Conversation
Score leads and launch AI voice + SMS engagement sequences. Supports real estate, debt collection, healthcare, and home services. MCP endpoint: https://mcp.aivi.io/mcp Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
@aivillc is attempting to deploy a commit to the 0xBuns Team on Vercel. A member of the Team first needs to authorize it. |
Greptile SummaryThis PR adds a new
The skill file itself should not be committed to the repository at all — it must be published via the ClawHub CLI instead.
Confidence Score: 0/5
Prompt To Fix All With AIThis is a comment left during a code review.
Path: skills/aivi-engagement/SKILL.md
Line: 56-76
Comment:
**`get_outcome` missing from billing table**
The `get_outcome` skill is documented above (lines 56–65) but has no corresponding entry in the billing table at the bottom of the file. If it is free, an explicit `Free` row would make the cost model complete and avoid confusion for users.
```suggestion
| score_lead | $0.75 |
| launch_sequence (one_day) | $1.00 |
| launch_sequence (three_day) | $1.50 |
| launch_sequence (twelve_day) | $3.00 |
| Booking add-on | +$1.00 |
| onboard_organization | Free (includes $5 trial credits) |
| get_outcome | Free |
```
How can I resolve this? If you propose a fix, please make it concise.Reviews (1): Last reviewed commit: "feat: add AIVI Lead Engagement skill" | Re-trigger Greptile |
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
| Returns: org_id, API key (shown once), AI agent config, $5 trial credits. | ||
|
|
||
| ### get_outcome | ||
| Use when: user wants to know what happened on a call or sequence. | ||
|
|
||
| Example prompts: | ||
| - "What happened on that call?" | ||
| - "Did the sequence convert?" | ||
| - "Show me the topics from the last call" | ||
|
|
||
| ## Billing | ||
| All skills require AIVI credits. Add credits at app.aivi.io → Billing. | ||
|
|
||
| | Skill | Cost | | ||
| |-------|------| | ||
| | score_lead | $0.75 | | ||
| | launch_sequence (one_day) | $1.00 | | ||
| | launch_sequence (three_day) | $1.50 | | ||
| | launch_sequence (twelve_day) | $3.00 | | ||
| | Booking add-on | +$1.00 | | ||
| | onboard_organization | Free (includes $5 trial credits) | |
There was a problem hiding this comment.
get_outcome missing from billing table
The get_outcome skill is documented above (lines 56–65) but has no corresponding entry in the billing table at the bottom of the file. If it is free, an explicit Free row would make the cost model complete and avoid confusion for users.
| Returns: org_id, API key (shown once), AI agent config, $5 trial credits. | |
| ### get_outcome | |
| Use when: user wants to know what happened on a call or sequence. | |
| Example prompts: | |
| - "What happened on that call?" | |
| - "Did the sequence convert?" | |
| - "Show me the topics from the last call" | |
| ## Billing | |
| All skills require AIVI credits. Add credits at app.aivi.io → Billing. | |
| | Skill | Cost | | |
| |-------|------| | |
| | score_lead | $0.75 | | |
| | launch_sequence (one_day) | $1.00 | | |
| | launch_sequence (three_day) | $1.50 | | |
| | launch_sequence (twelve_day) | $3.00 | | |
| | Booking add-on | +$1.00 | | |
| | onboard_organization | Free (includes $5 trial credits) | | |
| | score_lead | $0.75 | | |
| | launch_sequence (one_day) | $1.00 | | |
| | launch_sequence (three_day) | $1.50 | | |
| | launch_sequence (twelve_day) | $3.00 | | |
| | Booking add-on | +$1.00 | | |
| | onboard_organization | Free (includes $5 trial credits) | | |
| | get_outcome | Free | |
Prompt To Fix With AI
This is a comment left during a code review.
Path: skills/aivi-engagement/SKILL.md
Line: 56-76
Comment:
**`get_outcome` missing from billing table**
The `get_outcome` skill is documented above (lines 56–65) but has no corresponding entry in the billing table at the bottom of the file. If it is free, an explicit `Free` row would make the cost model complete and avoid confusion for users.
```suggestion
| score_lead | $0.75 |
| launch_sequence (one_day) | $1.00 |
| launch_sequence (three_day) | $1.50 |
| launch_sequence (twelve_day) | $3.00 |
| Booking add-on | +$1.00 |
| onboard_organization | Free (includes $5 trial credits) |
| get_outcome | Free |
```
How can I resolve this? If you propose a fix, please make it concise.![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 636c60e8ed
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| @@ -0,0 +1,76 @@ | |||
| --- | |||
There was a problem hiding this comment.
This change adds a new skill file under skills/, but the repository policy in AGENTS.md explicitly says PRs that add skills directly to repo content (including under skills/) must be rejected and that skills should be uploaded/published via CLI. Keeping this file in-tree bypasses the required publishing workflow and can leave repository state inconsistent with the actual published skill catalog.
Useful? React with 👍 / 👎.
773 calls analyzed, 494 moments detected. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 7dc7770838
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| @@ -0,0 +1,98 @@ | |||
| --- | |||
There was a problem hiding this comment.
This commit adds skills/aivi-engagement/SKILL.md directly to the repository, but AGENTS.md:43 explicitly requires rejecting PRs that add published skills in-tree and mandates publishing them via the CLI workflow instead. Keeping this file in git bypasses the required release path and can leave repository contents out of sync with the actual published skill catalog.
Useful? React with 👍 / 👎.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 8acb7a30b0
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| ALWAYS ask for API key before any skill call. | ||
| NEVER proceed without a valid api_key. | ||
|
|
There was a problem hiding this comment.
The global rule to always require a valid api_key before any skill call makes the documented onboard_organization flow unreachable for first-time users, because that operation is explicitly for users who do not have a key yet. In this state, a new customer asking to create an account will be blocked before the only self-service onboarding action can run.
Useful? React with 👍 / 👎.
| "Remember my AIVI API key is aivi_sk_xxxxx" | ||
|
|
||
| Claude will remember it across all future conversations. You will never need to type it again. |
There was a problem hiding this comment.
This instruction asks users to put raw API keys directly into conversational memory, which increases credential exposure through chat history/log retention and contradicts safer secret handling patterns (e.g., environment variables already declared in the frontmatter). The skill should avoid encouraging plaintext key sharing in prompts and direct users to secure credential configuration instead.
Useful? React with 👍 / 👎.
1 participant
Summary
MCP Endpoint
https://mcp.aivi.io/mcpSkills
Test plan
Note on CI
The Vercel deployment check fails because the fork doesn't have Vercel authorization — this is expected for external PRs. The skill files are markdown only (no build needed).