一键导入
init-review-policy
Initialize repo-scoped code review policy files under .opencode/review. Use when setting up project-specific review rules for /code-review.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Initialize repo-scoped code review policy files under .opencode/review. Use when setting up project-specific review rules for /code-review.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Build a fast, actionable branch/PR/commit context pack with scope, intent, changed files, hotspots, risks, and next actions. Use before handing work to another agent, reviewing a branch, resuming unfamiliar work, or preparing a PR/code-review prompt.
Create reviewed Codex goal setup packages for long-running /goal work. Use when the user wants to turn an idea, backlog, project mission, or vague objective into durable goal files under a project goals slug folder, with Plannotator review gates for brief, narrative plan with acceptance criteria, verification, blockers, and the final /goal prompt.
User guide for the local squash-safe `stack` CLI for stacked PR repair. Use when someone asks how to inspect, track, sync, merge, repair, document, or undo stacked pull requests in squash-merge repositories. Prefer this tool over GitHub's `gh stack` command for this workflow.
Manage long-running terminal jobs in a dedicated tmux-opencode session using wrapper scripts for run/wait, health checks, and crash-recovery cleanup.
Video understanding and transcription with intelligent multi-provider fallback. Use when: (1) Transcribing video or audio content, (2) Understanding video content including visual elements and scenes, (3) Analyzing YouTube videos by URL, (4) Extracting information from local video files, (5) Getting timestamps, summaries, or answering questions about video content. Automatically selects the best available provider based on configured API keys - prefers full video understanding (Gemini/OpenRouter) over ASR-only providers. Supports model selection per provider.
Designs and refactors React component APIs toward compound composition: fewer boolean mode props, clearer seams, context-backed internals, and JSX-first variant assembly. Use when building or reviewing React components with many props, conditional render branches, render props/slots, shared form/composer/card/table internals, or when the user mentions composition, compound components, Radix-style APIs, prop drilling, boolean props, or "composition is all you need".
| name | init-review-policy |
| description | Initialize repo-scoped code review policy files under .opencode/review. Use when setting up project-specific review rules for /code-review. |
Create a repo-local review policy package for use by /code-review and /review.
Initialize these files:
.opencode/review/policy.md (required).opencode/review/checklist.md (optional but recommended).opencode/review/severity.yml (optional but recommended)vcs-detect if available)..opencode/review/ if missing.# Review Policy
## Scope
- Applies to all code reviews in this repository.
- Overrides generic review defaults where explicitly stated.
## Critical Domains
- Authentication and authorization
- Data integrity and migrations
- Secrets, credentials, and PII handling
- Billing, quota, and financial calculations
## Must-Flag Findings
- Security vulnerabilities with practical exploit paths
- Silent data loss or corruption risks
- Backward-incompatible API or schema changes without migration plan
- Missing rollback/guardrails for risky deploy paths
## Usually Ignore
- Pure style nits unless they hide correctness issues
- Hypothetical edge cases without realistic trigger paths
## Repo-Specific Rules
- Add project rules here (framework constraints, architecture boundaries, test expectations)
## Required Review Output
- Severity: critical | high | medium | low
- File and line reference for every issue
- Why this is a bug/risk in this repository
- Concrete fix suggestion
# Review Checklist
## Correctness
- Logic matches intended behavior and existing contracts
- Error handling is explicit and testable
## Security
- No new injection/authz/secrets/PII exposure paths
## Data and Migrations
- Schema changes include compatibility and rollback notes
## Performance
- No obvious unbounded hot-path regressions
## Operations
- Logging/metrics/alerts are sufficient for new risk areas
## Testing
- Critical paths have adequate coverage for changed behavior
severity:
critical:
- remote code execution
- auth bypass
- irreversible data loss
high:
- privilege escalation
- data corruption risk
- breaking migration without rollback
medium:
- reliability regression on common paths
- significant performance regression
low:
- minor maintainability risk
- non-blocking robustness gaps
rules:
require_file_line_reference: true
require_concrete_fix: true
deduplicate_findings: true