ソース情報
- リポジトリ
- hpsgd/turtlestack
- ソースの最終更新活動
- 2026年4月16日 07:12
- 検出された SKILL.md の言語
- 英語
- スター
- 0
- フォーク
- 0
インストール方法
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
ソースファイルを確認
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
メニュー
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
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。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/hpsgd/turtlestack --skill launch-planコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか?SkillsMP が現在取得できるファイルをダウンロードできます。
Review staged or recent changes — native Claude Code review for mechanics, layered with team conventions and the team verdict contract
Perform a security-focused audit of code changes or a specific area of the codebase.
Propose a change to a marketplace repo based on learned patterns — new rules, updated skills, evolved regex patterns. Infers which upstream marketplace the learning belongs to, confirms with the user, then creates a branch, applies changes, shows diff for review, and raises a PR on approval. Use when patterns have enough evidence to share upstream.
SOC 職業分類に基づく
SKILL.md を表示中
| name | launch-plan |
| description | Create a launch plan checklist for a product or feature release. |
| argument-hint | [product or feature being launched] |
| user-invocable | true |
| allowed-tools | Read, Write, Edit, Bash, Glob, Grep |
Create a launch plan for $ARGUMENTS using the mandatory process below.
Not every launch is the same. Classify first:
| Tier | Description | Examples | Typical timeline |
|---|---|---|---|
| Tier 1 — Major | New product, major feature, pricing change, rebrand | New product launch, v2.0, new pricing model | 4-8 weeks prep |
| Tier 2 — Standard | Significant feature, integration, meaningful improvement | New integration, workflow overhaul, new API | 2-4 weeks prep |
| Tier 3 — Minor | Small feature, improvement, quality of life | UI improvements, minor new feature, performance boost | 1-2 weeks prep |
The tier determines which checklist items are required vs. optional below.
Complete these items before announcing anything. Items marked with tier numbers are required for that tier and above.
positioning skill)write-api-docs skill)write-changelog skill)write-kb-article skill)Choose and document the rollout approach:
| Strategy | When to use | Risk level |
|---|---|---|
| Big bang | Low-risk features, marketing-driven launches needing a moment | Medium |
| Percentage rollout | Any feature where you want to validate before full release | Low |
| Cohort-based | When you want feedback from specific user types first | Low |
| Beta → GA | Complex features needing extended validation | Lowest |
| Dark launch | Backend changes — enable for monitoring, no user announcement | Lowest |
Document the specific plan:
Rollout plan for [feature]:
- Day 0: Enable for internal team (dogfood)
- Day 1-3: 5% of users (monitor error rates, support volume)
- Day 4-7: 25% of users (watch for performance impact)
- Day 8: 100% of users (public announcement)
Kill switch: [feature flag name]
Rollback trigger: [specific condition — e.g., "error rate exceeds 1%" or "support tickets exceed 20/day"]
A linear sequence — do these in order:
#### Morning (before announcement)
- [ ] Final deployment to production verified
- [ ] Smoke test core user flows: [list them]
- [ ] Monitoring dashboards open: [links]
- [ ] War room / communication channel open: [channel]
- [ ] Feature flag set to target rollout percentage
- [ ] All team members online and available: [list who]
#### Launch (go time)
- [ ] Publish announcement page / landing page
- [ ] Send announcement email
- [ ] Post on social channels
- [ ] Post changelog entry
- [ ] Update in-app messaging / banners if applicable
- [ ] Notify partners / integrators if applicable
#### Afternoon (first hours monitoring)
- [ ] Check error rates vs. baseline — are they within acceptable range?
- [ ] Check support ticket volume — any spike?
- [ ] Check core metrics — signups, activation, feature usage
- [ ] Read initial user feedback — social, support, community
- [ ] Address any critical bugs immediately
- [ ] Post first update to the team: "Launch status: [green/yellow/red]"
Prepare messages for different audiences:
| Audience | Channel | When | Message |
|---|---|---|---|
| Internal team | Slack / email | Pre-launch (morning) | "Launching [feature] today. War room: [channel]. Rollback plan: [link]." |
| Support team | Briefing + doc | Pre-launch (1 week) | FAQ, known issues, escalation paths |
| Existing users | Launch time | Announcement with clear CTA | |
| Social followers | Social media | Launch time | Platform-appropriate announcement |
| Partners / integrators | Pre-launch (if breaking changes) | Technical changes, migration guide, timeline | |
| Press / analysts | Pre-launch (if Tier 1) | Embargo briefing, press kit |
Schedule a review at day 7. Assess:
| Metric | Baseline | Day 1 | Day 3 | Day 7 | Target | Status |
|---|---|---|---|---|---|---|
| Feature adoption (% of active users) | 0% | | | | [target]% | |
| Error rate | [baseline]% | | | | < [target]% | |
| Support ticket volume (feature-related) | 0 | | | | < [target] | |
| Conversion impact | [baseline] | | | | [target] | |
| NPS / satisfaction | [baseline] | | | | [target] | |
feedback-synthesis skill)Based on the 7-day review:
Output the complete plan as a document with:
## Launch Plan: [feature name]
### Launch Tier: [1/2/3] — [rationale]
### Pre-Launch Checklist
| # | Item | Owner | Due | Status |
|---|---|---|---|---|
| 1 | [task] | [person] | [date] | Pending/Done |
### Rollout Strategy
- **Stage 1:** [% of users, date, criteria to advance]
- **Stage 2:** [% of users, date, criteria]
- **Full rollout:** [date, criteria]
### Launch Day Run-of-Show
| Time | Action | Owner | Notes |
|---|---|---|---|
| [HH:MM] | [action] | [person] | [detail] |
### Communication Plan
| Audience | Channel | Message | Owner | When |
|---|---|---|---|---|
| [audience] | [channel] | [key message] | [person] | [date] |
### Success Metrics
| Metric | Target | Measurement method | Review date |
|---|---|---|---|
| [metric] | [number] | [how measured] | [when] |
### Post-Launch Review
- **Scheduled:** [date, 1–2 weeks post-launch]
- **Attendees:** [who]
- **Review template:** metrics vs targets, user feedback, incidents, next steps