Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Getting Started

ASecurity

Use when a user expresses interest in using the Recast API. They may hit limitations of the MCP tools such as "I need to run a forecast (or optimization) and the MCP can't" or "I want to create a repeatable, deterministic workflow" or they may explicitly ask for help getting set up on the API "I want to use the API", "How do I authenticate the API", "How do I get a PAT for the API", etc. The MCP uses OAuth authentication, but all API calls require a PAT.

5 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentspythongoshellbashexpressapi

Works with

claude codeclaude desktopcliapimcp

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add getrecast/recast-for-claude --skill getting-started --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Getting Started?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Getting Started
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/getrecast-getting-started/badge)](https://www.skillsdirectory.com/skills/getrecast-getting-started)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: getting-started
description: Use when a user expresses interest in using the Recast API. They may hit limitations of the MCP tools such as "I need to run a forecast (or optimization) and the MCP can't" or "I want to create a repeatable, deterministic workflow" or they may explicitly ask for help getting set up on the API "I want to use the API", "How do I authenticate the API", "How do I get a PAT for the API", etc. The MCP uses OAuth authentication, but all API calls require a PAT.
---

# Recast Getting Started — Auth & Plugin Setup

Recast has **two independent auth paths**. Don't conflate them — using the wrong
one is the most common source of confusion:

| What you're using | How it authenticates | Needs a PAT? |
|---|---|---|
| **MCP server** — the `recast` tools (`list_clients`, `run_report_tool`, `get_report`, …) | **OAuth** browser sign-in with your Recast account | **No** |
| **API skills** — code the `reporter-api` / `forecaster-api` / `optimizer-api` / `plans-api` skills generate to call the Recast API directly | a **`RECAST_PAT`** in the environment | **Yes** |

Most users only need the MCP server, and it needs **no token to configure** —
just an OAuth sign-in. Only reach for a PAT if you'll run the Python/R scripts
the API skills produce.

## Verify that the user wants to execute code
Many users may not be sure what the MCP can do and what the API skills are for. Additionally, users may be non-technical marketers who may not be comfortable running code. However, some users will be data scientists comfortable executing R or Python code. Confirm either from their stated goals or by asking them if they have a code execution environment and want help writing scripts that hit the API. If not, encourage the MCP use and do not try to set up a PAT for them.

## Getting a PAT (only if you'll run API-skill scripts)

Skip this unless you're running code generated by the `reporter-api`,
`forecaster-api`, `optimizer-api`, or `plans-api` skills — those call the Recast API directly
and read a personal access token from the `RECAST_PAT` environment variable. 

1. Log in to the Recast app at https://app.getrecast.com.
2. Open the **account menu** in the top nav bar — the dropdown labeled with your email address.
3. Click **"Generate API Token"**.
4. Confirm the dialog. **Warning:** this revokes any existing API token for the account — if a token is already in use elsewhere (scripts, another machine, Claude Desktop), reuse that token instead of generating a new one.
5. The token is shown **exactly once** in a modal — copy it immediately. It cannot be viewed again, only regenerated.

## Configuring RECAST_PAT (for the API skills)

Encourage users to set a `RECAST_PAT` environment variable following the best practices of whatever language they're using. For example, in Python, you can set it in the shell before running a script:

```bash
export RECAST_PAT="your-token-here"
```

In R, this is typically done in the `.Renviron` file:

```
RECAST_PAT=your-token-here
```

Encourage standard practices for storing secrets, such as using environment variables or secure vaults, and never hardcoding the token in scripts or committing them to version control.

Additionally, if they want Claude Code to see the token, they can add it to `~/.claude/settings.json` under the top-level `env` key:

```json
{
  "env": {
    "RECAST_PAT": "<your-pat>"
  }
}
```
Doing this will make it so Claude can execute the API-skill scripts when running Claude Code anywhere on your machine.


Attribution

getrecastgetrecast
View sourceMore from getrecast →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →