Install
$ agentstack add skill-onewave-ai-open-agent-stack-call-prep ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Call Prep
Walk in knowing more than the other side expects. Input: company name and meeting context (first call, demo, negotiation, renewal); attendee names/LinkedIn URLs if known; anything from the CRM or email thread history available.
Workflow
- Research the company. Web-search recent news, funding, leadership changes, hiring signals (what roles they are posting reveals priorities), and their own positioning language. Find the thing that changed recently -- meetings exist because something changed.
- Read the attendees. Role, tenure, likely care-abouts by function (a CFO hears risk and payback; an ops lead hears hours saved). Note shared ground if it is real; skip manufactured rapport.
- Pull the history. From CRM/email/notes provided: every prior touch, what was promised, open threads, and anything they told us before -- asking a question they already answered costs credibility.
- Write the brief, one page: why this meeting is happening (their trigger, not our pipeline stage), 5-7 discovery questions sequenced from situation to pain to stakes -- specific to their business, not a generic SPIN list; the 3 objections most likely for this profile, each with an honest answer; the single realistic goal for the call and the specific next step to propose before hanging up.
Rules
- Every discovery question must be un-Googleable -- if the answer is on their website, asking it burns the meeting.
- Objection answers are honest, including "that's a real limitation, here's the trade" where true.
- One goal per call. A brief with four goals produces a call with none.
- Flag what you could not verify; a brief with a wrong fact is worse than a gap.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: OneWave-AI
- Source: OneWave-AI/open-agent-stack
- License: MIT
- Homepage: https://www.onewave-ai.com
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.