Gradient logo

Gradient

Organization
Servosity
gradient

The Synthesize partner API from the terminal - every endpoint, plus a usage-push ledger, billing drift detection, and alert-to-ticket tracing no other Gradient tool has. Trigger phrases: `push usage counts to gradient`, `sync usage to synthesize`, `check my synthesize integration status`, `find unmapped gradient accounts`, `did my gradient alert create a ticket`, `use gradient`, `run gradient-cli`.

Overview

PublisherServosity
Repositorymsp-skills
Skill namegradient
Stars
68
Forks
14
Bundled files
133
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 133 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Servosity on GitHub. Read the source before you install it.

Installation

Install the Gradient AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Servosity/msp-skills/tree/main/skills/gradient
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Servosity/msp-skills.git /tmp/msp-skills
mkdir -p .claude/skills
cp -r /tmp/msp-skills/skills/gradient .claude/skills/gradient
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gradient in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Gradient on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Gradient is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Gradient MSP - Claude Code Skill

Prerequisites: Install the CLI

This skill drives the gradient-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:

  1. macOS / Linux:
    bash
    bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/gradient/install.sh)
  2. Windows (PowerShell):
    powershell
    iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/gradient/install.ps1 | iex
  3. Verify: gradient-cli --version
  4. Ensure ~/.local/bin (macOS / Linux) or %LOCALAPPDATA%\Programs\msp-skills (Windows) is on $PATH.

The installer downloads the gradient-cli and gradient-mcp binaries into ~/.local/bin (macOS / Linux) or %LOCALAPPDATA%\Programs\msp-skills (Windows). It does not register the skill with your agent and writes no MCP client config - see mcp-install.md for that wire-up.

If --version reports "command not found" after install, the runtime cannot see the binary directory on $PATH. Do not proceed with skill commands until verification succeeds.

Gradient MSP's Synthesize platform reconciles vendor usage against MSP billing, but its only tooling is a PowerShell SDK that makes you write a script project per integration. This CLI covers the full vendor API surface agent-natively with an offline SQLite mirror of your accounts, and adds what the API itself cannot: a local ledger of every count you push (usage drift), debounce-aware bulk pushes (usage push), mapping-hygiene rollups (hygiene unmapped), and async alert-to-ticket confirmation (alert send --wait).

When to Use This CLI

Use this CLI for any agent task that touches Gradient MSP's Synthesize vendor API: pushing usage unit counts for billing reconciliation, creating or updating accounts and services, checking or flipping integration status, dispatching alerts that must become PSA tickets, and auditing what was pushed (drift, ledgers, unmapped rollups). It is the right choice for nightly usage sync jobs and integration bring-up debugging.

Anti-triggers

Do not use this CLI for:

  • Pulling usage data OUT of vendor products (RMM, security tools) - this CLI only pushes into Synthesize; fetch from the vendor's own API first
  • Operating the MSP-side Synthesize web app (mapping approvals happen in the Gradient UI, not this API)
  • Managing PSA tickets directly (ConnectWise/Autotask/Halo operations) - alerts here only enqueue tickets via Gradient
  • Gradient's internal partner program administration or anything requiring a Synthesize web login session

Unique Capabilities

These capabilities aren't available in any other tool for this API.

Billing you can audit

  • usage push - Push a whole file of unit counts (CSV or JSON) in one shot and trigger exactly one billing rebuild instead of one per call.

    Reach for this whenever more than one unit count needs to land in Synthesize; it is the nightly sync primitive.

    bash
    gradient-cli usage push --file ./counts.csv --agent
  • usage drift - See exactly which accounts' usage changed between your last two pushes, with old-to-new deltas.

    Run before every invoice cycle to know what moved - the reconciliation pre-flight no API call can answer.

    bash
    gradient-cli usage drift --agent

Alert-to-ticket correlation

  • alert send - Dispatch an alert and wait until the PSA ticket actually exists, instead of fire-and-forget.

    Use when an alert must verifiably become a ticket - CI hooks and monitoring bridges need the confirmation, not the enqueue.

    bash
    gradient-cli alert send --account 123456789 --title "Backup failure" --description "Nightly job failed" --wait --agent
  • alert trace - Review every alert you have dispatched - messageId, account, time, last-known ticket state - and filter to ones that never became tickets.

    The fastest answer to 'which of my alerts are stuck in the queue' across days of dispatches.

    bash
    gradient-cli alert trace --stuck --agent

Mapping hygiene

  • hygiene unmapped - One rollup of every unmapped account and every service without a vendor SKU, shaped as an actionable work queue.

    Run it after every account/service push to see what mapping work remains before billing can reconcile.

    bash
    gradient-cli hygiene unmapped --agent
  • status ready - A single go/no-go verdict on whether the integration is ready to flip to active: live status, last sync age, and outstanding mapping gaps.

    Run before 'integration update-status --status active' to avoid activating an integration with unmapped accounts.

    bash
    gradient-cli status ready --agent

Command Reference

accounts - Manage accounts

  • gradient-cli accounts create - Creates an account
  • gradient-cli accounts list - Get Organization Accounts
  • gradient-cli accounts update - Updates 1 or more fields per Account
  • gradient-cli accounts update-one - Updates 1 or more fields of a single Account

alerting - Manage alerting

  • gradient-cli alerting <accountId> - Adds an alert to the alerting queue

billing - Manage billing

  • gradient-cli billing <serviceId> - Set route for adding new unit count for one account, and one service.

clients - Manage clients

  • gradient-cli clients - DEPRECATED - This route is used to get the Client data needed to handling mapping externally.

integration - Manage integration

  • gradient-cli integration get - Preferred route for checking credentials
  • gradient-cli integration update-status - Update the integration status for a partner. Set as pending when ready for inital mapping.

mappings - Manage mappings

  • gradient-cli mappings create - Create Service for a Vendor for an Organization
  • gradient-cli mappings update - Updates 1 or more fields of a single Service
  • gradient-cli mappings update-bulk - Updates 1 or more fields for each Service

services - Manage services

  • gradient-cli services create - Create Service for a Vendor
  • gradient-cli services get <serviceId> - Retrieves Vendor with VendorSku[] filtered by service id

ticket_events - Manage ticket events

  • gradient-cli ticket-events <messageId> - Checks for a ticket Event with the provided messageId to have created a ticket in the PSA

vendor - Manage vendor

  • gradient-cli vendor get - Get Vendor Details
  • gradient-cli vendor update - Update details for a vendor

Finding the right command

When you know what you want to do but not which command does it, ask the CLI directly:

bash
gradient-cli which "<capability in your own words>"

which resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code 0 means at least one match; exit code 2 means no confident match - fall back to --help or use a narrower query.

Recipes

Nightly usage sync with one billing rebuild

bash
gradient-cli usage push --file ./nightly-counts.csv --agent

Validates and fans out every account-service count with no_build until the final call, then records the run in the local ledger.

What changed since the last push?

bash
gradient-cli usage drift --agent

Joins the two most recent ledger runs and returns only the rows whose counts moved - the pre-invoice sanity check.

Inspect the vendor SKU catalog fields agents care about

bash
gradient-cli vendor get --agent --select data.name,data.skus.name,data.skus.category

The vendor profile nests the full SKU catalog; --select narrows the payload to the fields that matter.

Dispatch an alert and confirm the ticket

bash
gradient-cli alert send --account 123456789 --title "Backup failure" --description "Nightly job failed twice" --wait

Dispatches, captures the messageId, then polls the debug route until the PSA ticket exists or timeout.

Pre-activation readiness check

bash
gradient-cli status ready --agent

Combines live integration status with local mapping gaps into a single go/no-go before 'integration update-status --status active'.

Auth Setup

Synthesize issues a Vendor API key and a Partner API key pair (Synthesize UI: Integrations -> Custom -> Generate API Tokens; shown once). Every request sends a GRADIENT-TOKEN header whose value is base64(":"). Set GRADIENT_VENDOR_API_KEY and GRADIENT_PARTNER_API_KEY and the CLI derives the header for you, or set GRADIENT_TOKEN to the pre-computed value directly. Verify with gradient-cli doctor.

Agent Mode

Add --agent to any command. Expands to: --json --compact --no-input --no-color --yes.

  • Pipeable - JSON on stdout, errors on stderr

  • Filterable - --select keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs:

    bash
    gradient-cli accounts list --agent --select id,name,status
  • Previewable - --dry-run shows the request without sending

  • Offline-friendly - sync/search commands can use the local SQLite store when available

  • Non-interactive - never prompts, every input is a flag

  • Explicit retries - use --idempotent only when an already-existing create should count as success

Response envelope

Commands that read from the local store or the API wrap output in a provenance envelope:

json
{
  "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."},
  "results": <data>
}

Parse .results for data and .meta.source to know whether it's live or local. A human-readable N results (live) summary is printed to stderr only when stdout is a terminal AND no machine-format flag (--json, --csv, --compact, --quiet, --plain, --select) is set - piped/agent consumers and explicit-format runs get pure JSON on stdout.

Agent Feedback

When you (or the agent) notice something off about this CLI, record it:

gradient-cli feedback "the --since flag is inclusive but docs say exclusive"
gradient-cli feedback --stdin < notes.txt
gradient-cli feedback list --json --limit 10

Entries are stored locally at ~/.local/share/gradient-cli/feedback.jsonl. They are never POSTed unless GRADIENT_FEEDBACK_ENDPOINT is set AND either --send is passed or GRADIENT_FEEDBACK_AUTO_SEND=true. Default behavior is local-only.

Write what surprised you, not a bug report. Short, specific, one line: that is the part that compounds.

Output Delivery

Every command accepts --deliver <sink>. The output goes to the named sink in addition to (or instead of) stdout, so agents can route command results without hand-piping. Three sinks are supported:

SinkEffect
stdoutDefault; write to stdout only
file:<path>Atomically write output to <path> (tmp + rename)
webhook:<url>POST the output body to the URL (application/json or application/x-ndjson when --compact)

Unknown schemes are refused with a structured error naming the supported set. Webhook failures return non-zero and log the URL + HTTP status on stderr.

Named Profiles

A profile is a saved set of flag values, reused across invocations. Use it when a scheduled agent calls the same command every run with the same configuration - HeyGen's "Beacon" pattern.

gradient-cli profile save briefing --json
gradient-cli --profile briefing accounts list
gradient-cli profile list --json
gradient-cli profile show briefing
gradient-cli profile delete briefing --yes

Explicit flags always win over profile values; profile values win over defaults. agent-context lists all available profiles under available_profiles so introspecting agents discover them at runtime.

Exit Codes

CodeMeaning
0Success
2Usage error (wrong arguments)
3Resource not found
4Authentication required
5API error (upstream issue)
7Rate limited (wait and retry)
10Config error

Argument Parsing

Parse $ARGUMENTS:

  1. Empty, help, or --help → show gradient-cli --help output
  2. Starts with install → ends with mcp → MCP installation; otherwise → see Prerequisites above
  3. Anything else → Direct Use (execute as CLI command with --agent)

MCP Server Installation

  1. Install the MCP binary (run the install script from the Prerequisites section, or see mcp-install.md for per-agent wire-up).
  2. Register with Claude Code:
    bash
    claude mcp add gradient-mcp -- gradient-mcp
  3. Verify: claude mcp list

Direct Use

  1. Check if installed: which gradient-cli If not found, offer to install (see Prerequisites at the top of this skill).
  2. Match the user query to the best command from the Unique Capabilities and Command Reference above.
  3. Execute with the --agent flag:
    bash
    gradient-cli <command> [subcommand] [args] --agent
  4. If ambiguous, drill into subcommand help: gradient-cli <command> --help.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

and 73 more files.

Frequently asked questions

What does the Gradient AI skill do?

The Synthesize partner API from the terminal - every endpoint, plus a usage-push ledger, billing drift detection, and alert-to-ticket tracing no other Gradient tool has. Trigger phrases: `push usage counts to gradient`, `sync usage to synthesize`, `check my synthesize integration status`, `find unmapped gradient accounts`, `did my gradient alert create a ticket`, `use gradient`, `run gradient-cli`.

Why use Gradient on TypingMind?

Because you install it once and use it with any model. Gradient is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Gradient in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Servosity/msp-skills/tree/main/skills/gradient. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Gradient?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Gradient?

As many as you like. As long as a model supports skills, you can use Gradient with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Gradient AI skill free?

Yes. It is published on GitHub by Servosity under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇