Terminal
Terminal/Skill
Clay's table of contents: maps what you want to do, such as audiences, search, routines or workflows, to the right Clay skill.
By Clay
Works with
npx skills add clay-run/agent-plugins --skill clayClay is a GTM (go-to-market) data and automation product. This skill is a table of contents: find what you want to do and go to that skill.
Campaigns and Sequencer are interchangeable names for the same product surface. When the campaigns skill is available, route requests using either name to that skill and clay campaigns. A sequence is the message flow within a campaign.
Whatever you're doing in Clay, work transparently so the user can follow along:
jq, diff) into a
short takeaway, table, or count. Reserve raw output for when the user asks.clay whoami and tell the user which workspace (id) and user you're authenticated
as. If it's wrong, they can switch with clay logout then running clay login
again. If whoami fails on auth, run the setup skill.When a user asks what they can do, you are describing Clay's product, not your own abilities. Get the framing right:
Position it as Clay's, and as theirs to run. Say "Clay lets you…" and "you can…", not "skills I have," "here's what I can run for you," or "what you can do through me." These are Clay capabilities the user drives; you're just the interface.
Don't call them "playbooks." The surfaces below (audiences, searches, routines, tables, workflows, the CLI, the API) are Clay primitives and product surfaces — describe them as what they are. "Playbook" is wrong and confusing.
Don't crown Workflows as the main or "biggest" surface. Lead with Audiences, Search, and Clay-managed functions — those cover the large majority of GTM tasks. Reach for Workflows when a function genuinely can't do the job, and mention them as one option rather than the headline.
Lead with concrete, show-off use-cases, not a menu of verbs. Ground the answer in outcomes the user recognizes. Good examples to draw from (pick a few relevant ones, don't list all):
Then offer to run one — the goal is a first win, not reciting a catalog.
Clay exposes four core primitives (callable from the plugin/CLI/API):
| Primitive | What it's for |
|---|---|
| Audiences | The workspace's own people, companies, and deals — read and segment what they have |
| Searches | Find companies and people using Clay's GTM database |
| Routines | Run Clay-managed functions, custom functions, and Workflows |
| Tables (Enterprise) | Query existing Clay tables only — you cannot create tables programmatically |
Follow this escalation order — reach for the earliest option that fits:
clay routines list — check the catalog before building anything.If you are unsure what to surface, ask the user. There are often multiple ways to accomplish the same task, so when the choice is ambiguous, do not pick one arbitrarily.
Credit-consuming actions spend the user's money — always check in with the user and get their explicit go-ahead before running one. Never kick one off on your own initiative or "to be helpful." First show the user the estimated cost and the remaining balance, then wait for them to confirm.
Actions that consume credits (or count against plan/search limits) and require a check-in first include running a routine, testing or resuming a workflow, and some types of search.
Before running a credit-consuming routine, check its per-item estimatedCreditCost
(clay routines get <id>) against the remaining workspace balance (clay credits). See the
routines skill for how to size a run against the balance.
| Skill | Use it for |
|---|---|
audiences | Any question about the workspace's own people/companies/deals — counts, fill rates, lookups, and segments. |
search | Finding people or companies in Clay's GTM database with advanced queries or existing filters-mode searches. |
routines | Creating a routine from an existing function/workflow, running a saved routine, and fetching its results. |
tables-cli | Reading, querying, and exporting data from an existing Clay table via the CLI (creating tables is not supported). |
cli | Ephemeral, programmatic access to Clay capabilities from a shell — run a routine, query a table, search, etc. |
public-api | Building services and applications on top of Clay over HTTP. |
workflows-cli | Building and editing Clay workflows via the CLI. |
workflows-vs-tables | Explaining the difference between Workflows and Tables, or recommending which to use. |
clay-feedback | Sending a bug report or product feedback to the Clay team. |
If clay-for-reps (the Clay MCP for sales reps) is also connected in your session,
ignore its tools entirely. That server is designed for interactive conversational prospecting
in chat apps (ChatGPT, Claude.ai) — it shares the same Clay workspace but is a completely
different product. Use the clay CLI and these skills for all automation, data enrichment,
and GTM operations.
Run the setup skill.
Check clay update --check to make sure you're on the latest CLI version. To update Clay — update the plugin (which
pins the clay CLI it bundles) — use the update skill.