Config Tuning

config-tuning

Use when you notice a pattern that should be in the config. Analyzes current setup, researches best practices, and proposes specific config changes. Also use when asked to improve agent behavior or workflows.

majiayu000/claude-skill-registry·0installs663starsSecurity

SKILL.md

Full skill instructions

Config Tuning

Analyze and improve OpenCode configuration based on observed patterns.

Announce: "I'm using config-tuning to analyze this pattern and propose config improvements."

When to Use

User describes a pattern they noticed (good or bad)
User asks to improve agent behavior
User wants to add a new workflow or skill
After noticing repeated friction in workflows

Process

Phase 1: Understand the Pattern

Ask clarifying questions if needed:

What behavior did you observe?
When does this happen?
What would you prefer instead?

Phase 2: Analyze Current Config

Read relevant files:

opencode.jsonc           # Main config
AGENTS.md                # Root rules
.opencode/agent/*.md     # Agent definitions
.opencode/skills/*/      # Existing skills
.opencode/command/*.md   # Existing commands

Phase 3: Research

If the pattern relates to:

Agent behavior → Research OpenCode agent docs
Prompting patterns → Research Claude best practices
Tool usage → Research OpenCode tools docs
Workflows → Check existing skills for similar patterns

Use exa_web_search or webfetch for OpenCode docs if needed.

Phase 4: Propose Changes

Present a structured proposal:

## Observation

[What pattern was noticed]

## Analysis

[Why this happens with current config]

## Proposed Changes

### Option A: [Name]
- File: [path]
- Change: [specific edit]
- Tradeoff: [pros/cons]

### Option B: [Name] (if applicable)
- File: [path]
- Change: [specific edit]
- Tradeoff: [pros/cons]

## Recommendation

[Which option and why]

Phase 5: Apply (with approval)

ALWAYS ASK before modifying config files.

After approval:

Make the changes
Explain what was changed
Suggest how to test the improvement

Config Locations

Config Type	Location	Purpose
Main	`opencode.jsonc`	Models, tools, permissions
Rules	`AGENTS.md`, `*/AGENTS.md`	Instructions for all agents
Agents	`.opencode/agent/*.md`	Specialized agent definitions
Skills	`.opencode/skills/*/SKILL.md`	Workflow guides
Commands	`.opencode/command/*.md`	Quick shortcuts

Common Patterns

Agent not using skills enough

→ Add <skill_awareness> block to AGENTS.md → Improve skill descriptions to be more triggering

Agent doing X when it should do Y

→ Add explicit rule to AGENTS.md or agent definition → Consider permission restrictions

Repeated workflow friction

→ Create a new skill to guide the workflow → Or create a command for quick access

Context getting too large

→ Use progressive disclosure (read docs on-demand) → Consider DCP plugin for context pruning

Red Flags - STOP

If you catch yourself:

Modifying config without user approval
Making changes that affect security (permissions)
Removing existing functionality

STOP. Always get explicit approval for config changes.

Install skill

Copy and run in your terminal

npx -y skills add https://github.com/majiayu000/claude-skill-registry --skill config-tuning

View on GitHub

skills/data/config-tuning/SKILL.md

More Security skills

View all

Security

supabase

Handles the full Supabase workflow from schema changes to deployment, with built-in security guardrails that catch common traps like RLS...

2.7K 308.9K

View

Security

neon-postgres

Comprehensive guides and best practices for Neon Serverless Postgres, covering setup, connection methods, authentication, and platform APIs.

98 216.2K

View

Security

firebase-auth-basics

Guide for setting up and using Firebase Authentication. Use this skill when the user's app requires user sign-in, user management, or secure data access using auth rules.

462 163.8K

View

Security

firebase-security-rules-auditor

A skill to evaluate how secure Firestore security rules are. Use this when Firestore security rules are updated to ensure that the generated rules are extremely secure and robust.

462 127.7K

View

Security

firebase-ai-logic-basics

Official skill for integrating Firebase AI Logic (Gemini API) into web applications. Covers setup, multimodal inference, structured output, and security.

462 125.1K

View

Security

better-auth-best-practices

Complete Better Auth server and client setup with database adapters, session management, plugins, and security configuration.

222 118.2K

View

Security

vercel-cli-with-tokens

Deploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens rather than interactive login — e.g. "deploy to vercel", "set up vercel", "add environment variables to vercel".

31.9K 116.1K

View

Security

cloudflare

Complete Cloudflare platform integration with decision trees for compute, storage, AI, networking, security, and infrastructure-as-code.

3K 110.7K

View

Security

azure-compliance

Run Azure compliance and security audits with azqr plus Key Vault expiration checks. Covers best-practice assessment, resource review, policy/compliance validation, and security posture checks. WHEN: compliance scan, security audit, BEFORE running azqr (compliance cli tool), Azure best practices, Key Vault expiration check, expired certificates, expiring secrets, orphaned resources, compliance assessment.

253 103K

View