Builder's Toolkit
Six tested skills for people who build and run their own apps and automations with AI agents. Each one ships with its own scripts, tests and README, not just instructions.
- Inbox Autopilot: an e-mail assistant that drafts but never sends, and trashes but never deletes.
- WebGL Mobile Crash Fix: drop-in TypeScript fixes for three.js and WebGL apps that crash or reload on phones.
- PocketBase Gotchas: a scanner for silent PocketBase mistakes, including guest-writable rules in your live database.
- Hermes Cron Automation: quiet watchdogs and scheduled jobs that only call the model when something changed.
- Shelly Home Automation: safe Shelly control with scenes, sunset schedules and energy cost reports.
- Finish the Job: for unattended coding, the agent says "done" only when the project's own checks are green.
Separately $58.
Works with any agent that signs in to Agensi, such as Claude, ChatGPT, Claude Code, Cursor and Codex CLI.
One payment, lifetime access. 6 skills unlock instantly in your library.
What's included
6 skillsFor unattended coding: the agent keeps going until the project's own checks are green and says "done" only with evidence.
Scheduled jobs for Hermes Agent that cost nothing when nothing happens and never fail silently — with tested watchdog scripts.
A safe, low-cost e-mail assistant: wakes the model only for new mail, drafts but never sends, trashes but never deletes.
A scanner for PocketBase mistakes that fail silently — lost writes, filter injection, removed APIs and guest-writable rules.
Safe, repeatable Shelly control through the open-source shelly-mcp server: rooms, scenes, sunset schedules, energy costs.
Fix three.js and WebGL apps that crash or reload on phones, with tested drop-in TypeScript modules.
See it in action
Finish the Job
Example session with this skill installed
Finish the CSV import with tests — I am going out and will check tonight. Do not stop at a draft.
- Read your context and instructions
- Compiled the finish the job
Evidence — scripts/done_check.py (real runs)
Python project (an MCP server):
PASS lint .venv/bin/python -m ruff check . (0.1s)
PASS typecheck .venv/bin/python -m mypy src (1.4s)
PASS test .venv/bin/python -m pytest -q (5.7s)
VERDICT: DONE
TypeScript / three.js project:
PASS typecheck npx --no-install tsc -b --noEmit (7.8s)
PASS lint npm run --silent lint (13.5s)
PASS test npm run --silent test (21.7s)
VERDICT: DONE
Note the tsc -b: that repo has a solution-style tsconfig, where plain tsc --noEmit checks nothing and "passes" in 0.4 s. The checker detects this.
If something is left behind
Leftovers in the uncommitted diff:
app.ts:2: console.log: console.log(a)
app.ts:3: focused test: it.only('x', () => {})
app.ts:4: new TODO: // TODO later
VERDICT: NOT DONE
Report to you
Branch auto/csv-import, 4 commits, all checks green, no leftovers. Decision taken: empty rows are skipped and counted in the summary — change it if you prefer. Not pushed; merge after your review.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads these skills and uses them on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every skill in this bundle goes through our trust checks.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.