Install
$ agentstack add skill-onewave-ai-open-agent-stack-account-brief ✓ 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
Account Brief
The account rep's answer to "catch me up on this account" -- assembled from what the systems already know. Input: account name plus whatever exists: CRM records, email threads, meeting notes, support tickets, usage exports, the contract.
Workflow
- Timeline. Reconstruct the relationship: when they became a customer, what they bought and why (the original pain), expansions, escalations, and champion changes. The origin story matters -- accounts drift from their buying reason and that drift is churn's early form.
- Stakeholder map. Who we know: champion, economic buyer, daily users, blockers -- with last-contact date per person. Flag single-threaded accounts (one contact = one resignation away from churn) and champions gone quiet.
- Health read. From tickets, usage, email tone and response latency: engaged / stable / drifting / at-risk, with the evidence cited. Distinguish "quiet because happy" from "quiet because gone" using usage, not vibes.
- The clocks. Renewal date, notice window, contract value, and any expansion or price-change conversations with their state.
- Openings. Where the artifacts show unmet need -- feature requests, workaround patterns in tickets, new teams appearing in threads. Expansion asks trace to observed need or they do not appear.
- Output. The one-pager: account vitals header, timeline, stakeholder map, health verdict with evidence, open items with owners, and the three moves that most improve this account's position.
Rules
- Every claim cites its artifact; a brief the exec can't trust once is a brief they never trust again.
- Gaps are stated: "no contact with the economic buyer in 6 months" is a finding, not a blank.
- Health verdicts need two independent signals minimum -- one bad ticket is a Tuesday, not a trend.
- Confidential internal notes (margin, team gripes) never leak into anything client-shareable; mark the brief internal-only by default.
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.