How to use the Post ForgeCode Feature agent skill

What is an agent skill, and what does this one do?

An agent skill is a folder of instructions and optional files that an AI agent loads when a task matches the skill's description. This skill, post-forge-feature, is triggered when you ask for a tweet, a Twitter post, or a promotion of a ForgeCode feature on social media.

When it runs, the agent first reads the relevant source code, docs, or changelog to work out what the feature does, when a developer would use it, and what problem it removes. It then drafts 2-3 sentences that follow the style guide and shows you the draft, asking whether you want changes before it is finalized.

• Reads the feature's code, docs, or changelog before writing anything
• Keeps the post to 2-3 sentences, which fits about 280 characters
• Uses the name "ForgeCode" and never "Forge" alone
• Avoids em dashes, filler phrases, and hype words
• Ends with an approved hashtag line
• Assumes a video is attached and does not describe it

Install the post-forge-feature skill

Download the skill as a ZIP from this page. Unzip it so the skill folder ends up in one of these locations:

For a personal install that works across your projects, unzip it into ~/.claude/skills/. To limit it to one project, unzip it into that project's .claude/skills/ folder.

If you use the Claude apps instead, open Settings, go to Capabilities, and upload the skill under Skills.

• Personal: ~/.claude/skills/
• Project only: .claude/skills/ inside your project
• Claude apps: Settings → Capabilities → Skills, then upload

Trigger the skill with a natural request

You do not need a special command. Ask for a tweet or social post about a specific ForgeCode feature in plain words, and mention the feature by name so the agent knows what to read. The skill's description lists the trigger phrases it responds to: write a tweet, create a Twitter post, or promote a ForgeCode feature on social media.

Because the skill assumes a video is attached, attach your demo video to the conversation when you make the request.

• "Write a tweet about the new task context feature in ForgeCode."
• "Create a Twitter post promoting the file watcher in ForgeCode. The demo video is attached."
• "Draft a social post for our ForgeCode changelog entry on workflows."

Review and approve the draft

The agent will show you a draft and ask if you want tweaks. Check three things before you publish: that the feature is described accurately against the code or changelog, that the post opens with the developer benefit rather than the feature name, and that the hashtags match the approved set in the style guide.

Ask for specific edits in plain terms, such as shortening the post or changing the tone. The agent will revise within the same constraints.

• Check the facts against the changelog or docs
• Confirm the post does not refer to the video's contents
• Confirm the hashtag line is present at the end

What the skill needs and its safety notes

The skill lists no required tools or packages. It does not run scripts, and it does not use the network. Its files are SKILL.md and references/style-guide.md, which you can open and read before installing.

Because the skill reads source code and docs through your agent's tools, it can only see what your agent has access to in the project you are working in. Review the draft yourself, since the agent may still describe a feature inaccurately.

• No required dependencies are listed
• Runs scripts: no
• Uses network: no
• Files: SKILL.md and references/style-guide.md