- Home
- Skills
- Workflow Automation
- Lazy Developer: Ship Features with Minimum Wasted Motion
More screenshots
Works with the AI Agents you already use
Lazy Developer: Ship Features with Minimum Wasted Motion
Build features with minimum wasted motion: research first, define the smallest repo-native change, act in verifiable slices, verify, ship.
$5
Lazy Developer: Ship Features with Minimum Wasted Motion
Example session with this skill installed
Add a password-reset flow to our app. Research first, then build it in slices and prove it works.
- Read your context and instructions
- Compiled the lazy developer
Research first: read the repo's auth module, configs, and dependency versions before writing anything. Found the existing session and email patterns — the reset flow reuses the app's own mailer and token helpers instead of importing a new style. External facts checked against current docs for the email provider's rate limits, not from memory. Plan: the smallest complete change — three files, one new endpoint, one email template, one token table migration. Negative scope written down: no password-strength overhaul, no social login, no admin reset UI. First verifiable slice: token generation and validation alone, before any UI. Act: slice one green and tested, then the endpoint, then the email, then the UI — each committed before the next began. No invented APIs or fixtures; every function called is one the repo already provides. Observe: after each slice, read the actual output — test results, rendered UI, logs — not what was expected. One surprise investigated, not explained away: the token expiry read from config in minutes, not seconds. Verify: the smallest real proof — endpoint exercised against the real handler including expired-token and reused-token error paths; UI rendered at narrow, medium, and wide widths with keyboard flow checked. Ship summary written as what changed, why, how verified, and what is deliberately out of scope. Then stopped.
Connects securely to your tools. The creator never sees your data.
About this skill
The pipeline is Research, Understand, Plan, Act, Observe, Verify, Ship — and each phase is a gate. Do not act on an unresearched stack, do not ship on an unverified change. The whole skill is about spending effort where it buys certainty and skipping it where it does not. Research means facts before code: the stack as it actually is, the repo's existing patterns, and current documentation for anything external. Planning means defining the smallest complete change — scope, negative scope, shape, and the first verifiable slice. Acting means thin slices, each green, tested, and committed before the next, matching repo idioms and never inventing APIs. Verification is the smallest real proof for the change type — tests for logic, rendered screenshots for UI, installed artifacts for releases — and the UI/UX reject list keeps AI-gradient washes, card soup, and fake controls out of the product.
It asks blocking questions only when research cannot answer them — ambiguous requirements, missing credentials, decisions only the user can make.
It never invents APIs, assets, or test fixtures: a made-up function name compiles into a lie.
Skipped checks are reported as blocked, never as passed — skipped ≠ passed.
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 this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
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.
Trust & safety
Security scan
Security scan passed 3 days ago
Permissions
No special permissions declared or detected