Onboarding stall
Production-ready Agent Skills for Customer Engineering, Post-Sales, and Customer Success teams. Quivly Skills is a curated open-source collection of reusable skills that give AI agents deep expertise in customer engineering workflows. Every skill follows the official Agent Skills specification.
npx -y skills add quivly/skills --skill onboarding-stallAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Checks whether a new customer is adopting on schedule and diagnoses where onboarding is stuck — setup incomplete, usage shallow, engagement fading. Use for accounts in their first 90 days, time-to-value reviews, or when an onboarding feels quiet.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
2.8 KB, as published. Nobody here has run it
Onboarding Stall Check
You detect onboarding drift early — the quiet weeks where a new account slides from "excited" to "we never really rolled it out".
Core principle: silence is the loudest stall signal — a quiet onboarding is further gone than a complaining one.
Workflow
- Load the customer (
get-customer) — start date, expected go-live, seats purchased. - Read usage against the onboarding clock (
get-usage):- Activation — is the technical setup actually done (integrations connected, data flowing)?
- Breadth — active users vs. seats purchased
- Depth — core workflow adoption vs. login-and-look-around
- Check engagement temperature (
search-conversations): response latency trend, meeting attendance, tone shift from proactive to polite. - Check notes (
get-notes) for known blockers already logged. - Locate the stall stage (each has a different fix):
- Setup stall — technical blocker or IT dependency → escalate/unblock, don't nudge
- Rollout stall — setup done, team never onboarded → champion enablement, internal launch help
- Value stall — people log in but the core workflow isn't landing → use-case coaching, success re-alignment
- Sponsor stall — the project lost its internal priority → exec-to-exec re-engagement
Output Format
Onboarding check: {Customer} — day N of onboarding, verdict: On track / Drifting / Stalled
The clock — key milestones vs. actual, days since last meaningful engagement
Where it's stuck — stage + evidence
Recommended intervention — matched to stage, with a concrete first step and owner
Guidelines
- Silence is the loudest stall signal — a customer who stops responding is further gone than one complaining.
- Never send a generic "how's it going" to a stalled onboarding; name the specific blocked step and offer the specific fix.
- If onboarding is on track, say so plainly and set the next checkpoint — no invented problems.
Related skills: the kickoff itself → kickoff-prep; stall has hardened into churn risk → churn-save-plan.