ai-config-builder

SetupSmith

A reusable catalog of skills, agents, rules, templates, and Project Instructions, with guided setup and deterministic project-local skill installation for AI coding assistants.

Available now: the configuration catalog, manual adoption workflows, read-only CLI catalog discovery, explicitly approved selective skill installation, adoption, updates, restoration, and removal, and read-only managed-skill checks/diffs. Automatic synchronization is not implemented. See the MVP specification and managed installation guide.

Browse this README to find configuration. Use WORKFLOWS.md to choose a process for a specific task.

Projects can adopt only what they need. Keep product behavior, architecture, and other project-specific decisions in the project repository.

Quick start

• Choose a workflow: start with the scenario router in WORKFLOWS.md, then load the relevant skills.
• Adopt configuration into a project today: inspect its AI instructions, architecture, stack, Git workflow, and conventions. Then follow the manual Project adoption route in WORKFLOWS.md and copy only the selected canonical files. For example, add skills/firebase/SKILL.md only to a project that uses Firebase, and keep product-specific instructions there.
• Set up a multi-chat workspace: choose a Project Instructions preset below and tailor it with skills/ai-config-builder/SKILL.md.
• Discover catalog artifacts: run python3 scripts/setupsmith.py discover --source https://github.com/ehuerta6/setupsmith.git. It defaults to the Git source's advertised default branch; use --ref <branch-or-tag-or-revision> to select another ref. This command is read-only with respect to the target project and reports its resolved commit.
• Analyze a project: install only skills/setup-ai/SKILL.md using your assistant's supported skill mechanism, then invoke it as $setup-ai or select it from /skills in Codex, or as /setup-ai in Claude Code. The skill inspects and recommends only; it does not install or edit project files. Codex native discovery and invocation were checked for this skill; Claude Code runtime discovery is unavailable in the current environment.

The catalog below lists each artifact's canonical path and purpose.

Choosing configuration

Use the smallest artifact that fits the job:

You do not need to adopt the whole catalog. In an existing repository, inspect its own instructions first, then copy only the relevant canonical files and keep product and architecture decisions in that repository. For example, a Firebase project might adopt skills/firebase/SKILL.md and rules/security.md, while leaving unrelated skills behind.

The catalog also supports nontechnical work. Use research-and-compare for a focused comparison, learning-coach for a multi-chat learning workspace, or general-workspace when a workspace needs continuity across chats. Skills guide tasks; Project Instructions hold durable context. Keep personal details and decisions in the project workspace.

Skills

Configuration

setup-ai

Path: skills/setup-ai/SKILL.md

Analyze project conventions and recommend catalog configuration without modifying project files.

ai-config-builder

Path: skills/ai-config-builder/SKILL.md

Design or evolve skills, agents, rules, templates, and Project Instructions without unnecessary duplication.

audit-ai-config

Path: skills/audit-ai-config/SKILL.md

Audit existing project AI configuration for drift, duplication, stale instructions, and missing reusable configuration.

research-and-compare

Path: skills/research-and-compare/SKILL.md

Research a question and compare options using current, traceable evidence and explicit tradeoffs.

Planning

grill-me

Path: skills/grill-me/SKILL.md

Use when a feature, product decision, or implementation plan still contains ambiguity.

Stress-tests decisions before implementation so agents do not have to guess. Sharpens domain terminology, surfaces behavior conflicts, and identifies useful edge cases.

prototype

Path: skills/prototype/SKILL.md

Optional disposable UI or logic experiments for answering concrete design questions before implementation. Use only when trying alternatives will resolve uncertainty better than discussion.

to-spec

Path: skills/to-spec/SKILL.md

Turn resolved product and technical decisions into an implementation-ready specification.

Does not restart discovery or invent missing decisions.

to-issues

Path: skills/to-issues/SKILL.md

Break an approved spec into focused GitHub Issues.

Prefers vertical slices, explicit dependencies, and issues that fit inside a fresh agent context.

Implementation and review

implement-issue

Path: skills/implement-issue/SKILL.md

Implement one approved GitHub Issue while respecting its acceptance criteria and project conventions.

verify-change

Path: skills/verify-change/SKILL.md

Discover and run the repository's actual validation workflow.

Reports real evidence instead of assuming checks passed.

review-pr

Path: skills/review-pr/SKILL.md

Review completed work independently against both requirements and engineering quality.

debug-with-evidence

Path: skills/debug-with-evidence/SKILL.md

Debug using reproduction, evidence, explicit hypotheses, and focused tests instead of random edits.

git-flow

Path: skills/git-flow/SKILL.md

Execute the repository's Git and GitHub workflow for branches, commits, issues, PRs, and merging.

Project-specific Git rules override its defaults.

plan-issue-batches

Path: skills/plan-issue-batches/SKILL.md

Plan existing GitHub Issues into dependency-aware batches, generate a prompt for a selected batch, and update the plan as repository state changes.

Unlike to-issues, it does not create issues. Unlike the issue-batch-orchestrator agent, it prepares the plan and prompt rather than executing the batch.

Stack-specific

firebase

Path: skills/firebase/SKILL.md

Use for Firebase Auth, Firestore, Security Rules, Emulator Suite, Functions, Storage, seeds, and trusted server boundaries.

Only use in projects that actually use Firebase.

Agent workflow

handoff

Path: skills/handoff/SKILL.md

Create compact context for transferring unfinished work to another agent or session.

retro

Path: skills/retro/SKILL.md

Evaluate completed AI-assisted work and identify improvements to skills, rules, tooling, or workflow.

write-agent-instructions

Path: skills/write-agent-instructions/SKILL.md

Write and maintain compact instructions intended for AI agents.

Use this when creating or cleaning AGENTS files, skills, prompts, or similar agent context.

Writing and design

humanizer

Path: skills/humanizer/SKILL.md

Rewrite prose to sound natural while preserving facts, intent, and the writer's real voice.

unslop

Path: skills/unslop/SKILL.md

Clean technical prose by removing vague, inflated, formulaic, or low-signal writing.

impeccable

Path: skills/impeccable/SKILL.md

Design, critique, audit, polish, or improve frontend UI and UX.

Career