← Tough Tongue AICONTENT HISTORY

Update to Tough Tongue AI

Snapshot Sep 30, 2026 · 22:56 UTC · version 1.0.0

Collection source: not recorded for this historical snapshot.

WHAT CHANGED · RULE-BASED ANALYSIS

First saved snapshot

No earlier snapshot is available to establish a change.

Compare saved observations

Download comparison JSON
Full technical diff · 0 changed fields
Full snapshot data
{
  "name": "getting-started",
  "description": "Onboard a user to the ToughTongue AI plugin: verify the MCP connection and PAT, look at what's in their account, and route them into their first workflow. This skill should be used when the user says \"get started with ToughTongue\", \"set up ToughTongue\", \"is my ToughTongue MCP working\", \"test my ToughTongue connection\", \"what can I do with ToughTongue\", or has just installed the plugin. Not for creating, refining, or analyzing scenarios directly — hand off to scenario-creator, scenario-refiner, or session-analyst for those.",
  "included_files": [],
  "skill_md_contents": "---\nname: getting-started\ndescription: >\n  Onboard a user to the ToughTongue AI plugin: verify the MCP connection and\n  PAT, look at what's in their account, and route them into their first\n  workflow. This skill should be used when the user says \"get started with\n  ToughTongue\", \"set up ToughTongue\", \"is my ToughTongue MCP working\",\n  \"test my ToughTongue connection\", \"what can I do with ToughTongue\", or has\n  just installed the plugin. Not for creating, refining, or analyzing\n  scenarios directly — hand off to scenario-creator, scenario-refiner, or\n  session-analyst for those.\n---\n\n# Getting Started with ToughTongue\n\nVerify the setup, orient around the user's account, and launch their first\njourney. Keep each step short — this is a welcome mat, not a manual.\n\n## Step 1: Verify the connection\n\nCall the `ttai` MCP tool `list_organizations`.\n\n- **Tools not found** — the MCP server is not registered. Ask how they\n  installed:\n  - Plugin install: restart the agent app fully and start a new thread; the\n    plugin registers the server via its bundled `.mcp.json`.\n  - Skills-only install (skills.sh / Cursor): register manually —\n    `codex mcp add ttai --url https://api.toughtongueai.com/api/public/mcp\n    --bearer-token-env-var TTAI_PAT` (Codex) or\n    `claude mcp add --transport http ttai\n    https://api.toughtongueai.com/api/public/mcp\n    --header \"Authorization: Bearer ${TTAI_PAT}\"` (Claude Code).\n- **401 / auth error** — the PAT is not visible to the agent process. Walk\n  through: create a token at <https://app.toughtongueai.com/developer>,\n  `export TTAI_PAT=\"<token>\"` in the shell profile, on macOS also\n  `launchctl setenv TTAI_PAT \"$TTAI_PAT\"`, then fully quit and reopen the\n  agent app. NEVER ask the user to paste the token into the chat.\n- **Success** — report what came back: personal account only, or\n  organizations (name them). Explain that org work needs `org_id` passed to\n  tools, and this happens automatically in the other skills.\n\n## Step 2: Orient around the account\n\nCall `list_scenarios`, and `list_sessions` with a small limit.\n\nSummarize in 2-3 sentences what exists: how many scenarios, whether sessions\nhave been run, whether analyses are present. This decides the recommended\nfirst journey below.\n\n## Step 3: Launch the first journey\n\nOffer the paths that fit what Step 2 found, then invoke the matching skill:\n\n| Account state | Recommend | Skill |\n|---|---|---|\n| Empty (no scenarios) | Create a first practice scenario from a brief, URL, or call transcript | **scenario-creator** |\n| Scenarios but few sessions | Share a practice link; or create a scenario for an upcoming meeting | **scenario-creator** |\n| Sessions with analyses | Team/scenario performance report | **session-analyst** |\n| Low-scoring or complained-about scenario | Diagnose and fix it from real transcripts | **scenario-refiner** |\n\nClose by showing 2-3 of these prompts as things to try next (pick the ones\nmatching their account state):\n\n- \"Pull the last 3 calls from Gong where we lost on pricing and create a\n  practice scenario for that objection.\"\n- \"For my discovery-call scenario, pull the last 50 sessions — what are the\n  top 5 improvement areas?\"\n- \"Pull the 5 lowest-scoring sessions for our onboarding scenario and fix\n  the scenario.\"\n- \"I have a call with [name] from [company] in 30 minutes — create a quick\n  practice scenario so I can rehearse.\"\n"
}

SHA-256: f4ef47b41c05f2436720c6100ae52b535b48b36ace669ad67850f7edb2a68086