travisennis

12 mods across 1 repository, 5 stars between them.

add-opencode-model

01

travisennis/acai

Skill Claude CodeCodex

REQUIRED when adding OpenCode Zen models - provides a script that fetches accurate context, max tokens, pricing, and capabilities from the API. Use this skill whenever the user asks to add, register, or configure a new OpenCode Zen model. Do NOT guess model specifications—always fetch real data from the API.

5 1mo ago A 69 tokens original MIT

travisennis/acai

Skill Claude CodeCodex

REQUIRED when adding OpenRouter models - provides a script that fetches accurate context, max tokens, pricing, and capabilities from the API. Use this skill whenever the user asks to add, register, or configure a new OpenRouter model. Do NOT guess model specifications—always fetch real data from the API.

5 1mo ago A 67 tokens original MIT

compounding

03

travisennis/acai

Skill Claude CodeCodex

Analyzes the current session to identify self-improvement opportunities for acai.

5 1mo ago A 18 tokens original MIT

debugging-acai

04

travisennis/acai

Skill Claude CodeCodex

Debugging tools and techniques for acai. Use when investigating errors, analyzing session behavior, or troubleshooting issues in the acai CLI application. Includes guidance on reading logs, session files, and common error patterns.

5 1mo ago A 47 tokens original MIT

fallow

05

travisennis/acai

Skill Claude CodeCodex

Run fallow static analysis to find dead code, duplication, complexity issues, and architecture drift. Use before committing, after generating code, or when asked to clean up the codebase.

5 1mo ago A 40 tokens original MIT

travisennis/acai

Skill Claude CodeCodex

Survey a codebase as a senior advisor, find the highest-value improvement opportunities, present them for acceptance, and create ahm tasks for accepted findings. Strictly read-only on source code — never implements, fixes, or refactors anything itself.

5 1mo ago C 53 tokens original MIT

grooming-backlog

07

travisennis/acai

Skill Claude CodeCodex

Go through Open, Pending, and Blocked tasks in the backlog and make sure all decisions are made, dependencies are correct, and no open questions remain. The goal is to get tasks into a ready state for work.

5 1mo ago A 50 tokens original MIT

manual-testing

08

travisennis/acai

Skill Claude CodeCodex

Manually test acai features by running the app in tmux, interacting with the REPL, and inspecting logs and session files. Use after implementing a feature to verify it works end-to-end.

5 1mo ago A 43 tokens original MIT

travisennis/acai

Skill Claude CodeCodex

Migrate applications from AI SDK 6.x to AI SDK 7.0. Use when upgrading Vercel AI SDK packages, fixing v7 migration errors, or when the user mentions AI SDK v6, v7, upgrade, migration, breaking changes, system to instructions, fullStream, telemetry, tool context, or finalStep.

5 1mo ago A 79 tokens original MIT

preflight

10

travisennis/acai

Skill Claude CodeCodex

Run a focused review-readiness pass on a nearly finished change before commit. Scales the review to change size (XS/S = one pass, M = two passes, L/XL = three sequential passes covering rules conformance, correctness/source-of-truth, and overengineering). Then synthesize and apply the worthwhile fixes.

5 1mo ago A 68 tokens original MIT

verify

11

travisennis/acai

Skill Claude CodeCodex

How to build and drive acai end-to-end to verify changes at its real surface.

5 1mo ago A 20 tokens original MIT

acai AGENTS.md

12

travisennis/acai

Instructions file CodexOpenCode

Instructions for travisennis/acai, covering agent instructions, project, operating loop, workflow routing and cli, repl, tui, and user output.

5 1mo ago A 1,769 tokens original MIT