
Feature Promotion Drafting
FreeEasily draft user-facing announcements for shipped features.
Free · Opens the source repo
What Feature Promotion Drafting does
ce-promote is a bash-based skill designed to streamline the process of creating promotional copy for features that have just been shipped. This tool integrates seamlessly into your engineering workflow, allowing developers and designers to generate copy that can be used for announcements, social media posts, and changelogs without waiting for a separate marketing effort. By leveraging context from your development environment, ce-promote can automatically derive what has shipped and draft relevant messaging accordingly.
The skill works by analyzing various sources of information, such as merged pull requests, changelogs, and recent commits, to summarize the user-facing value of the new feature. This means that instead of spending time crafting promotional messages manually, you can focus on other tasks while ce-promote handles the initial draft. The output is always a draft for your review, ensuring that you maintain control over the final messaging.
If you have the Spiral CLI installed and authenticated, ce-promote can tailor the drafted copy to match your brand's voice. However, even without Spiral, the skill provides a basic level of editorial and social media expertise to create effective announcements. This makes it a versatile tool for teams that want to enhance their communication without introducing additional complexity into their workflow.
Overall, ce-promote is ideal for engineering teams looking to improve their feature launch communication while minimizing the overhead typically associated with marketing tasks. It allows for quick, efficient drafting that can adapt to various channels, making it a valuable addition to any developer's toolkit.
When to use it
Use `ce-promote` after shipping a feature to quickly generate announcement drafts for various channels.
When not to use it
This skill is not suitable for posting or publishing directly; it only creates drafts for your review.
What you can build with it
Post-Launch Announcement
After shipping a new feature, use `ce-promote` to generate a draft announcement for your team to review.
Social Media Messaging
Request specific drafts for Twitter and LinkedIn to promote your latest feature across social media channels.
Changelog Updates
Quickly draft a one-line changelog entry for your project to inform users of the latest updates.
How to install Feature Promotion Drafting
View source1. Install with the skills CLI
npx skills add everyinc/compound-engineering-plugin/ce-promote --agent claude-code2. Or install it manually
Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.
Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs
Inside SKILL.md
Written by everyinc/ce-promote
Turn a feature that just shipped into copy-pasteable, user-facing announcement copy — right inside the engineering workflow.
Purpose
After you ship, the messaging shouldn't wait for a separate marketing pass. ce-promote figures out what shipped, picks the right channels, and drafts the copy. It is spiral-agnostic by default: with nothing installed it draws on a lite layer of editorial and social-media expertise to produce strong channel-specific copy. When the Spiral CLI (see references/spiral-cli.md) is present and authed, it uses Spiral so the drafts are voice-matched to your brand — a subtle enhancement, never a requirement.
This skill drafts only. It never posts, publishes, commits, or opens PRs. Posting is a human action. The output is always drafts for you to review, edit, and ship yourself.
Usage
/ce-promote # Derive what shipped from context, draft defaults
/ce-promote [free-form description] # You describe what shipped
/ce-promote a tweet thread and a LinkedIn post # Request specific channels
/ce-promote 3 tweet options for the new export feature
Phase 1 — Figure out what shipped
If the user gave a free-form description of the feature, use it as the source of truth.
Otherwise, derive it from context (use what's available; don't block on any one source):
- Merged/active PR —
gh pr view --json title,body,url 2>/dev/null(andgh pr viewfor the current branch). The title and body usually state the user-facing value. - The diff —
git diff main...HEAD --statand skim notable changes to ground the claim in what actually changed. - Changelog — the top/
[Unreleased]entry indocs/changelog.md,CHANGELOG.md, or similar. - Recent commits —
git log --oneline -15for the arc of the change.
Then write a 1–3 sentence summary of the user-facing value — what a user can now do that they couldn't before, and why they'd care. Describe the outcome, not the implementation. ("You can now export any report to CSV in one click" — not "Added a CsvSerializer and an export endpoint.")
If you can't confidently tell what shipped, ask the user one short question rather than guessing.
Phase 2 — Pick channels
Default to a small, sensible set:
- An X post or short thread (lead with the value; thread only if the change warrants it)
- A one-line changelog / release blurb
Scale to what the change warrants and to what the user asked for. If they named channels ("LinkedIn", "email", "a blog intro", "a short demo script"), draft those instead of or in addition to the defaults. A small fix needs one or two short drafts; a flagship feature can justify a cross-channel set. Don't force a fixed template.
Phase 3 — Draft the copy
First, detect Spiral's state with two quick, non-blocking commands:
which spiral
spiral auth status --json 2>/dev/null
Classify into one of three states:
- Absent (no binary,
which spiralfinds nothing) → Path 0 (install), then Path A if set up, else Path B. - Otherwise read
spiral auth status --json:- Ready — JSON with
"authenticated": true(equivalently"status": "authenticated") → Path A (voice-matched). - Unauthed — JSON with
"authenticated": false→ Path 0, then Path A if the user signs in, else Path B. - If the output isn't JSON (older CLI that ignores
--jsononauth status), fall back to the legacy signal in that same output: ready iff it containsspiral_sk_, else unauthed.
- Ready — JSON with
Never let a Spiral failure, timeout, or odd output block or slow the skill — when in doubt, treat it as not-ready and continue.
Path 0 — Offer Spiral setup (first run, declinable)
When Spiral isn't ready, offer to set it up once — unless the user previously opted out. The point is one proactive nudge, never a recurring one, and never a blocker: a decline always proceeds to Path B. Any dismissal records the opt-out, so a single first-run decline stops the offer for good in this repo — the user is never asked twice.
Read references/spiral-cli.md for the exact setup prompt (built with the platform's blocking-question tool), the connect/install steps, and how the opt-out is recorded so later runs skip this. In short:
- Unauthed → the agent runs
spiral login --json(CLI >= 1.8.0; non-blocking, the API key never passes through the agent). Onstatus: already_authenticated→ use Path A. Onstatus: pending→ surface theauth_url, the user approves in their browser, then pollspiral auth status --jsonuntilauthenticated: true→ Path A. Never have the user paste a key into chat. (Older CLI without agent login → suggestnpm i -g @every-env/spiral-cli@latest, or have the user runspiral loginthemselves.) Escape hatch: "or the agent can just draft directly, without Spiral's personalization and humanization." - Absent → guide the user to install + connect in one step via the pairing-code command from Settings → Connect an Agent.
- Decline → record the opt-out (best-effort) and go to Path B.
Skip Path 0 entirely — straight to Path B — when the opt-out is already recorded, or when running headless / non-interactive (no human to answer). If a human is present but no blocking-question tool is available, do not skip — fall back to a numbered list of the two options in chat and wait for a reply (per the Ask section of references/spiral-cli.md).
Path A — Spiral ready (voice-matched)
Use the Spiral CLI so drafts match the user's brand voice. Read references/spiral-cli.md before composing the prompt — multi-channel vs. single-channel-variations is phrasing-driven (channel keywords / cue words vs. --num-drafts) and getting it wrong silently returns the wrong number or shape of drafts. The exact phrasing rules live there; don't restate them from memory. Essentials:
- Always pass
--instantand--json. Parsedrafts[](each carries its ownchannel) plussession_id. - Present every returned draft, grouped by
channel. Spiral decides how many drafts per channel — multi-channel runs often return several per channel — so never assume one-per-channel or drop extras.
If the spiral write call errors or returns no usable drafts, silently fall back to Path B for the affected channels.
Path B — Direct drafting (lite editorial & social expertise)
No Spiral needed — draft strong copy directly using a compact layer of editorial and social-media fundamentals. (The Spiral path goes further: brand-voice matching, humanization, saved styles, and cross-channel campaign orchestration.)
Editorial fundamentals — every channel:
- Lead with the user-facing outcome: what someone can now do, not how it was built.
- One idea per piece. Cut windup, hedges, and throat-clearing.
- Be concrete and specific; show the value, don't assert it.
- Plain, active language. Strip AI tells — "thrilled/excited to announce," "game-changer," "in today's fast-paced world," "unlock/leverage/seamless," em-dash padding.
- Sanity check: read it as if saying it to one user. If a person wouldn't say it, rewrite it.
Social fundamentals — distributed channels:
- The first line is the hook and has to earn the next line (feeds truncate). No preamble.
- Match each channel's native shape and length; never reuse one draft verbatim across channels.
- One clear CTA where the channel supports it.
- Hashtags: 0–2, only where the channel expects them — never a wall of tags.
Per channel:
- X — value in the first line; ~1–3 tight lines. Thread only when there's more than one beat worth its own line.
- Changelog / release blurb — one declarative line naming the new capability. Plain, not promotional.
- LinkedIn — a short paragraph: human angle (why it matters), then the what. Warmer than X.
- Email — benefit-stating subject + 2–4 sentence body + one CTA.
- Blog intro — one strong opening paragraph framing the problem and the new capability; leave the deep-dive to the author.
- Demo script — 3–6 spoken beats: hook, problem, action, payoff.
Drafts per channel: one strong draft by default; produce more only when asked ("3 tweet options"), capped ~3.
Phase 4 — Present the drafts
Show every draft as a clean, copy-pasteable block, labeled by channel. For each:
### X post
<the copy>
- If Spiral produced them, also surface the
session_idand each draft'surlso the user can open and tweak them in the Spiral web app. - Offer to revise (tone, length, angle, more variations, another channel).
- Do not post, publish, schedule, commit, or open a PR. End by reminding the user the drafts are theirs to ship.
Examples
Single-channel variations — "3 tweet options":
User:
/ce-promote 3 tweet options for the new one-click CSV export→ Summarize the value. Spiral path:spiral write "3 tweet options for one-click CSV export" --instant --num-drafts 3 --json(no cue words). No-Spiral path: write 3 distinct tweets directly. Present all three.
Multi-channel set — "a campaign across X, LinkedIn, and email":
User:
/ce-promote draft a launch across X, LinkedIn, and email→ Spiral path:spiral write "announcing one-click CSV export — a launch across X, LinkedIn, and email" --instant --jsonreturns a set of drafts per channel (Spiral decides the count — often several), each carrying itschannel. (--num-draftsignored here.) No-Spiral path: draft one X post, one LinkedIn post, one email directly. Present every returned draft, grouped by channel.
Frequently asked questions about Feature Promotion Drafting
Similar skills
Agent-Browser Core
Efficient browser automation for AI agents.
Setup My IQ
Effortlessly create and update your personal context portfolio.
CRM Maintenance
Automate HubSpot updates from your calendar and emails.
Zoom MCP
Streamline access to Zoom meeting assets and recordings.
Slack Automation
Automate tasks and extract data from Slack easily.
SMB Onboard
Guides small business owners through initial tool setup.
