Feature Flag Rollout Plan skill for Claude and Codex

Feature Flag Rollout Plan as an AI skill. It asks for Feature, Flag system, Risk if it goes wrong and 4 more, then does the rest. Free to install in Claude or…

Install it once and Claude or Codex runs it for you. When your request matches, your AI loads the skill, asks for anything it is missing, and works through the template itself. Prefer to fill it in by hand? See the full prompt template.

Download the skill (.zip) · View SKILL.md

When it is used

Use when a feature is about to ship behind a flag and the team needs staged audiences, go or stop thresholds and a tested kill switch. Do not use for choosing which feature to build or setting up the flag tooling. Related topics: product, devops.

What it will ask you for

• Feature (longer free text)
• Flag system (free text, e.g. "LaunchDarkly or Firebase Remote Config or homegrown")
• Risk if it goes wrong (choose one: Cosmetic, Lost conversions, Data corruption, Outage)
• User base size (free text, e.g. "About 20000 weekly users")
• Success metric (free text, e.g. "The number that proves the feature works")
• Guardrail metrics (longer free text)
• Who can roll back (free text, e.g. "Role or team on call")

How it works

1. Pick stage sizes and audiences that match the risk and the user base so each stage yields readable data.
2. Set go, hold and stop thresholds for the success metric and every guardrail at each stage.
3. Define the kill switch: who flips it, how fast it takes effect and what happens to data already written.
4. Write the first-hour monitoring checklist for each stage with the exact dashboards or queries to open.
5. Set a flag removal date and the owner who deletes the dead code path.

What you get

A stage table with audience, size, soak time, metrics and exit rule, a kill switch section, a monitoring checklist per stage, and a flag cleanup date with an owner.

What it watches out for

• Advancing on elapsed time alone, when the stage has too few users to show a regression.
• Treating the kill switch as safe without checking data written under the flag, which may not roll back.
• Leaving the flag in place after full rollout, which doubles the code paths to test forever.

How to install

Claude.ai and the Claude desktop app

1. Download the skill .zip.
2. Open Settings, then Capabilities, and find Skills.
3. Choose Upload skill and select the .zip.
4. Ask Claude for help with the task. It loads the skill when your request matches.

Claude Code

1. Download the skill .zip.
2. Unzip it into ~/.claude/skills/ (or .claude/skills/ inside a project).
3. Start a new session. Claude Code loads the skill when your request matches.

Codex

1. Download the skill .zip.
2. Unzip it into ~/.agents/skills/ (or .agents/skills/ inside a project).
3. Codex picks it up on its own. Type $ and the skill name to use it, or just ask for the task.

Cursor

1. Download the Cursor rule (.mdc).
2. Save it in .cursor/rules/ inside your project.
3. Cursor's agent applies the rule when your request matches its description.

AGENTS.md (Codex, Cursor, and other coding agents)

1. Copy the AGENTS.md section.
2. Paste it into AGENTS.md at the root of your repository, creating the file if needed.
3. Coding agents that read AGENTS.md follow it when your request fits.