Agent Native

vectara-agent-orchestration

This skill enables building multi-step, deterministic agent workflows using state machines with structural tool gating and platform-enforced phase transitions.

by VectaraOfficial publisherNot reviewed

Identity proven by GitHub's verified organisation badge (vectara)

Agents
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode
License
No license stated
Pin
a0b1d2bpinned Oct 9, 2026
Context cost
about 8,600 tokenswhen the skill loads
GitHub stars
0on vectara/agent-skills
Scripts
None found

What it does

“Build multi-step, deterministic, step-gated Vectara agents. State machines via first_step_name + steps{} map + next_steps + allowed_tools enforce phase transitions STRUCTURALLY at the platform level — not via session.metadata variables read by a single-step LLM prompt. Covers sub-agent delegation, structured-output gating (output_parser type "structured" with strict JSON schema), runtime-constrained generation, MCP/lambda tools, reentry_step for follow-up turns, and cross-session approval workflows.”
The author's description, from SKILL.md

Generated summary from the skill's own text

This skill enables building multi-step, deterministic agent workflows using state machines with structural tool gating and platform-enforced phase transitions. Steps are defined via a map with allowed_tools and next_steps conditions, preventing the LLM from skipping ahead or calling out-of-phase tools. It covers structured output parsing, sub-agent delegation, runtime-constrained generation, and cross-session approval patterns.

When to use it

  • Workflows with discrete phases requiring different tools per step
  • Approval gates and deterministic execution that LLMs cannot bypass
  • Delegating to specialist sub-agents with different tool sets
  • Routing based on structured output from previous steps

When not to

  • Simple single-turn conversational tasks without workflow phases
  • When you need shared key-value store across steps beyond current output
  • Systems where LLM should have freedom to choose any tool at any time

Install

No license stated: install from the publisher's repository, and ask the author before you reuse or share it.

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add vectara/agent-skills --skill vectara-agent-orchestration

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install vectara/agent-skills vectara-agent-orchestration@a0b1d2b65a5912722493abf68243d62d5d409809

Installs the commit we checked (a0b1d2b).

Copy by hand

Download the folder at a0b1d2b and put it in .claude/skills/vectara-agent-orchestration for Claude Code and in .agents/skills/vectara-agent-orchestration for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at a0b1d2b

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "vectara-agent-orchestration" by Vectara.

Source, pinned to commit a0b1d2b65a5912722493abf68243d62d5d409809:
https://github.com/vectara/agent-skills/tree/a0b1d2b65a5912722493abf68243d62d5d409809/skills/agent-orchestration

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/vectara-agent-orchestration/ for Claude Code and .agents/skills/vectara-agent-orchestration/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Its license is restricted or not stated. Show me the license terms from the repository before you copy anything.

Listing and checks: https://www.agentnative.dev/skills/vectara/vectara-agent-orchestration

SKILL.md at the pin

The license of this skill does not let us show its files here.

View SKILL.md on GitHub at a0b1d2b

Files

1 file, 35 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at a0b1d2b
All 8 skills from Vectara

More from Vectara

  • vectara-agent-auth-and-secrets

    Configure authentication for Vectara agent tools using OAuth, API keys, and service-account credentials via agent.secrets, session.metadata, and $ref…

    Claude Code, Codex, Cursor +3 · about 3.2K tokens · pinned 6 days ago

  • vectara-agents

    This skill enables developers to build AI agents on the Vectara platform using retrieval-augmented generation (RAG).

    Claude Code, Codex, Cursor +3 · about 8K tokens · pinned 6 days ago

  • vectara-corpus-and-ingestion

    Manages Vectara corpus creation, document ingestion through three pathways (file upload, structured JSON, core indexing), metadata filtering with SQL-like…

    Claude Code, Codex, Cursor +3 · about 7.4K tokens · pinned 6 days ago

  • vectara-hallucination-and-eval

    This skill helps developers measure and reduce hallucinations in Vectara RAG pipelines using four distinct tools: HHEM for factual consistency scoring, the…

    Claude Code, Codex, Cursor +3 · about 4.9K tokens · pinned 6 days ago

  • vectara-pipelines

    This skill configures Vectara pipelines, which automate bulk ingestion from external sources like S3 into Vectara agents.

    Claude Code, Codex, Cursor +3 · about 5.8K tokens · pinned 6 days ago

  • vectara-python-sdk

    The Vectara Python SDK skill helps developers build Python applications against Vectara's retrieval-augmented generation platform using typed client interfaces.

    Claude Code, Codex, Cursor +3 · about 6.5K tokens · pinned 6 days ago

All AI and agents skills

Related in AI and agents

  • -21risk-automation

    This skill automates 21risk operations by connecting to the 21risk toolkit through Composio's Rube MCP server.

    by ComposioOfficial publisher

    Claude Code, Codex, Cursor +3 · about 690 tokens · pinned 6 days ago

  • -2chat-automation

    This skill automates 2chat tasks by integrating with Composio's 2chat toolkit through Rube MCP.

    by ComposioOfficial publisher

    Agents not labelled yet · about 680 tokens · pinned 6 days ago

  • ably-automation

    This skill automates Ably messaging platform tasks by connecting to Composio's Ably toolkit through Rube MCP.

    by ComposioOfficial publisher

    Agents not labelled yet · about 680 tokens · pinned 6 days ago

  • abstract-automation

    This skill enables agents to automate Abstract design platform operations through Composio's Abstract toolkit via Rube MCP.

    by ComposioOfficial publisher

    Claude Code, Codex, Cursor +3 · about 690 tokens · pinned 6 days ago

  • abuselpdb-automation

    This skill automates Abuselpdb operations through Composio's toolkit via Rube MCP, enabling the agent to search for IP/domain abuse reports and manage threat…

    by ComposioOfficial publisher

    Agents not labelled yet · about 700 tokens · pinned 6 days ago

  • abyssale-automation

    This skill enables agents to automate Abyssale tasks through Composio's toolkit via Rube MCP.

    by ComposioOfficial publisher

    Claude Code, Codex, Cursor +3 · about 690 tokens · pinned 6 days ago

Open roles at Vectara

No open roles at Vectara on the Agent Native jobs board right now.

Browse the jobs board

The skills listed here are third-party software, collected from public GitHub repositories as a catalog of recent skills and provided as is. Agent Native does not write or control them and is not responsible for any harm, loss or damage caused by installing or using them. Labels and checks describe what we saw at one commit and are not a guarantee. Read a skill's files before you run it. Terms of use