メニュー
Enforces project safety constraints by blocking risky operations outside their approved scope during active development. Use when activating a safety guard or constraint for the current session.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Turns real agent failures, repeated prompts, team-specific workflows, and durable project lessons into better SDD skills or memory entries. Use when the user asks to create/update/refine skills, extract reusable lessons, improve skill routing, encode team process, or save patterns for future sessions.
Provides the vendored agent-style v0.3.5 prose rule pack as a portable Claude skill. Use when installing, syncing, applying, or auditing SDD Agent-Style support in another project, or when a style-review workflow needs the bundled rules.
Reviews Markdown prose against the pinned agent-style v0.3.5 rules and optionally writes a polished copy beside the source. Use for specs, ADRs, PR bodies, release notes, and technical docs when prose quality or evidence discipline matters.
Scans Markdown (.md) files for malicious code injection including XSS, prompt injection, script injection, obfuscated payloads, and supply chain attack vectors. Use when auditing .md files for security threats or when the user mentions scanning markdown for malicious content.
Provides .NET and ASP.NET Core patterns for REST APIs, Entity Framework, dependency injection, and middleware. Use when working with C# files (*.cs, *.csproj) or when the user mentions .NET, ASP.NET Core, C#, or Entity Framework.
Designs hybrid cloud architectures connecting on-premises infrastructure with public cloud services. Use when designing systems spanning on-prem and cloud, or when the user mentions hybrid cloud or multi-environment architecture.
| name | guard |
| description | Enforces project safety constraints by blocking risky operations outside their approved scope during active development. Use when activating a safety guard or constraint for the current session. |
| argument-hint | [no arguments] |
| user-invocable | true |
| allowed-tools | Read, Bash |
| effort | 1 |
| agent | release-manager |
| when_to_use | Before merging PR, deploying, or pushing to main/develop when unsure if a freeze is active |
Check the freeze status of the codebase. Use as a gate check before any operations on the main branch.
.freezeIf it does not exist:
✅ CLEAR — No active freeze.
Development and merging can proceed normally.
Stop here.
If it exists, proceed to step 2.
🔒 CODEBASE IS FROZEN
Reason : [REASON from .freeze]
Since : [FROZEN_AT]
Branch : [BRANCH]
Duration: [calculated from FROZEN_AT to current time]
⚠️ Non-critical merges are blocked during a freeze period.
Ask:
"What type of operation is this?"
A) Urgent Hotfix — production bug, security patch B) Release Artifact — changelog, version bump, release notes C) Non-critical — feature, refactor, chore, normal docs
If A or B: Allow to proceed with a note:
"⚠️ Permitted to proceed. Note that this is a freeze period — execute only necessary operations."
If C: Block and instruct:
"🚫 Non-critical changes must wait until after
/unfreeze. Save your work and continue after the release is complete."
/unfreeze — If the release is finished/release-checklist — If currently in the release process/hotfix — If an urgent fix deployment is needed/freeze — Lock codebase/unfreeze — Remove freeze/hotfix — Urgent deployment during freeze/release-checklist — Full release workflow