Run it yourself, or let it run itself
Every entry here is the same underlying thing: a prompt that does one job on your tickets. What changes is what starts it — and that’s the whole difference between a skill and an agent.
Every Agent can also be run by hand in Super Magic — that’s how you prove one before you wire the trigger.
Agents
A Flow runs these unattended — add a trigger and a write scope and the job runs itself.
Skills
You run these on demand in Super Magic, confirming each write as it goes.
This library is public and fully crowdsourced — every entry started as a prompt someone wrote for their own desk, and anyone can add one.
Contribute a skill
Built something clever in Super Magic, or have a workflow your peers would love? Share it. The library is open to everyone — every skill here started as a prompt someone wrote for their own desk, and yours can join them.Add or improve a skill on GitHub
Fork the repo, add your skill, and open a pull request. Once it’s approved it syncs into this library automatically — credited to you in the repo history.
1
Fork the repo and copy the template
Fork Thread-Magic/super-magic-skills, then copy TEMPLATE.md to
skills/<category>/<your-skill>/SKILL.md.2
Write it in plain language
Fill in the frontmatter (category, role, outcome, connectors) and write the prompt the way you’d explain the task to a teammate — no code, no tool names. Keep the prompt under 3,000 characters: that’s Super Magic’s limit on skill instructions, so a longer one can’t be saved. The contributing guide has the full format and a checklist.
3
Open a pull request
Submit your PR. A maintainer reviews it, and once it’s merged it appears here on the next sync.
Popular skills
Smart Dispatch
Auto-assign and schedule your techs by expertise and load
Skill-Based Routing
Route to whoever actually fixed this before — not just whoever’s free
Duplicate Hunter
Catch duplicate tickets before they waste tech time
Catchall Routing
Automatically route ownerless tickets to the right client
Queue-Scoring Triage
Always know which ticket to work next
Ticket QA Review
Automate ticket QA against your own rubric
Stale-Ticket Follow-up
Automate the follow-up nobody has time for
CSAT Follow-up Loop
AI-driven CSAT capture and follow-through
Escalation Prep
Hand off a ticket cold-ready, every time
Shift Handoff
Nothing drops between shifts
Phishing Triage
Automate first-response security triage
Client Risk Scan
Spot at-risk accounts before they churn
QBR & SBR Prep
Walk into every QBR already briefed
KB Article Draft
Turn every resolution into reusable self-service content
Ticket Research Co-pilot
Cited, evidence-based research before you touch the ticket
Liongard Access Pattern
See what changed, across every connected system
Device Health Check
Diagnose a device fleet and get a remediation plan
New Hire Onboarding Coach
Train a new tech on real tickets, scored against your rubric
Client Reply
Draft the client reply in your house voice
Daily Digest
Your open tickets, skimmable in under a minute
Ticket Summary & Closure Note
A clean closure note, every time
Custom Time-Entry Writer
Time entries written your way
Verified
Battle-tested on real MSP service desks — the proven subset of the library. See all verified skills.Escalation Advisor
Sweep active tickets against L2/L3, management, and project-conversion trigger lists and recommend which should escalate: before they age into problems.
New Hire Onboarding
Run a new-hire onboarding end to end with role-based accounts, licenses, groups, hardware, and MFA driven from the client’s own onboarding checklist.
Ticket QA Review
Grade a completed ticket against the closure rubric (resolution, classification, owner, time logged, title, client message) pass or bounce it back.
Catchall Routing
Identify the correct client and contact for a ticket that landed in a catchall or no-company mailbox, including forwarded mail and vendor alert routing.
Printer Troubleshooting
Diagnose printing problems (nothing prints, stuck queues, garbled output, wrong printer, scan-to-email fails) via a spooler, driver, and network matrix.
Ticket Triage
Classify a new or unassigned ticket, gauge severity, catch duplicates, and route it to the right board, status, and priority for the queue.
Backup Failure Triage
Classify a backup failure by alert text and device state, check for recurrence, and decide whether to fix locally or escalate to the backup vendor.
Client Health Report
Summarize a client’s support health for a period: volume trend, recurring issues, noisy assets, SLA performance, and a few concrete recommendations.
Device Offline Runbook
Work a device-offline alert or “won’t connect” ticket: site-wide check first, maintenance windows, last activities, and clear escalate criteria.
Duplicate Hunter
Check whether a ticket duplicates an existing open ticket for the same client, contact or asset, and symptom, and merge only on an exact reference match.
Scheduling Intent Detector
Find “can we get on a call / book a time” requests hiding in recent tickets and route them to scheduling, skipping tickets where a tech has already engaged.
Shift Handoff
Produce a skimmable end-of-shift or end-of-day one-pager of open work, grouped by status, for the next shift or a single named receiving technician.
All categories
- Triage & Routing
- QA & Closure
- Scheduling & Dispatch
- Communication
- Documentation
- Escalation
- Onboarding & Access
- Devices & Infrastructure
- Security
- Vendor Runbooks
- Liongard Inspectors
- Compliance & Audit
- Troubleshooting Playbooks
- Alert Runbooks
- End-User Guides
- Role Rituals
- Localized
- Microsoft 365 Administration
- PSA-Specific Workflows
- Change & Problem Management
- Voice & Messenger
- Industry Packs
- MSP Business Operations
- Reporting & Analytics
- Account Management
- Client Lifecycle
- Finance & Billing
- Sales & Quoting
- Automation & Flows
- Connectors
- Training & Enablement
- Personal Productivity