agentleFS
VektoAIVektoAI/pmstack/launch/SKILL.md

launch

Skill0 starsChanged 8 months agoMITView on GitHub

Launch Commander mode. End-to-end launch planning: GTM strategy, channel plan, enablement materials, rollback criteria, success metrics, week-by-week execution timeline, RACI, and launch day runbook. Three tiers: MAJOR (new product/market), STANDARD (significant feature), MINOR (incremental improvement).

66 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-policy, tool-rename-deprecation and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • OpenCortexIDESkill

    add-policy

    Use when adding, modifying, or reviewing VS Code configuration policies. Covers the full policy lifecycle from registration to export to platform-specific artifacts. Run on ANY change that adds a `policy:` field to a configuration property.

    Also in 4 projects that use this

  • gitpod-ioSkill

    tool-rename-deprecation

    Ensure renamed built-in tool references preserve backward compatibility. Use when renaming a toolReferenceName, tool set referenceName, or any tool identifier. Run on ANY change to tool registration code. Covers legacyToolReferenceFullNames for tools and legacyFullNames for tool sets.

    Also in 4 projects that use this

  • CesarjoquinSkill

    competitors

    When the user wants to create competitor comparison or alternative pages for SEO and sales enablement. Also use when the user mentions 'alternative page,' 'vs page,' 'competitor comparison,' 'comparison page,' '[Product] vs [Product],' '[Product] alternative,' 'competitive landing pages,' 'how do we compare to X,' 'battle card,' or 'competitor teardown.' Use this for any content that positions your product against competitors. Covers four formats: singular alternative, plural alternatives, you vs competitor, and competitor vs competitor. For sales-specific competitor docs, see sales-enablement.

    Also in 12 projects that use this

  • CesarjoquinSkill

    paywalls

    When the user wants to create or optimize in-app paywalls, upgrade screens, upsell modals, or feature gates. Also use when the user mentions "paywall," "upgrade screen," "upgrade modal," "upsell," "feature gate," "convert free to paid," "freemium conversion," "trial expiration screen," "limit reached screen," "plan upgrade prompt," "in-app pricing," "free users won't upgrade," "trial to paid conversion," or "how do I get users to pay." Use this for any in-product moment where you're asking users to upgrade. Distinct from public pricing pages (see cro) — this focuses on in-product upgrade moments where the user has already experienced value. For pricing decisions, see pricing.

    Also in 9 projects that use this

  • riggyzSkill

    attribution

    Attribution rules for issues, pull requests, work items, reviews, and comments created or edited by the agent in GitHub, Linear, Azure DevOps, or similar collaboration systems. Use when creating, commenting on, reviewing, or modifying external tracker content.

    Also in 6 projects that use this

  • coreyhaines31Skill

    conversion-tracking

    Set up, audit, verify, or fix website conversion tracking. Use when the conversion is a form submission, booked meeting, chat, phone call, signup, or purchase; when conversions must reach Google Ads, Meta, GA4, LinkedIn, TikTok, or Microsoft Ads; when the work involves GTM tags and dataLayer events, pixels, the Conversions API (CAPI), Enhanced Conversions, server-side tagging, or gclid and fbclid capture; or when the user reports conversion problems like "conversions stopped", "double counting", "spend but no conversions", "GA4 and Google Ads don't match", or an Unverified or Inactive status. Covers lead gen and ecommerce. Always fire on confirmed success, never the submit click; verify a test conversion arrives; diagnose before changing anything; offer free and native paths alongside paid ones and disclose partner tools. For tracking plans and UTMs, see analytics. For attribution models, see attribution. For campaigns and bidding, see ads. For CRM lead-stage design, see revops.

    Also in 3 projects that use this

  • +4 more from Cesarjoquin

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 60 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    The #1 launch failure: No rollback plan. If this launch goes badly, what happens?

    line 26
  2. Distinctive:

    Every deliverable has an owner and due date

    line 276
  3. Distinctive:

    After the launch brief, pause: "Launch brief look right?

    line 279

“Common” is measured: kept by at least 6 in 10 of the 60 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

{{PREAMBLE}}

Launch Planning Mode

Philosophy

A launch is not a date. It's a campaign with a beginning, a middle, and an ongoing measurement phase. The date is just the midpoint.

The #1 launch failure: No rollback plan. If this launch goes badly, what happens? Can you turn it off? How fast? Who decides? If you don't know, you're not ready to launch.

The #2 launch failure: Launching without knowing what success looks like. "We'll see how it goes" is not a launch strategy. Define success criteria BEFORE launch so you can evaluate honestly, not retroactively.

The #3 launch failure: Internal launch ≠ external launch. The product is "done" but sales doesn't know it exists, support doesn't know how to troubleshoot it, and marketing doesn't have assets. This is a launch failure, not a product success.

Launch Tier Selection

Ask the user (via AskUserQuestion):

What size launch is this?

RECOMMENDATION: Choose the tier that matches the GTM effort needed, not the engineering effort.

A) MAJOR — New product, new market, or flagship feature. Full GTM campaign. Press, blog, enablement, event. (4-8 weeks prep) B) STANDARD — Significant feature or improvement. Blog post, email, in-app announcement, sales enablement. (2-4 weeks prep) C) MINOR — Small improvement or bug fix. Changelog entry, maybe a tweet. (1 week prep) D) Help me decide — describe the feature and I'll recommend a tier


Step 1: Launch Brief

LAUNCH BRIEF
═════════════
Feature: [Name]
Tier: [Major / Standard / Minor]
Launch Date: [Target date]
Owner: [Name — single DRI for the launch]

ONE-LINE PITCH:
"[What this is and why it matters — the sentence that goes in the blog post headline]"

TARGET AUDIENCE:
- Primary: [Who benefits most — specific segment]
- Secondary: [Who else benefits]
- Internal: [Sales, support, CS teams who need to know]

VALUE PROPOSITION:
Before: [What the user's life looks like today]
After:  [What the user's life looks like with this feature]
Delta:  [The specific improvement — quantified if possible]

SUCCESS CRITERIA (measured at launch +30 days):
1. [Metric]: [Target] — Measured by: [How]
2. [Metric]: [Target] — Measured by: [How]
3. [Metric]: [Target] — Measured by: [How]

ROLLBACK CRITERIA (when to pull the feature):
- If [condition], then [rollback action] — Decision maker: [Who]
- If [condition], then [rollback action] — Decision maker: [Who]

ROLLBACK MECHANISM:
[How: Feature flag? Revert deploy? Config change? How long does rollback take?]

Step 2: Channel Plan (MAJOR and STANDARD)

CHANNEL PLAN
═════════════
| Channel | Content | Owner | Due Date | Status |
|---------|---------|-------|----------|--------|
| Blog post | [Title/topic] | [Who] | [Date] | ⬜ |
| Email (existing users) | [Subject line] | [Who] | [Date] | ⬜ |
| Email (prospects) | [Subject line] | [Who] | [Date] | ⬜ |
| In-app announcement | [Copy summary] | [Who] | [Date] | ⬜ |
| Social (Twitter/LinkedIn) | [Theme] | [Who] | [Date] | ⬜ |
| Documentation | [Pages to create/update] | [Who] | [Date] | ⬜ |
| Changelog | [Entry text] | [Who] | [Date] | ⬜ |

MAJOR only: | Press/AR | [Outlets/analysts to brief] | [Who] | [Date] | ⬜ | | Webinar/demo | [Topic + format] | [Who] | [Date] | ⬜ | | Partner notification | [Partners to notify] | [Who] | [Date] | ⬜ | | Landing page | [URL + key messaging] | [Who] | [Date] | ⬜ | | Video/demo | [Script outline] | [Who] | [Date] | ⬜ |


Step 3: Enablement Plan

INTERNAL ENABLEMENT
════════════════════
| Team | What they need | Format | Due Date | Owner |
|------|---------------|--------|----------|-------|
| Sales | Talking points + demo script | Doc + video | [Date] | [Who] |
| Support | Troubleshooting guide + FAQ | KB article | [Date] | [Who] |
| CS/AM | Customer communication template | Email draft | [Date] | [Who] |
| Marketing | Messaging framework + assets | Brief | [Date] | [Who] |

KEY MESSAGING:
- For sales: "[How to position this in deals]"
- For support: "[Common questions and answers]"
- For CS: "[How to communicate this to existing customers]"

TRAINING:
- [Session 1]: [Audience] — [Date] — [Format: live demo / async video / doc]
- [Session 2]: [Audience] — [Date] — [Format]

Step 4: Launch Timeline

LAUNCH TIMELINE: [Feature Name]
════════════════════════════════

T-[N] weeks: PREPARATION
├── [Date]: Content drafts due (blog, email, docs)
├── [Date]: Sales enablement materials ready
├── [Date]: Internal preview / dogfooding begins
├── [Date]: Support documentation published (internal)
└── [Date]: Go/no-go decision checkpoint

T-1 week: FINAL PREP
├── [Date]: All content reviewed and approved
├── [Date]: Feature flag enabled for beta users (if applicable)
├── [Date]: Launch day runbook reviewed by all owners
├── [Date]: Monitoring dashboards verified
└── [Date]: Rollback mechanism tested

T-0: LAUNCH DAY
├── [Time]: Feature enabled for all users
├── [Time]: Blog post published
├── [Time]: Email campaign sent
├── [Time]: Social media posts go live
├── [Time]: In-app announcement activated
├── [Time]: T+2 hours: First metrics check
└── [Time]: T+4 hours: End-of-day status to stakeholders

T+1 week: EARLY MONITORING
├── Daily metrics review (owner: [Who])
├── Support ticket monitoring (owner: [Who])
├── Bug triage and hotfix readiness
└── [Date]: Week 1 launch report

T+2-4 weeks: MEASUREMENT
├── [Date]: 30-day launch report vs success criteria
├── [Date]: Win/loss data collection (if B2B)
├── [Date]: User feedback synthesis
└── [Date]: Post-launch retro

Step 5: Launch Day Runbook

LAUNCH DAY RUNBOOK
═══════════════════
Date: [Launch date]
DRI: [Name] — Backup: [Name]
War room: [Slack channel / Zoom link / physical room]

PRE-LAUNCH CHECKLIST (morning of):
□ Feature flag ready to flip — confirmed by: [Who]
□ Monitoring dashboards open — link: [URL]
□ Rollback tested in staging — confirmed by: [Who]
□ Support team briefed and ready — confirmed by: [Who]
□ Content scheduled and verified — confirmed by: [Who]
□ Go/no-go call completed — decision: [GO / HOLD]

LAUNCH SEQUENCE:
[Time] — [Who]: [Action — e.g., "Enable feature flag for 10% of users"]
[Time] — [Who]: [Action — e.g., "Monitor error rates for 30 min"]
[Time] — [Who]: [Action — e.g., "Ramp to 50%"]
[Time] — [Who]: [Action — e.g., "Ramp to 100%"]
[Time] — [Who]: [Action — e.g., "Publish blog post"]
[Time] — [Who]: [Action — e.g., "Send email campaign"]
[Time] — [Who]: [Action — e.g., "Post on social media"]

MONITORING (first 4 hours):
| Signal | Normal range | Alert threshold | Action if breached |
|--------|-------------|----------------|-------------------|
| Error rate | <0.5% | >2% | Rollback to 50% |
| Latency p95 | <200ms | >500ms | Investigate |
| Support tickets | <5/hour | >15/hour | Pause rollout |

ESCALATION PATH:
- Level 1: [DRI] handles — minor issues, expected volume
- Level 2: [Eng lead] + [DRI] — unexpected errors, elevated volume
- Level 3: [VP Eng] + [VP Product] — rollback decision needed

END OF DAY:
- [Time]: Status update to stakeholders
- [Time]: Metrics snapshot saved
- [Time]: Any hotfixes needed? Y/N
- [Time]: Tomorrow's monitoring plan confirmed

Step 6: RACI Matrix (MAJOR launches)

RACI: [Feature Launch]
═════════════════════
| Activity | PM | Eng | Design | Marketing | Sales | Support |
|----------|-----|-----|--------|-----------|-------|---------|
| Feature development | C | R | C | I | I | I |
| Launch timing decision | R | C | I | C | C | I |
| Blog post | A | C | C | R | I | I |
| Sales enablement | R | C | I | C | A | I |
| Support documentation | A | C | I | I | I | R |
| Rollback decision | A | R | I | I | I | C |

R = Responsible, A = Accountable, C = Consulted, I = Informed

Completion Summary

LAUNCH PLAN SUMMARY
══════════════════════════════════════
Feature: [Name]
Tier: [Major/Standard/Minor]
Launch date: [Date]
DRI: [Name]

| Component | Status |
|──────────────────────|───────────────────|
| Launch brief | ✓ Written |
| Success criteria | ___ metrics defined |
| Rollback plan | ✓ Defined + tested |
| Channel plan | ___ channels, ___ assets |
| Enablement | ___ teams briefed |
| Timeline | T-[N] to T+30 mapped |
| Runbook | ✓ Launch day sequenced |
| RACI | ✓ Defined (MAJOR only) |
══════════════════════════════════════

Open items before launch:
1. [Item] — Owner: [Who] — Due: [Date]
2. [Item] — Owner: [Who] — Due: [Date]

Ready for: /metrics (to finalize measurement plan) or /brief --audience exec (to communicate launch plan)

Formatting Rules

  • Timelines use T-minus notation (T-2 weeks, T-0, T+1 week)
  • Every deliverable has an owner and due date
  • Rollback is not optional — every launch plan includes it
  • Launch day runbook is time-sequenced with specific people and actions
  • After the launch brief, pause: "Launch brief look right? Ready to build the channel plan?"

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.