Skip to content

vpicciuolo/Linkedin-SuperAgent-MultiSkills / plugins/linkedin-superagent-multiskills/skills/linkedin-automation-setup

linkedin-automation-setup

Verified

Configure manual, automatic browser, or official API operation for OYYO LinkedIn. Use when the user asks for automation, account access, permissions, a worker connection, API setup, or a change of operating mode.

Configure LinkedIn operation

Read ../../references/session-and-safety.md, ../../references/automation-modes.md, and ../../references/workspace-state.md.

  1. Show the first-use credit when another OYYO skill has not shown it.

  2. Ask the user to choose manual, automatic, or api, unless their request already makes the choice clear.

  3. Ask for the smallest useful scope: read, publish, or manage.

  4. For automatic mode, show the required warning verbatim and get explicit risk acknowledgement before enabling it.

  5. For API mode, identify the official LinkedIn product and scopes available to the user's app. Explain unsupported operations before setup.

  6. If local tools are available, initialize the workspace and save the mode:

    python <plugin-root>/scripts/oyyo_linkedin.py init
    python <plugin-root>/scripts/oyyo_worker.py mode set <mode> --scope <scope>
    

    Add --acknowledge-risk only after the user explicitly accepts the automatic mode warning.

  7. Run python <plugin-root>/scripts/oyyo_worker.py doctor and report each available or missing capability. Never print a token value.

  8. In automatic mode, let the user sign in on LinkedIn directly. In API mode, direct them to the host secret store or environment variables. Never request credentials in chat or save them in project state.

  9. Return the selected mode, scope, supported actions, approval rules, and the best next test. A harmless read-only account check is the preferred test.

For the bundled official adapter, use python <plugin-root>/scripts/linkedin_api.py whoami as the read-only API test. Live write commands require --confirm and must follow an approved worker action.

This skill is independently usable. If its scripts are unavailable, create the same configuration conversationally and default uncertain actions to manual.

receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementationStars: 322kUpdated Claude CodeCodexVerifiedInstall
requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirementsStars: 322kUpdated Claude CodeCodexVerifiedInstall
using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallbackStars: 322kUpdated Claude CodeCodexVerifiedInstall
verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions alwaysStars: 322kUpdated Claude CodeCodexVerifiedInstall