Day-zero checklist: main Bot, connectors, CLI and recurring work

Check role setup, identity, execution environment and triggers separately before expanding a first workflow.

The source covers a main Bot, fixed tasks, specialist skills, CLI tools and connectors. This checklist preserves the sequence while keeping third-party installation conditional.

Verification status

Source reading and media coverage are listed below. This site has not executed the live workflow. Fixtures, fields and prompts here are independent exercises, not the author’s results.

Scenario and input

Synthetic goal: a main Bot handles one research request and returns three sourced points.

1. Define the main role

Explain intake, clarification and concise reporting in chat. Start with role proposals rather than automatic roster creation.

2. Run one fixed task

Use explicit input and acceptance criteria, checking that the original source was actually read.

3. Check connector identities

Verify account and scope in the current connection interface, then use a small read-only test. Manage external authorization separately from a Bot’s existence.

4. Distinguish CLI environments

Record whether a CLI runs locally or in the cloud, its identity and its allowance. Use its supported authentication flow rather than copying sessions.

5. Add triggers last

After stable manual results, propose skills or triggers with timezone, duplicate handling and stop conditions.

A synthetic acceptance fixture

capabilities.csv: capability, account, environment, read_test, write_scope. An X connection does not prove CLI authorization; cloud and local environments get separate rows.

Copyable task brief

Copy template

Use the synthetic fixture to prepare the deliverable for Day-zero checklist: main Bot, connectors, CLI and recurring work. Do not connect real services yet.
Input: Synthetic goal: a main Bot handles one research request and returns three sourced points.
Requirements:
1. Explain intake, clarification and concise reporting in chat. Start with role proposals rather than automatic roster creation.
2. Use explicit input and acceptance criteria, checking that the original source was actually read.
3. Verify account and scope in the current connection interface, then use a small read-only test. Manage external authorization separately from a Bot's existence.
4. Record whether a CLI runs locally or in the cloud, its identity and its allowance. Use its supported authentication flow rather than copying sessions.
5. After stable manual results, propose skills or triggers with timezone, duplicate handling and stop conditions.
Return itemized records, evidence locations, unknowns and next steps, marking unperformed actions explicitly.
Do not install tools, change access, purchase, publish, create Bots or schedule work in this pass.

Acceptance and review

Each capability has an identity and environment, with uninstalled skills and uncreated triggers clearly recorded.

Copy template

Review the artifacts without taking external actions.
Acceptance: Each capability has an identity and environment, with uninstalled skills and uncreated triggers clearly recorded.
Separate pass, fail, untested and evidence; distinguish synthetic fixtures from live results.
Stop on missing sources, permissions or uncertain outcomes and list the required evidence.
Propose one next step with a recovery plan and wait for confirmation.

Sources and applicability

Original article: @czzzzzzJ_; published 2026-10-14.

Index-to-source mapping: strong content match.

The collector reports viewing 26 images; 0 videos remain unwatched. Screenshots add main-Bot settings, connectors, handoff receipts and local versus cloud CLI use. An unreadable small-text setting is not made into a universal instruction.

Prices, interfaces and menus change. Check unresolved conditions against the actual account and current official documentation.

See the rewrite and verification map for all 24 sources