一键导入
spec-sync
Review changes against SPEC.md and docs/decisions/. Capture architectural decisions as ADRs, update SPEC.md if invariants changed. Run before pushing.
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
Review changes against SPEC.md and docs/decisions/. Capture architectural decisions as ADRs, update SPEC.md if invariants changed. Run before pushing.
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
| name | spec-sync |
| description | Review changes against SPEC.md and docs/decisions/. Capture architectural decisions as ADRs, update SPEC.md if invariants changed. Run before pushing. |
| allowed-tools | Read, Edit, Write, Glob, Grep, Bash |
Review the current branch's changes against the project's correctness envelope and decision records. Propose updates if needed, skip if nothing changed.
Before pushing to a PR branch. Part of the pre-push workflow in AGENTS.md:
mise run check — must pass/spec-sync — this skill/context-engineering update — if AGENTS.md affected/docs-workflow update — if docs/ affectedgit diff origin/main...HEAD --name-only
git diff origin/main...HEAD --stat
If no changes, report "nothing to sync" and exit.
SPEC.md — current invariants, requirements, interfacesdocs/decisions/ — existing ADRs (if directory exists)For each significant change, ask:
Skip trivial changes: formatting, typo fixes, test-only changes, dependency bumps without behavioral impact.
ADRs: One ADR per branch summarizing key decisions. Follow the schema:
---
id: {project}-adr-{NNNN}
title: ADR {NNNN} — {Title}
description: >
{One-line summary}
index:
- id: decision
keywords: [{relevant, keywords}]
---
# ADR {NNNN}: {Title}
**Status**: Accepted
**Date**: {YYYY-MM-DD}
**Deciders**: {names}
**Generated from**: {diff | pr | agent-session | manual}
---
## Context
{Why this decision was needed}
## Decision
{What was chosen}
## Consequences
**Positive:**
- {benefits}
**Negative / Trade-offs:**
- {costs}
## Alternatives Considered
| Alternative | Reason not chosen |
|---|---|
| {option} | {reason} |
SPEC.md: Use targeted edits — update only the affected section. Don't rewrite the whole file.
Architecture.md decisions index: If a new ADR was created, add it to the
decisions index table in docs/architecture.md.
Print a summary:
mise run check will catch malformed ADRs or
missing SPEC sections. Run it after making changes.Run Foreman repo-local agent simulation validation scenarios for PR-sized behavior checks, especially synthetic tmux/native-signal/Pi-subagent rollouts that should exercise public Foreman CLI surfaces without requiring real long-running agents.
Use when designing, reviewing, or changing Foreman's native Swift macOS overlay UI. Applies macOS HIG guidance, Foreman-specific command-palette UX, screenshot review, accessibility, and visual iteration rules.
Use when adding tests, fixtures, screenshot capture, fake foreman harnesses, or validation tasks for Foreman's Swift macOS overlay.
Use when designing or building native macOS applications with SwiftUI or AppKit. Triggers on menu bar structure, keyboard shortcuts, multi-window behavior, Liquid Glass design system, macOS Tahoe/Sequoia, sidebar navigation, toolbar design, app icons, SF Symbols, or making an app feel like a "good Mac citizen."
Apple Human Interface Guidelines for Mac. Use when building macOS apps with SwiftUI or AppKit, implementing menu bars, toolbars, window management, or keyboard shortcuts. Triggers on tasks involving Mac UI, desktop apps, or Mac Catalyst.
Creates, updates, or evaluates AGENTS.md and CLAUDE.md files for a repository. This skill activates when users want to create onboarding docs, update agent context files, or evaluate documentation quality. Generates docs with YAML frontmatter indexes for machine-readable progressive disclosure, system invariants, redirect-pattern gotchas (DO/NOT/BECAUSE), and validated commands. Supports incremental updates via git-based staleness detection.