skills.rest
CarlosWilliamsR
CarlosWilliamsRCOMMUNITY
Explore all skills by this author →
GitHub

gentle-ai-bench

Authors and verifies gentle-ai bench journeys with driven harness execution.

Updated Aug 25, 2026
Search Tags:#go#test harness#ci verification#bench testing#journey corpus#driven execution
One-click install
npx skills add https://github.com/CarlosWilliamsR/SketchOS --skill gentle-ai-bench-carloswilliamsr
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gentle-ai-bench
Source: https://github.com/CarlosWilliamsR/SketchOS/tree/main/.config/opencode/skills/gentle-ai-bench
Command: npx skills add https://github.com/CarlosWilliamsR/SketchOS --skill gentle-ai-bench-carloswilliamsr

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It prevents false confidence in bench testing by enforcing that journey changes in the gentle-ai bench corpus are proven through driven harness execution, not just go test ./bench, which only validates corpus declarations. ## Core Features & Use Cases - Journey Authoring Rules: Enforces unique journey IDs across journeys_*.go files, mandatory Review: declarations, and runnable commands on every execute transition. - CI Reproduction Guidance: Directs you to copy the exact build and gentle-ai-bench run --binary ... commands from the Unit Tests step in .github/workflows/ci.yml, using --only <journey-id> for single journeys. - Semantic Change Auditing: Requires grepping the corpus for journeys pinning old behavior when a ratified product semantic changes, so stale assertions do not keep defects green. - Use Case: When adding a new journey or diagnosing a bench failure in CI, follow the contract to produce PR evidence containing the driven-mode summary line (completed / unsupported / failed counts) from a locally built binary. ## Quick Start Ask the assistant to add a new bench journey to the gentle-ai corpus and verify it with the driven harness using the exact CI invocation.

Frequently Asked Questions about gentle-ai-bench

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I verify a gentle-ai bench journey actually executes?▼

Build the harness and the product binary, then run the harness against it using the exact commands from the Unit Tests step in .github/workflows/ci.yml. A green go test ./bench only validates corpus declarations and proves nothing about driven execution.

How do I run a single bench journey instead of the whole corpus?▼

Pass --only <journey-id> to the gentle-ai-bench run command along with the --binary flag pointing at the locally built product binary. Copy the exact invocation from the CI workflow rather than guessing flags.

Why does my bench journey fail validation before running?▼

Common causes are a missing Review declaration, a duplicate journey ID across journeys_*.go files, or an execute transition without a runnable command. The validateCorpus, collision, and dead-execute guards each fail loudly naming the problem.

What is the difference between reviewOptedIn and reviewUntouched in a journey?▼

reviewOptedIn means the runner enables receipt-driven development globally before the first step and fails the journey if the switch does not come on. reviewUntouched is for journeys whose subject is the switch itself or that have nothing to do with reviews.

What should I check when a product semantic changes?▼

Grep the journey corpus for journeys pinning the old behavior before shipping, since the corpus is a second test surface beyond unit tests. A journey asserting the old defect keeps that defect green, so list the journeys you checked in the PR.

Related Skills

Explore More Software Engineering Skills→
Gentleman-ProgrammingGentleman-Programming
6.1k

gentle-ai-bench

Authors and verifies gentle-ai bench journeys with driven harness execution.

Official
Intermediate
DarkCodePEDarkCodePE

tdd-workflow

Automates RED-GREEN-REFACTOR cycles with checkpoint commits for unit, integration, and end-to-end tests.

Community
Advanced
The-Tech-IdeaThe-Tech-Idea
1

connectionproperties

Configure BeepDM datasource connections with a centralized typed model.

Official
Basic
Probably-GroupProbably-Group
3

windows-ui-automation

Automate Windows desktop UI testing via UIA and Win32 interactions.

Official
Advanced