kenzo09/ai

Repositório de prompts e templates para AI

This repository also configures its own agents. See what ai tells them →

4Stars on the repository
11Mods indexed here, across every type
22d agoLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied

handoff

01

kenzo09/ai

Skill Claude Code

Compact the current conversation into a handoff document for another agent to pick up.

not rated 4 +1 changed 1mo ago A 19 tokens

kenzo09/ai

Skill Claude Code

Use when the user gives a public GitHub repo URL and wants its .claude/ config (skills, agents, hooks, rules, CLAUDE.md) installed or merged into the current project.

not rated 4 +1 changed 20d ago A 46 tokens

live-docs

03

kenzo09/ai

Skill Claude Code

Central documentation skill for the few docs that earn their maintenance cost; system architecture, external integrations, core business capabilities and non-obvious architectural decisions. Use when a core capability is added or changed, when an integration, entry point or datastore is added, when an architectural…

not rated 4 +1 changed 20d ago A 185 tokens

test-evidence

04

kenzo09/ai

Skill Claude Code

Use when about to claim a delivery is done, finished, working or ready (an endpoint, page, flow, fix or feature someone else will check), and visual proof of it running has not been captured yet. Also use when choosing how to capture (playwright-skill, Swagger, Postman, DevTools, curl in a terminal), when redacting…

not rated 4 +1 changed 20d ago A 148 tokens

split-merges

05

kenzo09/ai

Skill Claude Code

Use when a feature branch (or a set of sibling-repo branches sharing one ticket) grew too large to review as one merge request and must be split into smaller, independently mergeable MRs, or when a previous split is in progress and the next slice must be cut. Triggers on "quebrar em MRs menores", "separar esse WIP"…

not rated 4 +1 changed 20d ago A 131 tokens

parallel-batches

06

kenzo09/ai

Skill Claude CodeCodex

Use after an implementation plan is written and approved, to execute it with the maximum number of subagents working at the same time instead of one implementer at a time. Maps task dependencies, groups independent tasks into parallel batches and drives the dispatch as tech lead. Triggers on "roda o plano em…

not rated 4 +1 changed 29d ago A 128 tokens

playwright-skill

07

kenzo09/ai

Skill Claude CodeCodex

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions…

not rated 4 +1 changed 1mo ago A 95 tokens

visual-briefing

08

kenzo09/ai

Skill Claude Code

Use when someone asks to explain, present or brief a module, feature, branch, WIP, pull/merge request, service or whole system to others, in any language, framework or architecture, and the answer should be a visual page rather than chat text. Also use when asked for an explainer, overview, onboarding page…

not rated 4 +1 changed 20d ago A 141 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: