원클릭으로 Manus에서 모든 스킬 실행

시작하기

opencode-audit

스타9

포크1

업데이트2026년 2월 12일 11:59

Audit OpenCode configuration quality, safety, and operability with a 100-point rubric and concrete remediations.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

Awish021

Awish021/opencode

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

OpenCode Audit Skill

What this skill does

This skill runs a practical OpenCode audit and outputs:

a 100-point score with grade
category-by-category findings
concrete, ready-to-use commands and config snippets
a short remediation plan

When to use

Use this skill when the user asks to:

audit OpenCode setup quality
improve OpenCode safety and permissions
review agents, commands, skills, MCP, or plugins
prepare a hardening checklist before team rollout

Required inputs

Target repo or config path
Optional focus area (permissions, agents, skills, runtime checks)

Audit workflow

Load references/OPENCODE-AUDIT.md.
Discover project and global OpenCode files.
Score all 8 rubric categories.
Build prioritized findings with evidence paths.
Produce copy-paste remediation snippets.
Return total score, grade, and 7-day plan.

Discovery checklist

AGENTS.md, .opencode/AGENTS.md, ~/.config/opencode/AGENTS.md
.opencode/config.json, .opencode/opencode.json, .opencode/opencode.jsonc
~/.config/opencode/config.json, ~/.config/opencode/opencode.json, ~/.config/opencode/opencode.jsonc
.opencode/agents/*.md, ~/.config/opencode/agents/*.md
.opencode/commands/*.md, ~/.config/opencode/commands/*.md
.opencode/skills/*/SKILL.md, ~/.config/opencode/skills/*/SKILL.md
.claude/skills/*/SKILL.md, ~/.claude/skills/*/SKILL.md when present
MCP and plugin sections in config

Output contract

Return in this order:

Total score and grade.
Category scores.
Top findings with severity.
Ready-to-use fixes.
7-day action plan.

Guardrails

Stay OpenCode-specific; do not use non-OpenCode terminology unless compatibility paths are relevant.
Do not invent files; only cite discovered paths.
Keep fixes actionable and minimal.
Prefer least-privilege recommendations for permissions.

이 저장소의 다른 Skills

같은 저장소

atomic-code-changes

Awish021/opencode

Use when implementing code changes, bug fixes, refactors, or multi-step edits that may sprawl; keeps work split into atomic, independently verifiable changes.

2026-06-199

helm-chart-patterns

Awish021/opencode

Helm chart development patterns for packaging and deploying Kubernetes applications. Use when creating reusable Helm charts, managing multi-environment deployments, or building application catalogs for Kubernetes.

2026-02-129

conventional-commits

Awish021/opencode

Generate commit messages following conventional commit format.

2026-02-129

find-skills

Awish021/opencode

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

2026-02-129

gitlab-ci-patterns

Awish021/opencode

Build GitLab CI/CD pipelines with multi-stage workflows, caching, and distributed runners for scalable automation. Use when implementing GitLab CI/CD, optimizing pipeline performance, or setting up automated testing and deployment.

2026-02-129

golang-k8s-agent

Awish021/opencode

Use when building Go-based Kubernetes agents/controllers, reconcile loops, or cloud-native systems. Invoke for controller-runtime, CRDs, leader election, and Go concurrency.

2026-02-129

name	opencode-audit
description	Audit OpenCode configuration quality, safety, and operability with a 100-point rubric and concrete remediations.

OpenCode Audit Skill

What this skill does

This skill runs a practical OpenCode audit and outputs:

a 100-point score with grade
category-by-category findings
concrete, ready-to-use commands and config snippets
a short remediation plan

When to use

Use this skill when the user asks to:

audit OpenCode setup quality
improve OpenCode safety and permissions
review agents, commands, skills, MCP, or plugins
prepare a hardening checklist before team rollout

Required inputs

Target repo or config path
Optional focus area (permissions, agents, skills, runtime checks)

Audit workflow

Load references/OPENCODE-AUDIT.md.
Discover project and global OpenCode files.
Score all 8 rubric categories.
Build prioritized findings with evidence paths.
Produce copy-paste remediation snippets.
Return total score, grade, and 7-day plan.

Discovery checklist

AGENTS.md, .opencode/AGENTS.md, ~/.config/opencode/AGENTS.md
.opencode/config.json, .opencode/opencode.json, .opencode/opencode.jsonc
~/.config/opencode/config.json, ~/.config/opencode/opencode.json, ~/.config/opencode/opencode.jsonc
.opencode/agents/*.md, ~/.config/opencode/agents/*.md
.opencode/commands/*.md, ~/.config/opencode/commands/*.md
.opencode/skills/*/SKILL.md, ~/.config/opencode/skills/*/SKILL.md
.claude/skills/*/SKILL.md, ~/.claude/skills/*/SKILL.md when present
MCP and plugin sections in config

Output contract

Return in this order:

Total score and grade.
Category scores.
Top findings with severity.
Ready-to-use fixes.
7-day action plan.

Guardrails

Stay OpenCode-specific; do not use non-OpenCode terminology unless compatibility paths are relevant.
Do not invent files; only cite discovered paths.
Keep fixes actionable and minimal.
Prefer least-privilege recommendations for permissions.