What makes outlit notable?

2K downloads. Trust evidence available

How should outlit be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

outlit

Use when accessing Outlit customer intelligence through the `outlit` CLI, Outlit MCP tools, Pi tools, or @outlit/tools, including customer lookups, users, workspace users, timelines, facts, source evidence, semantic search, revenue, churn, SQL analytics, identity splits, merge suggestions, setup, integrations, or troubleshooting agent access. Skill: outlit Owner: leo-paz Summary: Use when accessing Outlit customer intelligence through the outlit CLI, Outlit MCP tools, Pi tools, or @outlit/tools, including customer lookups, users, workspace users, timelines, facts, source evidence, semantic search, revenue, churn, SQL analytics, identity splits, merge suggestions, setup, integrations, or troubleshooting agent access. Tags: latest:1.0.11 Version history: v1

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

2.0k

Updated

Oct 9, 2026

Version

1.0.11

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 2K downloadsadoption · observed Oct 9, 2026
Latest release: 1.0.11release · observed Sep 29, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s1719ryyr8azsrbf1erk7aem7x84mmzf:outlit

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-leo-paz-outlit/snapshot"

Documentation

CLAWHUB

146,246 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: outlit
description: Use when accessing Outlit customer intelligence through the `outlit` CLI, Outlit MCP tools, Pi tools, or @outlit/tools, including customer lookups, users, workspace users, timelines, facts, source evidence, semantic search, revenue, churn, SQL analytics, identity splits, merge suggestions, setup, integrations, or troubleshooting agent access.
metadata:
  openclaw:
    homepage: "https://outlit.ai"
    emoji: "🔦"
    requires:
      bins: [outlit]
    primaryEnv: OUTLIT_API_KEY
    install:
      - kind: node
        package: "@outlit/cli"
        bins: [outlit]
      - kind: brew
        formula: outlitai/tap/outlit
        bins: [outlit]
---

# Outlit

Outlit joins product activity, conversations, billing, support, CRM, and web signals into customer profiles, timelines, facts, and source evidence for agents.

## When to Use Outlit

Use Outlit when the user needs real customer context for onboarding, adoption, retention, renewal, or expansion. Typical jobs include:

- Find accounts with declining activity, renewal risk, expansion demand, or stalled onboarding.
- Explain what changed for a customer and trace the answer to facts, events, conversations, or source records.
- Prepare account research, customer-success follow-up, or custom analytics across customer data.
- Inspect or configure an Outlit workspace capability when the user explicitly asks.

Do not call Outlit for generic customer-success advice that does not need workspace data. Use the `outlit-sdk` skill instead when the user wants to instrument an application with tracking SDKs.

## Choose the Interface

Use the highest-level interface already available:

1. If suitable `outlit_*` MCP or Pi tools are present, call them.
2. Otherwise, if the `outlit` CLI is installed, use it.
3. Otherwise, guide setup:
   - Coding agents: run `outlit onboard --agent <agent> --json`. Outside CI, it can start browser approval when no key is available, install this skill, validate access, and return next actions.
   - Skills only: run `outlit setup --yes` or `outlit setup skills`.
   - MCP clients: use the workspace URL from **Settings > CLI & MCP** and complete OAuth in the client. Do not hardcode a shared endpoint, bearer header, or API key into remote MCP configuration.

## Quick Chooser

Tool availability depends on the MCP server or Pi tool policy. If a named tool is absent, use the CLI only where your policy permits, or ask the user to enable the appropriate toolset.

| Need | Tool when exposed | CLI |
|------|-------------------|-----|
| Browse customers | `outlit_list_customers` | `outlit customers list` |
| Browse customer-associated users | `outlit_list_users` | `outlit users list` |
| Browse workspace users | `outlit_list_workspace_users` | `outlit ws-users list` |
| Single account profile | `outlit_get_customer` | `outlit customers get` |
| Current customer relationship | `outlit_get_customer_relationship` | `outlit customers relationship` |
| Chronology | `outlit

_meta.json

{
  "ownerId": "kn7c03kweztgxab3q20f9vahz1817040",
  "slug": "outlit",
  "version": "1.0.11",
  "publishedAt": 1790653043637
}

references/identity.md

# Customer identity and merge workflow

Use the tool schemas exposed by the connected MCP server or installed CLI. Identity tools require a supporting server rollout and client version; documentation alone does not prove they are deployed. If a tool is absent, check the installed CLI help and available published upgrade. Do not invent a command or bypass an agent policy.

## Diagnose before combining records

`outlit_get_customer_identity` takes `{ customerId }` and returns candidate metadata and supporting references, a search window, timestamps, coverage, and limits. Its current search is bounded by call-participant domains, not every possible identity source. Candidates do not grant access to another customer's evidence. Treat an incomplete result as unknown coverage.

```sh
outlit customers identity <customerId> --json
```

Inspect exact customer records and source evidence within your existing access. A shared consultant, similar company name, related domain, or parent/subsidiary relationship is not enough to establish that the records represent the same company. If uncertain, stop at diagnosis and explain the uncertainty.

## Saved suggestions and existing work

`outlit_list_identity_merge_suggestions` accepts optional `customerId`, `suggestionId`, `status`, `confidence`, `cursor`, and `limit`. It returns `{ suggestions, nextCursor, canManageIdentityMerges }`. The default limit is 50 and maximum is 100. Status filters are `suggested`, `processing`, `merged`, and `rejected`; confidence filters are `HIGH`, `MEDIUM`, and `LOW`.

```sh
outlit identity suggestions list --customer-id <customerId> --json
outlit identity suggestions list --suggestion-id <suggestionId> --json
```

Each suggestion includes its `id`, survivor, duplicate, review details, impact, `canMerge`, `canReject`, and nullable `latestJob`. Inspect one suggestion through this list filter; there is no separate suggestion-get tool. Follow `nextCursor` using `--cursor` for more pages.

When `latestJob.operationId` is non-null, pass it to the status tool. `latestJob.id` is a job ID, not an operation ID. A null operation ID means there is no matching tracked operation for that job; do not substitute the job ID or infer that no work has happened. An empty suggestion list does not rule out an unsuggested merge. Reuse an operation ID from an earlier execution response when available.

If a merge is already queued or running, track it rather than submitting a new request. If prior execution is uncertain, retry only the identical execution input with its original request ID. Do not generate a new ID to get around a conflict. If prior execution is uncertain and neither the original request ID nor operation ID is available, stop execution and report the unresolved state.

To reject a suggestion when the user asks, use `outlit_reject_identity_merge_suggestion` with `{ suggestionId, reviewNotes? }`. Its response is exactly `{ suggestionId, status: "REJECTED" }`; rejection keeps the records sepa

references/sql-reference.md

# SQL Reference

Use this when writing or debugging `outlit_query` / `outlit sql` queries.

Always inspect schema first with `outlit_schema` or `outlit schema`.

## Tables

Use the public analytics views exposed by `outlit schema`, not backend table names:

- `activity`: product, communication, support, CRM, and other customer activity
- `customers`: customer/account attributes, billing status, and revenue fields
- `users`: user/contact attributes and journey-stage fields
- `revenue`: revenue and MRR reporting fields

## ClickHouse patterns

```sql
now()
today()
toStartOfMonth(occurred_at)
dateDiff('day', first_seen_at, now())
occurred_at >= now() - INTERVAL 30 DAY
countIf(billing_status = 'PAYING')
sumIf(mrr_cents, billing_status = 'PAYING')
JSONExtractString(properties, 'path')
```

Use ClickHouse syntax, not MySQL or Postgres helpers like `DATE_SUB()`.

## Rules

- Only `SELECT` queries are allowed.
- Add time filters for event queries.
- Use `LIMIT`.
- Prefer specific columns over `SELECT *`.
- Divide cents by `100` for display.

## Use SQL when

- You need aggregates, cohorts, joins, or time-series analysis.
- You need cross-customer reporting.

Use customer tools or commands instead for single-account lookups.

skill-card.md

## Description:

Guides agents in using Outlit customer intelligence to investigate accounts, analyze customer data, and manage authorized workspace changes through available tools.

This skill is ready for commercial/non-commercial use.

## Publisher:

[leo-paz](https://clawhub.ai/user/leo-paz)

### License/Terms of Use:

MIT-0

## Use Case:

Customer-success teams and developers use this skill to investigate onboarding, adoption, retention, renewal, and expansion using Outlit customer records and analytics. With explicit authorization, they can also configure workspace capabilities and review customer identity changes.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Piping a downloaded installer into a shell can execute unreviewed code.

Mitigation: Prefer the documented npm or Homebrew installation paths when practical.

Risk: Workspace write grants can change access, destinations, integrations, activation, settings, Features, or identity records.

Mitigation: Confirm the intended change and grant only the permissions needed before allowing write actions.

Risk: Customer merges are irreversible and can combine unrelated records.

Mitigation: Review the merge preview and execute only after clear authorization and confirmation that both records identify the same customer.

## Reference(s):

- [Outlit documentation](https://docs.outlit.ai/)
- [Outlit documentation index](https://docs.outlit.ai/llms.txt)
- [Outlit homepage](https://outlit.ai)
- [Outlit ClawHub release](https://clawhub.ai/leo-paz/skills/outlit)
- [Customer identity and merge workflow](references/identity.md)
- [SQL reference](references/sql-reference.md)

## Skill Output:

**Output Type(s):** [Text, Markdown, Shell commands, SQL, Configuration guidance]

**Output Format:** [Markdown with inline commands and query examples]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Responses should distinguish evidence from interpretation; workspace changes require explicit authorization.]

## Skill Version(s):

1.0.11 (source: server-resolved ClawHub release)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 2h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.