Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Launch Plan

ASecurity

Plan a release or go-to-market — when asked how to launch a feature/product, announce a version, run a campaign, or "what should we do for the launch". Produces a dated plan with owners and channels.

2 stars
0 votes
0 copies
0 views
Added 10/3/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 10/3/2026

$npx -y skills add ivanvp91/TRCode --skill launch-plan --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Launch Plan?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Launch Plan
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ivanvp91-launch-plan/badge)](https://www.skillsdirectory.com/skills/ivanvp91-launch-plan)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: launch-plan
description: Plan a release or go-to-market — when asked how to launch a feature/product, announce a version, run a campaign, or "what should we do for the launch". Produces a dated plan with owners and channels.
description_ru: Спланировать релиз или выход на рынок — когда спрашивают, как запустить фичу или продукт, анонсировать версию, провести кампанию, «что делаем на запуск». Даёт план с датами, ответственными и каналами.
triggers: запуск продукта, запуск фичи, план запуска, лонч, launch, релиз, release, go to market, gtm, вывод на рынок, кампания, campaign, анонс, announcement
---

# Launch plan

## 1. Define the launch
- **What** ships, in one sentence a user understands.
- **Tier**: silent (changelog only) / standard (blog + email + social) / major (campaign, press, partners). Most releases are not major — matching the tier to reality saves the audience's attention for when it matters.
- **Goal**: one number this launch should move (signups, activations, upgrades), plus the current baseline. No baseline means no way to judge it.
- **Date**, and what must be true to hold it.

## 2. Check readiness before promotion
Nothing goes out until: the feature works for a new user with no hand-holding, docs exist, pricing/limits are decided, support knows what to answer, and there is a rollback. A launch that drives traffic to a broken first-run is worse than no launch.

## 3. Sequence the audience
Order by risk, narrowest first: internal → existing power users / beta → all customers → public. Each stage has a stop condition — what you would have to see to pause.

## 4. Assets per channel
For each channel you actually use, list the asset and its one job:
- Changelog / release notes — what changed, for existing users.
- Docs page — how to use it.
- Email — to the segment who asked for it; one CTA.
- Blog / announcement — the why and the outcome, with a screenshot or demo.
- Social — one hook per post, spread over days, not one blast.
- In-app — where a user meets the feature at the moment it is useful.
- Community / forums / partners — only where you already have standing.

Skip any channel you have no audience on. Three well-made assets beat nine placeholders.

## 5. Timeline
Work backwards from the date: T-7 assets drafted and reviewed, T-3 docs and support ready, T-1 staged and dry-run, T-0 ship then publish in a fixed order, T+1 monitor and answer, T+7 measure against the goal and write down what happened.

Assign a name to each item. An item without an owner does not happen.

## 6. Risks
List the three most likely failures (load, a broken flow, a pricing objection, silence) and the response to each.

## What not to do
- Do not launch on a Friday or into a holiday.
- Do not announce what is not fully rolled out.
- Do not measure "impressions" as success when the goal was activations.
- Do not skip the retro — the plan's value is mostly in the next one.

## Answer format
A table: date → item → channel → owner → status. Then goal + baseline, the readiness checklist, and the risks with responses. Keep it to one page.

Attribution

ivanvp91ivanvp91
View sourceSee grades on GitHubMore from ivanvp91 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →