Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+22 moreClaude CodeCursorCodex CLIMuseDots
OpenClaw
Manus
Grok
Grok Bot+18 agentsSpec Trace Gate: prove every requirement reaches a real test
Fails your build when a spec requirement has no task, a task cites a phantom requirement, or a task names a test that does not exist.
Free
About this skill
Spec-driven tools (Spec Kit, Kiro, BMAD) give you specs and task lists, but nothing proves the finished code covers every requirement. This skill does.
Tag acceptance criteria AC-N (EARS), map each task to criteria and to named tests, and a dependency-free Python gate fails on dropped requirements, phantom references, or tests that do not exist. Works with pytest, Jest/Vitest, Go, JUnit, RSpec and xUnit test layouts.
Includes an EARS cheat sheet, spec and task templates, and a GitHub Actions step. Runs in CI on the public agent-forge repo (github.com/Ces107/agent-forge).
How to use
Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scanned
Verified clean today
- Free to download with an account
Requires
Python