MiguelAPerez/agent-skills.md

MiguelAPerez/agent-skills.md

Skill Claude CodeCodex

Instructions for creating new agent skills. Use this skill whenever you are asked to create, generate, or set up a new skill.

MiguelAPerez/agent-skills.md

Skill Claude CodeCodex

Use this skill to bootstrap a new Next.js application with TypeScript, Tailwind CSS, React, and an API backend.

MiguelAPerez/agent-skills.md

Skill Claude CodeCodex

Use this skill when first entering a new project or when asked to "get a basic understanding" of the codebase. It helps to map out the structure and locate documentation.

MiguelAPerez/agent-skills.md

Skill Claude CodeCodex

File-based persistent memory for sub-agents and skills — where to store it, memory types (user, feedback, project, reference), save/recall rules, and MEMORY.md indexing. Read this skill when an agent definition says it uses persistent memory, or when saving or recalling learnings across sessions.

MiguelAPerez/agent-skills.md

Skill Claude CodeCodex

Triage the review feedback on a pull request — fetch every review comment, judge which points are valid vs. not (against the repo's own conventions and platform/scope constraints), pause for the user to confirm, then implement the agreed fixes and post a summary comment back to the PR. Use this whenever the user wants…

MiguelAPerez/agent-skills.md

Skill Claude CodeCodex

Use this skill to set up a basic PHP project. It initializes Composer, installs testing and static analysis tools (PHPUnit, PHPStan, PHPCodeSniffer), and provisions basic configuration files (phpstan.neon.dist and phpcs.xml).

MiguelAPerez/agent-skills.md

Skill Claude CodeCodex

Ship a change as a pull request the safe way — branch off main, stage only the relevant files, sanity-check the diff, run the repo's build/tests, and open the PR via the project's remote platform. Use this whenever the user wants to "ship it", "open a PR", "make a PR", "push this up for review", or otherwise turn…

MiguelAPerez/agent-skills.md

Skill Claude CodeCodex

Manually verify UI features on an iOS or macOS simulator after unit tests pass — when to delegate, how to brief a subagent, screenshot tap coordinates, and safety rules. Use when finishing a UI feature, before shipping, or when tests are green but "nothing happens" bugs are suspected. Delegate the actual driving to a…

MiguelAPerez/agent-skills.md

Skill Claude CodeCodex

Reference for interacting with a self-hosted Gitea remote — how to derive owner/repo, which MCP tools to use for PR and review operations, and known API quirks. Consult this whenever a skill needs to talk to a Gitea remote (creating PRs, fetching reviews, posting comments, resolving threads).