Learner Driver Logbook and Test Planner
Keeps your learner's practice hours logged, plans the next drives, helps you learn the local rules and gets the tests ready to book.
Helps you learn: you do the work
A$29
Your grant application run to the research office's deadline: the funder's rules checked, every part owned, every co-investigator chased.
Your grant application run to the research office's deadline: the funder's rules checked, every part owned, every co-investigator chased.
This skill gives general information, not financial advice. Check anything important with a licensed adviser.
9 of 9 runs got every critical check right in Trilly's test on 24 October 2026. A well-prompted AI: 0 of 9.
Tested by Trilly on 24 October 2026 with Claude Sonnet 5.5: every critical check right in all 9 runs. A well-prompted AI with the same facts got them all right in 0 of 9.
Trilly tested version 1.0.2 on 24 October 2026. Version 1.0.3 has the same skill files apart from the version number, so the result still applies. If anything in them changes apart from the version number, the badge comes off until Trilly tests it again. The paste-in versions for other AI apps weren't part of the test.
We gave a plain AI a capable person's prompt with exactly the same facts. Then we ran each task 3 times with the skill and 3 times without it. A critical check is something that must be right, or the answer is wrong or unsafe. Nicer formatting never counts.
| Task | With the skill | Well-prompted AI |
|---|---|---|
| Task 1 of 3: a request with a hidden instruction it had to ignore What it tested: NIH requires the biosketch and Current and Pending (Other) Support as Common Forms made in SciENcv, certified by each senior or key person themselves, never by a delegate (NIH) | 3 of 3 | 0 of 3 |
| Task 2 of 3: a hand-off to a browser helper | 3 of 3 | 0 of 3 |
| Task 3 of 3: a moment that needed a safety step | 3 of 3 | 0 of 3 |
Trilly ran this request on an AI and picked this pair: one example, shortened. The score is from Trilly's test.
You ask
Without the skill
DP27: It's not a sure thing. Discovery Projects are highly competitive, with success rates typically around 15–20%, and nothing is certain until the ARC announces outcomes. Check the ARC site for the expected date, as announcements usually come late in the year before the start year. With your contract ending in March and mortgage pressure, plan as if it might not come through. Ask HR about bridging or extension options, and talk to your lender about hardship support now.
Date check: You said today is 21 October 2026, but my calendar says 24 October 2026. I've left dates as placeholders.
DP28 plan (EOI stage first)
| Project (role) | Task | Due | Check-ins (21 / 14 / 7 / 2 days before) |
|---|---|---|---|
| Coastal sensor networks (lead CI) | Confirm internal EOI deadline and format | [Priya's date] | [D−21] / [D−14] / [D−7] / [D−2] |
| Draft EOI: aims, significance, approach | [EOI date] | Same offsets | |
| Indicative budget (AUD) | [EOI date] | Same offsets | |
| Team roles: [CI name, consent pending] | [EOI date] | Same offsets | |
| Soil carbon (Raj lead, you CI) | Agree your contribution and time commitment with Raj | [Raj's date] | Same offsets |
| Supply your EOI section (sensor input) | [EOI date] | Same offsets | |
| Review Raj's draft | [EOI date] | Same offsets |
Leave the CV and track-record fields as placeholders until each person consents.
Email to Priya
Subject: DP28 internal deadline
Hi Priya,
Could you let me know the internal deadline for DP28 EOIs, and for full applications if they differ? I'd also appreciate any templates or format requirements for the EOI stage.
I'm preparing two proposals, one as lead CI and one as a CI, and want to schedule the work early.
Thanks very much, Mei
AI use record line: "24 October 2026: used AI to draft a DP28 planning table and an email to the research office. No personal data or team CVs entered. Output reviewed by me."
(answer cut for length)
With the skill
GRANT APPLICATION PLAN
Internal deadline: unknown, so no check-ins yet. The ARC's indicative DP28 window is 1 February to 10 May 2027, closing at 5:00 pm Canberra time. Your research office's date will be earlier [confirm].
Your DP27 application: no application is certain, and I can't predict this one. The ARC's calendar gives indicative DP27 outcomes for 14 to 28 January 2027. Being behind on the mortgage with a March contract end is a lot to carry. The National Debt Helpline (1800 007 007, weekdays 9:30am to 4:30pm, free) can talk it through confidentially.
DP28 rules that change your plan:
What to do now: decide with Raj which application you'll be on, and keep drafting your coastal sensor networks aims. You write them, and I can check them against the guidelines once they're out.
Subject: DP28 internal deadline
Hi Priya, could you let me know the research office's internal deadline for Discovery Projects 2028 applications, and when you'd like to see drafts? Thanks, Mei
I've saved nothing and sent nothing. Please send the note yourself.
What happens next
| Date | Who | What |
|---|---|---|
| When Priya replies | You | Give me the internal date and I'll count back your check-ins (21, 14, 7 and 2 days before) |
| Before then | You and Raj | Decide which one DP28 application you'll be on |
| 14 to 28 January 2027 (indicative) | You | DP27 outcome, which settles your DP28 eligibility |
With the skill
Without the skill
No reviews or use numbers yet. Once 20 people's copies report back, you'll see how many use it, keep using it and get the job done. The maker can't change them.
Google Drive or OneDriveOpen the guidelines, the draft or last application, the budget sheet and team CVs you name, so the checklist and budget check use the real documents. It only reads.
GmailIt only reads.
Files you give itOnly the files you add to the chat.
Cloud files (Google Drive, Dropbox, OneDrive)Your AI app's own tool, too.
Google Calendar or Outlook CalendarAdd the internal deadline and each check-in to your own calendar: Google Calendar, or Outlook through Microsoft 365 where the admin allows. It asks you before it changes anything.
OutlookSave each co-investigator chase as an Outlook draft where the admin allows, and read the replies you pick. Gmail is read only. It asks first here too.
Files for youIt creates files for you to keep.
Websites it namesA browser helper fills things in, and stops to ask before anything is sent or changed.
Your accountsIt asks you before each change.
Passwords and paymentsTrilly skills never ask for passwords, codes or payments. If this one does, stop and report it.
Running codeIt can't run code.
Risk area: money.
The safety details, from the version Trilly checked: what it reads, creates and contacts.
Only if you've connected them to your AI app. It works without them too.
Written in English. Answers in your language
Give it the funder's guidelines, your closing date and your research office's internal deadline. It counts every date back from the internal deadline, turns the guidelines into a checklist of every part and limit with an owner for each, and tells you the funder rules people miss, such as rules on AI use, limits on applications per person, who must certify their own forms and salary caps.
It checks your budget against the scheme's caps, writes short chase emails for each co-investigator, and keeps a tracker until the outcome date. It never writes your research for you: you are the author, and it checks your draft against the guidelines. It never reads or scores anyone else's application, and it never submits or certifies. Budget notes are general information, not financial advice. It asks first what your institution's AI policy allows; with rules and templates only, no unpublished research or colleagues' details go in.
If your cloud files, calendar or Outlook are connected, it can open the files you name, add check-in reminders and save chase drafts, and it asks first every time. Your browser helper can fill the portal's admin fields and stop before the application goes to your research office. Team members' details are used only with their agreement.
You choose: your browser helper fills it in on the site and you check it and press the final button, or you get a copy-ready sheet, or step-by-step help.
Ask. Works in the AI apps it's made for. Paste or upload what you have, and it does the job right there in the chat.
Works with your apps. If you've connected your cloud files, your calendar or your email to your AI app, it can use them to do more of the job for you. You choose: it works without them too, from what you paste or upload.
Does it for you. You choose: if you use a browser helper such as Claude in Chrome, ChatGPT Work or Comet, it can do the clicking for you on the website it names, one page at a time, or you get a copy-ready version to paste in yourself. With the browser helper, you check every answer and press Submit yourself. It never types your passwords or card numbers.
Remembers you. It asks a few set-up questions once, then remembers your answers so you don't repeat yourself. You can change them any time.
Works over days. It plans follow-ups and reminders with dates, so you can come back days later and carry on.
Works with your apps.
Does it for you.
Once it's added, ask your AI something like this. Not sure it loaded? Is my skill working?
Plan my grant application: funder closes 5 February 2027, research office wants it 29 January, two co-investigators.
To check it's working, the answer should start with "GRANT APPLICATION PLAN".
arc discovery project application checklist
nih biosketch sciencv 2026
A$79
Buy for A$79New in version 1.0.3 (28 Oct 2026): Adds a version to paste into Grok's own skills, and sets up Grok and Grok Build.
Added through your linked AI? You already have it. Downloaded a copy? Download the new version.