Agent skill

Provider Analysis

by fossasia in fossasia/eventyay-interpretation

A skill your agent uses when integrating, debugging, or auditing third-party provider integrations (transcription APIs, MediaMTX, Jitsi, future Eventyay API integration).

Apache-2.0Auto-check passedMedia & Creative

Install Provider Analysis

skills CLI

$ npx skills add fossasia/eventyay-interpretation --skill provider-analysis -a claude-code

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

GitHub CLI

$ gh skill install fossasia/eventyay-interpretation provider-analysis --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/fossasia/eventyay-interpretation.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/provider-analysis .claude/skills/provider-analysis && 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/

Paste into Claude Code

Install the "provider-analysis" agent skill from https://github.com/fossasia/eventyay-interpretation/tree/dev/.agents/skills/provider-analysis into .claude/skills/provider-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "provider-analysis", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/fossasia/eventyay-interpretation/tree/dev/.agents/skills/provider-analysis

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add fossasia/eventyay-interpretation --skill provider-analysis -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install fossasia/eventyay-interpretation provider-analysis --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/fossasia/eventyay-interpretation.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/provider-analysis .agents/skills/provider-analysis && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "provider-analysis" agent skill from https://github.com/fossasia/eventyay-interpretation/tree/dev/.agents/skills/provider-analysis into .agents/skills/provider-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "provider-analysis", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add fossasia/eventyay-interpretation --skill provider-analysis -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install fossasia/eventyay-interpretation provider-analysis --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/fossasia/eventyay-interpretation.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/provider-analysis .cursor/skills/provider-analysis && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "provider-analysis" agent skill from https://github.com/fossasia/eventyay-interpretation/tree/dev/.agents/skills/provider-analysis into .cursor/skills/provider-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "provider-analysis", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/fossasia/eventyay-interpretation.git --path .agents/skills/provider-analysis

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add fossasia/eventyay-interpretation --skill provider-analysis -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install fossasia/eventyay-interpretation provider-analysis --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/fossasia/eventyay-interpretation.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/provider-analysis .gemini/skills/provider-analysis && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "provider-analysis" agent skill from https://github.com/fossasia/eventyay-interpretation/tree/dev/.agents/skills/provider-analysis into .gemini/skills/provider-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "provider-analysis", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install fossasia/eventyay-interpretation provider-analysis

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add fossasia/eventyay-interpretation --skill provider-analysis -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/fossasia/eventyay-interpretation.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/provider-analysis .github/skills/provider-analysis && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "provider-analysis" agent skill from https://github.com/fossasia/eventyay-interpretation/tree/dev/.agents/skills/provider-analysis into .github/skills/provider-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "provider-analysis", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add fossasia/eventyay-interpretation --skill provider-analysis -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install fossasia/eventyay-interpretation provider-analysis --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/fossasia/eventyay-interpretation.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/provider-analysis .opencode/skills/provider-analysis && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "provider-analysis" agent skill from https://github.com/fossasia/eventyay-interpretation/tree/dev/.agents/skills/provider-analysis into .opencode/skills/provider-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "provider-analysis", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: provider-analysis
GitHub stars: 1.6k
Token cost: ~1.3k tokens
SKILL.md length: 462 words
Files: 1
Skills in repo: 38
Repo updated: Oct 5, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

A skill your agent uses when integrating, debugging, or auditing third-party provider integrations (transcription APIs, MediaMTX, Jitsi, future Eventyay API integration).

Works in 5 steps: Admin enters key via admin panel form. → Key encrypted via… → At transcription start:… → …
Auditing third-party provider integrations (transcription APIs
SKILL.md covers MediaMTX, Jitsi Meet, OpenAI (Transcription) and Deepgram (Transcription), plus 4 more sections
Calls uv; reaches api.openai.com; needs API_KEY_ENCRYPTION_KEY

What it does

Provider Analysis is an agent skill from fossasia/eventyay-interpretation. Use this skill when integrating, debugging, or auditing third-party provider integrations (transcription APIs, MediaMTX, Jitsi, future Eventyay API integration).

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative, covering Transcription and Third-party API integration. It works with FastAPI. The repository describes itself as: A plugin for live interpretation of video streams. The licence is Apache-2.0.

When your agent uses it

Auditing third-party provider integrations (transcription APIs
Future Eventyay API integration)

Example prompts

“/provider-analysis”

Requirements

Python 3
A credential in API_KEY_ENCRYPTION_KEY

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

Admin enters key via admin panel form.
Key encrypted via portal.crypto.encrypt_val(key) → stored in DB.
At transcription start: get_api_key(event, ProviderEnum.X) → decrypt_val(encrypted_col).
API_KEY_ENCRYPTION_KEY must be set as env var (≥32 chars); fails loudly if default.
Key rotation: add new key as prefix to comma-separated API_KEY_ENCRYPTION_KEY; MultiFernet tries all keys.

What it can do on your machine

Read from SKILL.md and the folder at commit 1ca0139. 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
Shell commands in SKILL.md call:
- uv
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- api.openai.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- API_KEY_ENCRYPTION_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Provider Analysis loads about 1.3k tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 462 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~45
When it runs · the whole SKILL.md, loaded when a task matches: ~1.3k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from fossasia/eventyay-interpretation at commit 1ca0139, republished under its Apache-2.0 licence (© fossasia). 462 words, ~1,286 tokens.

Download SKILL.mdSave it as .claude/skills/provider-analysis/SKILL.md (or your agent's skills folder).

name: provider-analysis
description: Use this skill when integrating, debugging, or auditing third-party provider integrations (transcription APIs, MediaMTX, Jitsi, future Eventyay API integration).

Skill: Provider Analysis

Use this skill when integrating, debugging, or auditing third-party provider integrations (transcription APIs, MediaMTX, Jitsi, future Eventyay API integration).

MediaMTX

Role: Media server — WHIP ingest, WHEP playback, RTSP for transcription.

Key integration points

Endpoint	Used by	Purpose
`{MEDIAMTX_WHIP_BASE}/{path}/whip`	Browser (JS)	Interpreter audio ingest
`{MEDIAMTX_WHIP_BASE}/{path}/whep`	Browser (JS)	Listener audio playback
`rtsp://mediamtx:8554/{path}`	ffmpeg (Python)	Transcription audio source
`{MEDIAMTX_API_BASE}/v3/config/paths/add/{path}`	FastAPI (`_ensure_mediamtx_path`)	Create named path with `alwaysAvailable`
`{MEDIAMTX_API_BASE}/v3/config/paths/patch/{path}`	FastAPI (fallback)	Update existing path config
`{MEDIAMTX_API_BASE}/v3/paths/list`	FastAPI (`_check_mediamtx`)	Reachability check

`alwaysAvailable` path creation

Called before returning WHIP URL or rendering booth page.
Creates named path so WHEP readers survive publisher handoffs.
Cache: _created_paths set prevents duplicate API calls.
Idempotent: if path exists, PATCHes it to ensure alwaysAvailable: True.

`overridePublisher`

Set in mediamtx.yml — allows a new WHIP publisher to kick the previous one. Enables seamless handoff when coordinator reassigns active interpreter.

Reachability check

python

await _check_mediamtx()  # returns True if API responds < 500

Used by /healthz and booth page template.

Jitsi Meet

Role: Floor session monitoring — receive-only iframe embedded in interpreter booth.

Integration

Embedded as an iframe in templates/interpreter_booth.html.
URL: room-specific Jitsi URL from DBBooth.room.jitsi_url (admin-configured) OR _make_jitsi_url(base_url, default_jitsi_room).
URL format: {effective_jitsi_base_url}/{room_name} (if room is not already a full URL).
Domain passed to template as jitsi_domain (derived from effective_jitsi_base_url).
Self-hosted; image: jitsi/*:stable-9823.

Jitsi room naming convention (auto-generated)

When admin creates a room, a Jitsi URL is auto-generated:

python

clean_name = re.sub(r'[^a-zA-Z0-9]+', '', display_name)
room_id_str = f"Voxbento-{event.slug}-{clean_name}"
jitsi_url = _make_jitsi_url(effective_jitsi_base_url, room_id_str)

Critical: Jitsi is monitoring only

Never use Jitsi's audio as the broadcast source. Interpreter mic → WHIP → MediaMTX is the only valid ingest path.

OpenAI (Transcription)

whisper-1: POST https://api.openai.com/v1/audio/transcriptions — WAV file upload per 3-second chunk.
gpt-4o-realtime: wss://api.openai.com/v1/realtime?model={model} — WebSocket streaming with PCM frames.
Auth: Authorization: Bearer {api_key} header.
API key: stored encrypted as events.openai_api_key; requires event.transcription_api_enabled = True.
Retry: tenacity, exponential backoff 2–10s, max 3 attempts on 429/5xx.
HTTP client: portal.transcription.shared_http_client (shared httpx.AsyncClient).

Show full SKILL.md (178 more words)Show less

Deepgram (Transcription)

wss://api.deepgram.com/v1/listen?model=nova-2&language={lang}&encoding=linear16&sample_rate=16000&channels=1&interim_results=true&keepalive=true&endpointing=2000&smart_format=true&punctuate=true
Auth: Authorization: Token {api_key}.
Protocol: WebSocket streaming — send raw PCM, receive JSON transcripts.
KeepAlive: sends {"type":"KeepAlive"} every 5 seconds if no audio.
API key: events.deepgram_api_key.

NVIDIA Riva (Transcription)

Parakeet-RNNT / Parakeet-CTC via Riva gRPC.
Requires optional dependency: uv add eventyay-interpretation-portal[nvidia].
Function ID configured via settings.nvidia_function_id (from NVIDIA_FUNCTION_ID env var).
API key: events.nvidia_api_key.

ElevenLabs (Transcription)

scribe_v2 model.
API key: events.elevenlabs_api_key.
Implementation in portal/transcription/providers/elevenlabs.py.

API Key Security Pattern

All external API keys follow this pattern:

Admin enters key via admin panel form.
Key encrypted via portal.crypto.encrypt_val(key) → stored in DB.
At transcription start: get_api_key(event, ProviderEnum.X) → decrypt_val(encrypted_col).
API_KEY_ENCRYPTION_KEY must be set as env var (≥32 chars); fails loudly if default.
Key rotation: add new key as prefix to comma-separated API_KEY_ENCRYPTION_KEY; MultiFernet tries all keys.

Future Eventyay Integration

Currently there is no live API coupling to Eventyay. The pattern mirrors Eventyay conventions only:

Event.slug mirrors Eventyay event slug.
Room.eventyay_room_id is a nullable foreign reference (not yet used).
Role names match Eventyay role conventions.

When integrating: use portal.* imports; do not couple to pretix.*, pretalx.*, or venueless.*.

Files

Just SKILL.md in .agents/skills/provider-analysis of fossasia/eventyay-interpretation.

Open the folder on GitHubat commit 1ca0139

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in fossasia/eventyay-interpretation, which our catalogue first saw on October 7, 2026.

fossasia/voxbento.agents/skills/provider-analysis

Compare with similar skills

Provider Analysis 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.

Provider Analysis compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Provider Analysis this skillfossasia/eventyay-interpretation	1.6k	—	~1.3k	Automated safety check: Pass	Apache-2.0	3 days ago
Video Translatorshang-zhu/violin	1.1k	—	~1k	Automated safety check: Notes	MIT	1 mo ago
Twinmind Local Dev Loopjeremylongshore/tons-of-skills-marketplace	2.8k	—	~2k	Automated safety check: Notes	MIT	today
Short Video Extractordontbesilent2025/dbskill	11k	—	~949	Automated safety check: Pass	Custom licence	yesterday
Verifylkmeta/txtify	135	—	~583	Automated safety check: Pass	Apache-2.0	1 mo ago
PayRam Checkout IntegrationPayRam/payram-mcp	158	—	~3.4k	Automated safety check: Notes	None	today

Similar skills

Video Translator
shang-zhu/violin
Dub a video into another language and generate subtitles using the default Together + Cartesia stack.
1.1k GitHub stars~1k tokensUpdated 1 mo ago
Media & CreativeAuto-check: notes
Twinmind Local Dev Loop
jeremylongshore/tons-of-skills-marketplace
Set up local development workflow with TwinMind API integration.
2.8k GitHub stars~2k tokensUpdated today
Testing & QAAuto-check: notes
Short Video Extractor
dontbesilent2025/dbskill
Extracts post data and speech transcripts from Douyin, Xiaohongshu and WeChat Channels share links and saves the transcripts as Markdown by author and title.
11k GitHub stars~949 tokensUpdated yesterday
Media & CreativeAuto-check passed
Verify
lkmeta/txtify
Verify a Txtify change end-to-end. An agent skill from lkmeta/txtify.
135 GitHub stars~583 tokensUpdated 1 mo ago
DevOps & CloudAuto-check passed
PayRam Checkout Integration
PayRam/payram-mcp
Adds crypto checkout to a web app with PayRam: create a payment from your backend, send the customer to the payment page, then confirm the result.
158 GitHub stars~3.4k tokensUpdated today
Backend & APIsAuto-check: notes
Fishjam Python Server SDK
software-mansion-labs/skills
Python server SDK for Fishjam — backends that create rooms, mint peer tokens, receive server notifications, and run voice agents.
291 GitHub stars~1.3k tokensUpdated 11 days ago
Backend & APIsAuto-check passed

Questions about Provider Analysis

What does Provider Analysis do?

A skill your agent uses when integrating, debugging, or auditing third-party provider integrations (transcription APIs, MediaMTX, Jitsi, future Eventyay API integration). Provider Analysis is an agent skill from fossasia/eventyay-interpretation. Use this skill when integrating, debugging, or auditing third-party provider integrations (transcription APIs, MediaMTX, Jitsi, future Eventyay API integration).

When should I use Provider Analysis?

Provider Analysis fits situations like: auditing third-party provider integrations (transcription APIs; future Eventyay API integration).

How do I install Provider Analysis in Claude Code?

Run `npx skills add fossasia/eventyay-interpretation --skill provider-analysis -a claude-code`. Or copy the skill folder (.agents/skills/provider-analysis in fossasia/eventyay-interpretation) into .claude/skills/provider-analysis in your project. Claude Code loads it when a task matches its description.

How do I install Provider Analysis in Codex?

Run `npx skills add fossasia/eventyay-interpretation --skill provider-analysis -a codex`. Or copy the skill folder (.agents/skills/provider-analysis in fossasia/eventyay-interpretation) into .agents/skills/provider-analysis in your project. Codex loads it when a task matches its description.

Can I use Provider Analysis 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 fossasia/eventyay-interpretation --skill provider-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/provider-analysis, .gemini/skills/provider-analysis, .github/skills/provider-analysis and .opencode/skills/provider-analysis in your project.

What does Provider Analysis need to run?

Going by SKILL.md and its folder, Provider Analysis needs the command-line tools its instructions call (uv) and credentials named API_KEY_ENCRYPTION_KEY. Our summary lists: Python 3; A credential in API_KEY_ENCRYPTION_KEY.

Does Provider Analysis access the network?

SKILL.md names 1 domain. In commands or code: api.openai.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Provider Analysis 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. Review the folder before installing.

What licence does Provider Analysis use?

Provider Analysis is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Provider Analysis use?

About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Provider Analysis?

Skills that share tags, products or a category with Provider Analysis: Video Translator (shang-zhu/violin, 1.1k stars), Twinmind Local Dev Loop (jeremylongshore/tons-of-skills-marketplace, 2.8k stars), Short Video Extractor (dontbesilent2025/dbskill, 11k stars) and Verify (lkmeta/txtify, 135 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Provider Analysis?

fossasia (a GitHub organization) maintains it in fossasia/eventyay-interpretation, which has 1,551 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on October 5, 2026.

Source: fossasia/eventyay-interpretation on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Provider Analysis

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Skill: Provider Analysis

MediaMTX

Key integration points

alwaysAvailable path creation

overridePublisher

Reachability check

Jitsi Meet

Integration

Jitsi room naming convention (auto-generated)

Critical: Jitsi is monitoring only

OpenAI (Transcription)

Deepgram (Transcription)

NVIDIA Riva (Transcription)

ElevenLabs (Transcription)

API Key Security Pattern

Future Eventyay Integration

Files

Used in 1 other repository

Compare with similar skills

Similar skills

More from fossasia/eventyay-interpretation

Related

Questions about Provider Analysis

`alwaysAvailable` path creation

`overridePublisher`