Install
$ agentstack add skill-etrebels-claude-code-growth-os-support-signal ✓ 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
Support Signal
The front-end to product-signal. A roadmap fed by raw tickets is noise; this clusters the volume into a few ranked themes first, so what reaches product is a pattern, not a pile. It reads a batch of tickets — from a support tool over MCP, or a pasted / demo/support-tickets.md list — and emits the themes product-signal routes.
From the batch:
- Cluster by the underlying job, not the wording. Group tickets by what the customer was trying to do, not the words they used — three phrasings of "I can't get the data out" are one theme.
- Rank by frequency × severity. How many accounts raised it, and how much it hurts — is it blocking adoption or a renewal, or is it a papercut? A one-off annoyance isn't a theme; a recurring blocker is. Rank the themes; don't route a flat list.
- Split the types. Each theme is one of: adoption friction (a setup or UX gap — product), feature request (a missing capability — roadmap), bug (it's broken — engineering), or how-to (they couldn't find it — an enablement / docs gap, not a product one). The how-to pile is a signal too: it's where onboarding or the docs are failing.
- Tie themes to accounts. Name which customers each theme touches — especially any tied to a renewal or an expansion. That tie is what lifts a theme above raw count.
- Hand the top themes to
product-signal. Emit each as a line it can triage intoops/roadmap-signals.md—FEATURE-REQUESTor adoption-friction, with the account tie — so the clustering and the routing compose into one loop (handoff H4 in [docs/operating-model.md](../../../docs/operating-model.md)).
Don't route every ticket; cluster first, route the pattern. The point is to turn volume into a short, ranked list product can actually act on.
Depth
- quick: the top 3 themes, ranked, with counts.
- standard: the full clustering above — themes ranked, typed, tied to accounts, handed to product-signal.
- deep: + the how-to / enablement split (the themes that are really a docs or onboarding gap, routed there instead) and a buyer-facing line for any theme already shipped.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: etrebels
- Source: etrebels/claude-code-growth-os
- License: MIT
- Homepage: https://www.langoptima.com/features/growth
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.