETE "$HOST/manager/search/<QUERY_ID>"

© open-edge-platform, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 13 other files (scripts, references) in sample-applications/video-search-and-summarization/.github/skills/vss-search-index of open-edge-platform/edge-ai-libraries.

  • SKILL.md
  • benchmark/benchmark.json
  • benchmark/benchmark.md
  • evals/evals.json
  • example-prompts/01-upload-and-index-new-clip.md
  • example-prompts/02-simple-natural-language-search.md
  • example-prompts/03-tag-and-time-filtered-search.md
  • example-prompts/04-reindex-failed-embeddings.md
  • example-prompts/05-find-filenames-for-ranked-clips.md
  • example-prompts/06-persistent-watched-query.md
  • example-prompts/07-bootstrap-fresh-machine.md
  • example-prompts/README.md
  • references/search-request.md
  • scripts/vss-bootstrap.sh

Open the folder on GitHubat commit 0ed0479

Compare with similar skills

Vss Search Index next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Vss Search Index compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vss Search Index this skillopen-edge-platform/edge-ai-libraries171—~2.2kAutomated safety check: PassApache-2.0
Chroma Vector DatabaseOrchestra-Research/AI-Research-SKILLs13k7 repos~2.3kAutomated safety check: PassMIT
SageMaker Serving Image Selectionhuggingface/skills11k1 repos~4.6kAutomated safety check: PassApache-2.0
Codebase Managementgiancarloerra/SocratiCode3.3k1 repos~1.8kAutomated safety check: PassAGPL-3.0
CLIP Image-Text MatchingOrchestra-Research/AI-Research-SKILLs13k7 repos~1.7kAutomated safety check: PassMIT
Sentence-Transformers Training Routerhuggingface/skills11k1 repos~2.6kAutomated safety check: PassApache-2.0

Similar skills

  • Chroma Vector Database

    Orchestra-Research/AI-Research-SKILLs

    Shows how to store documents and embeddings in Chroma, query them by similarity with metadata filters, and persist them to disk for RAG and semantic search projects.

    13k GitHub starsUsed in 7 repos~2.3k tokens
    AI & LLM EngineeringAuto-check passed

  • SageMaker Serving Image Selection

    huggingface/skills

    Official

    Chooses the right serving container and current image URI for deploying a Hugging Face model to a SageMaker endpoint, preferring Hugging Face images over generic ones.

    11k GitHub starsUsed in 1 repo~4.6k tokens
    AI & LLM EngineeringAuto-check passed

  • Codebase Management

    giancarloerra/SocratiCode

    Set up, index, and manage SocratiCode codebase indexing. An agent skill from giancarloerra/SocratiCode.

    3.3k GitHub starsUsed in 1 repo~1.8k tokens
    AI & LLM EngineeringAuto-check passed

  • CLIP Image-Text Matching

    Orchestra-Research/AI-Research-SKILLs

    Explains OpenAI's CLIP model for zero-shot image classification, image-text similarity, semantic image search and content moderation, with install steps and code patterns.

    13k GitHub starsUsed in 7 repos~1.7k tokens
    AI & LLM EngineeringAuto-check passed

  • Sentence-Transformers Training Router

    huggingface/skills

    Official

    Routes a sentence-transformers training task to the right model type and required reference docs and example scripts, covering bi-encoders, rerankers, sparse and multi-vector models.

    11k GitHub starsUsed in 1 repo~2.6k tokens
    AI & LLM EngineeringAuto-check passed

  • Mashup Mods

    rehan-remade/universal-modder

    Build cross-game mashups and total conversions, the "Minecraft inside Elden Ring" or "skateboarding in MW2" kind.

    6.5k GitHub stars~3.3k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

More from open-edge-platform/edge-ai-libraries

All 29 skills in this repo

  • Time Series Analytics User

    open-edge-platform/edge-ai-libraries

    Build a new time-series analytics use case on top of the deployed Time Series Analytics microservice — bring it up with Docker Compose (from a repo clone, or by fetching the compose files from…

    171 GitHub stars~3.1k tokensUpdated yesterday
    Auto-check passed

  • Vss Add Nest Module

    open-edge-platform/edge-ai-libraries

    Scaffolds and wires a new NestJS service/module for the Video Search & Summarization sample app's pipeline-manager using the repo's real conventions.

    171 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed

  • Chatqna Helm Deploy

    open-edge-platform/edge-ai-libraries

    Deploy Chat Question-and-Answer Core to Kubernetes using Helm (OpenVINO CPU, OpenVINO GPU, or Ollama), including values.yaml configuration, helm install/upgrade, deployment verification, uninstall…

    171 GitHub stars~2.3k tokensUpdated yesterday
    Auto-check passed

  • Generate Changelog

    open-edge-platform/edge-ai-libraries

    Generates or updates CHANGELOG.md by analyzing git commit history between two branches, tags, or revisions in ANY git repository or folder.

    171 GitHub stars~3.1k tokensUpdated yesterday
    Auto-check passed

  • Vss Deploy

    open-edge-platform/edge-ai-libraries

    Deploys and manages VSS through setup.sh and its Docker Compose overlays.

    171 GitHub stars~4.1k tokensUpdated yesterday
    Auto-check passed

  • Vss Deploy Helm

    open-edge-platform/edge-ai-libraries

    A skill your agent uses whenever a developer needs to deploy VSS to Kubernetes, helm install VSS, configure values.yaml for VSS, or run VSS on k8s with GPU/vLLM for the…

    171 GitHub stars~3.8k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Vss Search Index

What does Vss Search Index do?

Search a video library with natural language via the VSS Pipeline Manager - upload a video (POST /videos), generate its embeddings (POST /videos/search-embeddings/{id}), then run a query (POST…. Vss Search Index is an agent skill from open-edge-platform/edge-ai-libraries. Search a video library with natural language via the VSS Pipeline Manager - upload a video (POST /videos), generate its embeddings (POST /videos/search-embeddings/{id}), then run a query (POST /search/query) with optional tag and time filters and read the ranked clip results.

When should I use Vss Search Index?

Vss Search Index fits situations like: the user says search my videos; find something in the videos; wants to ingest/index a video for search.

How do I install Vss Search Index in Claude Code?

Run `npx skills add open-edge-platform/edge-ai-libraries --skill vss-search-index -a claude-code`. Or copy the skill folder (sample-applications/video-search-and-summarization/.github/skills/vss-search-index in open-edge-platform/edge-ai-libraries) into .claude/skills/vss-search-index in your project. Claude Code loads it when a task matches its description.

How do I install Vss Search Index in Codex?

Run `npx skills add open-edge-platform/edge-ai-libraries --skill vss-search-index -a codex`. Or copy the skill folder (sample-applications/video-search-and-summarization/.github/skills/vss-search-index in open-edge-platform/edge-ai-libraries) into .agents/skills/vss-search-index in your project. Codex loads it when a task matches its description.

Can I use Vss Search Index in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add open-edge-platform/edge-ai-libraries --skill vss-search-index -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vss-search-index, .gemini/skills/vss-search-index, .github/skills/vss-search-index and .opencode/skills/vss-search-index in your project.

What does Vss Search Index need to run?

Going by SKILL.md and its folder, Vss Search Index needs a shell for the scripts in its folder and the command-line tools its instructions call (curl, jq, bash and git). Our summary lists: A Bash shell; Docker.

Does Vss Search Index access the network?

SKILL.md contains no URLs. Its commands use curl and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Vss Search Index safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Vss Search Index use?

Vss Search Index is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Vss Search Index use?

About 2.2k tokens (SKILL.md is roughly 8.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 860 tokens, read only when the agent opens those files.

What are the alternatives to Vss Search Index?

Skills that share tags, products or a category with Vss Search Index: Chroma Vector Database (Orchestra-Research/AI-Research-SKILLs, 13k stars), SageMaker Serving Image Selection (huggingface/skills, 11k stars), Codebase Management (giancarloerra/SocratiCode, 3.3k stars) and CLIP Image-Text Matching (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vss Search Index?

open-edge-platform (a GitHub organization) maintains it in open-edge-platform/edge-ai-libraries, which has 171 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on October 10, 2026.

Source: open-edge-platform/edge-ai-libraries on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.