Agent skill

Automations

by truffle-ai in truffle-ai/dexto

Create and manage automations using the scheduler tools with suggestive defaults.

Custom licenceAuto-check passedAI & LLM Engineering

Install Automations

skills CLI
$ npx skills add truffle-ai/dexto --skill automations -a claude-code

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

GitHub CLI
$ gh skill install truffle-ai/dexto automations --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/truffle-ai/dexto.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/automations .claude/skills/automations && 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
automations
GitHub stars
649
Token cost
~420 tokens
SKILL.md length
186 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
Custom licence

At a glance

Create and manage automations using the scheduler tools with suggestive defaults.

  • Works in 7 steps: Infer a sensible default schedule from… → Propose a compact, human-friendly… → Create the automation with… → …
  • AI & LLM Engineering work in your project
  • SKILL.md covers Purpose, Inputs, Steps and Output Format
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Automations is an agent skill from truffle-ai/dexto. Create and manage automations using the scheduler tools with suggestive defaults.

Its SKILL.md is about 420 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 AI & LLM Engineering. It works with Model Context Protocol and TypeScript. The repository describes itself as: Agent harness and tookit for building AI agents and agentic applications. CLI and SDKs included.

When your agent uses it

  • AI & LLM Engineering work in your project

Example prompts

  • “/automations”

Requirements

  • Pre-approved tools (allowed-tools): create_schedule, update_schedule, list_schedules, get_schedule, get_schedule_history, trigger_schedule_now, delete_schedule

Workflow steps

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

  1. Infer a sensible default schedule from the user’s request and keep the canonical cron internal (do not display it).
  2. Propose a compact, human-friendly configuration (name, cadence, enabled, instruction). Inherit the default session mode unless the user…
  3. Create the automation with create_schedule after confirmation.
  4. If the user asks to edit an existing automation, use update_schedule with only the changed fields.
  5. For review or troubleshooting, use
  6. If the user wants to run immediately, call trigger_schedule_now with the schedule id.
  7. If the user wants to remove it, call delete_schedule with the schedule id.

What it can do on your machine

Read from SKILL.md and the folder at commit 6c70654. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • create_schedule
    • update_schedule
    • list_schedules
    • get_schedule
    • get_schedule_history
    • trigger_schedule_now
    • delete_schedule

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

Automations loads about 420 tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 186 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~23
When it runs · the whole SKILL.md, loaded when a task matches
~420

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 186 words (~420 tokens).

“Create, update, list, and manage scheduled automations using the scheduler tools with suggestive defaults and minimal back-and-forth.”

— opening of SKILL.md by truffle-ai, Custom licence
name
automations
allowed-tools
create_schedule, update_schedule, list_schedules, get_schedule, get_schedule_history, trigger_schedule_now, delete_schedule
toolkits
scheduler-tools

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .agents/skills/automations of truffle-ai/dexto.

Open the folder on GitHubat commit 6c70654

Compare with similar skills

Automations 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.

Automations compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Automations this skilltruffle-ai/dexto649—~420Automated safety check: PassCustom licence
Agent Squad for TypeScript2FastLabs/agent-squad7.8k—~4.3kAutomated safety check: PassApache-2.0
Sponsio Agent Safety SetupSponsioLabs/Sponsio454—~12kAutomated safety check: PassApache-2.0
Opikcomet-ml/opik-mcp220—~2.1kAutomated safety check: PassApache-2.0
Neurolink Guidejuspay/neurolink144—~1.4kAutomated safety check: PassMIT
Agent Inspectrajudandigam/agent-inspect165—~424Automated safety check: PassMIT

Similar skills

  • Agent Squad for TypeScript

    2FastLabs/agent-squad

    Guide to building Node.js and TypeScript apps on the agent-squad package: orchestrator, agent types, classifier routing, storage, retrievers and MCP tools.

    7.8k GitHub stars~4.3k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Sponsio Agent Safety Setup

    SponsioLabs/Sponsio

    Installs, tunes and enforces Sponsio contracts that block unsafe tool calls in LLM agents, covering setup, auditing, observe mode and flipping to enforce.

    454 GitHub stars~12k tokensUpdated 4 days ago
    AI & LLM EngineeringAuto-check passed
  • Opik

    comet-ml/opik-mcp

    Reference for the Opik SDK — tracing, span types, framework integrations, threads, and the prompt library (Python, TypeScript, REST).

    220 GitHub stars~2.1k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Neurolink Guide

    juspay/neurolink

    Guide for using the NeuroLink SDK and CLI. An agent skill from juspay/neurolink.

    144 GitHub stars~1.4k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Agent Inspect

    rajudandigam/agent-inspect

    Local evidence debugger and trajectory-test toolkit for TypeScript AI agents.

    165 GitHub stars~424 tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed
  • Tool Design

    agentailor/fullstack-langgraph-nextjs-agent

    Design and verify tools that AI agents can actually use — for any framework or language (MCP servers, LangChain/LangGraph, function-calling, raw JSON schema; TypeScript, Python, or otherwise).

    132 GitHub stars~3.2k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

More from truffle-ai/dexto

  • Simplify

    truffle-ai/dexto

    Review changed code for reuse, quality, and efficiency, then fix any issues found.

    649 GitHub stars~1k tokensUpdated yesterday
    Auto-check passed
  • Create Skill

    truffle-ai/dexto

    Create or update Dexto skill bundles with SKILL.md, handlers, scripts, mcps, and references.

    649 GitHub stars~895 tokensUpdated yesterday
    Auto-check passed

Questions about Automations

What does Automations do?

Create and manage automations using the scheduler tools with suggestive defaults. Automations is an agent skill from truffle-ai/dexto. Create and manage automations using the scheduler tools with suggestive defaults.

When should I use Automations?

Automations fits situations like: AI & LLM Engineering work in your project.

How do I install Automations in Claude Code?

Run `npx skills add truffle-ai/dexto --skill automations -a claude-code`. Or copy the skill folder (.agents/skills/automations in truffle-ai/dexto) into .claude/skills/automations in your project. Claude Code loads it when a task matches its description.

How do I install Automations in Codex?

Run `npx skills add truffle-ai/dexto --skill automations -a codex`. Or copy the skill folder (.agents/skills/automations in truffle-ai/dexto) into .agents/skills/automations in your project. Codex loads it when a task matches its description.

Can I use Automations 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 truffle-ai/dexto --skill automations -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/automations, .gemini/skills/automations, .github/skills/automations and .opencode/skills/automations in your project.

What does Automations need to run?

SKILL.md names no scripts, command-line tools or credentials: Automations is instructions for the agent only. Its frontmatter pre-approves these tools: create_schedule, update_schedule, list_schedules, get_schedule, get_schedule_history, trigger_schedule_now, delete_schedule.

Does Automations access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Automations 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 Automations use?

Automations has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Automations use?

About 420 tokens (SKILL.md is roughly 1.7k 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 Automations?

Skills that share tags, products or a category with Automations: Agent Squad for TypeScript (2FastLabs/agent-squad, 7.8k stars), Sponsio Agent Safety Setup (SponsioLabs/Sponsio, 454 stars), Opik (comet-ml/opik-mcp, 220 stars) and Neurolink Guide (juspay/neurolink, 144 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Automations?

truffle-ai (a GitHub organization) maintains it in truffle-ai/dexto, which has 649 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 9, 2026.

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