Development Craft Pack
Skills for people who ship with coding agents. Tests fail first. Find root cause before a patch. Review one diff with findings, not “looks good.” Time-box a throwaway spike. Delete until the tests still pass.
Works with any agent that signs in to Agensi, such as Claude, ChatGPT, Claude Code, Cursor and Codex CLI.
One payment, lifetime access. 3 skills unlock instantly in your library.
What's included
3 skillsEnforce strict RED-GREEN-REFACTOR cycles with mandatory failing tests and verifiable run records.
A disciplined debugging methodology that enforces root cause isolation and regression testing before applying fixes.
A strict security and quality gate that scans diffs for secrets, injections, and regressions with zero "vibe" tolerance.
See it in action
Test Driven Development (TDD)
Example session with this skill installed
Run TDD for the 'exponential backoff' behavior in my 'payment-processor' project. Test path is tests/test_retry.py and source is lib/retry.py. Use 'pytest' as the command.
- Read your context and instructions
- Compiled the test driven development
I have completed the RED-GREEN-REFACTOR cycle for the exponential backoff behavior. Production code written before the test was cleared, a failing test was verified, and the implementation now passes.
TDD Run Record: payment-processor
Behavior: Exponential backoff doubling the delay on each retry.
Status: ready
Paths
tests/test_retry.py: Modified (1 test added)lib/retry.py: Modified (Implementation added)
RED
Command: pytest tests/test_retry.py::test_backoff_doubles_delay
Result: AssertionError: assert 1 == 2 (Proven: delay logic was missing)
GREEN
Command: pytest tests/test_retry.py::test_backoff_doubles_delay
Result: PASSED
Suite Command: pytest
Suite Result: 14 passed, 0 failed
Refactor
- Renamed internal variable
dtodelay_secondsfor clarity. - Removed redundant initialization in
RetryStrategy.
Diff Bounds
- All changes restricted to
tests/test_retry.pyandlib/retry.py.
Residual
- next_behavior: not started
- review: not this role
- code_first: no
Next steps
- Review the generated implementation in
lib/retry.py. - Define the next behavior (e.g., maximum retry limit) for a new cycle.
- Merge the
plans/tdd-run.mdlog into your documentation if required.
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.