Index of every page on this site: llms.txt
All skills
deanpeters avatar

/launch-plan

@476ae12
Run it yourself

Build a launch plan sized by tier: owners, dates, go/no-go criteria, and a readiness scorecard. Use when a launch needs every function ready at once and nobody has defined 'ready'.

Use this Skill: https://skilld.dev/gh/deanpeters/product-manager-skills/launch-plan

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

template.md

≈904 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Launch Plan Template

Fill the tier first. It sizes everything below. Every unsupplied date, owner, quantity, or threshold stays [NEEDS SOURCE]. Quality checks at the bottom.


1. Tier assessment

Criterion Low / Med / High One-line reason
Revenue and margin at stake
Newness to the customer
Newness to the company
Regulatory and safety exposure
Installed-base impact
Channel impact

Proposed tier: [1 Full / 2 Standard / 3 Light] · Why: [one line] A lighter tier would leave uncovered: [name the rows] Confirmed by: [forum, date]

2. The four dates

Moment Date Gap to the next, and why it is acceptable
Announce
Order opens
First delivery
Full support

Fixed date driving the plan: [event, contract, season, budget year] Critical-path lead times: [certification, tooling, translation, partner price-list deadlines, security review]

3. Checklist by function

Function Deliverable ("done" in one line) Owner (named) Due Status Tag
Sales and channel
Support / Service / spare parts
Operations / production
Pricing and commercial
Legal / compliance
Documentation and training
Marketing
Internal enablement

Status: Not started · On track · At risk · Done · Not applicable (with a reason). Tag: [FROM YOU] · [RESEARCH] · [AI-SUGGESTED, VALIDATE THIS].

4. Go/no-go criteria (written before the gate)

# What is checked Threshold Evidence Owner Must-pass or Watch

Gates: [name, date, Approver] · [name, date, Approver] DACI per gate: Driver [ ] · Approver [one person] · Contributors [ ] · Informed [ ]

5. Launch Readiness Scorecard

Status definitions (written before the first review):

  • Ready: [what evidence exists]
  • At risk: [what is missing or unconfirmed]
  • Not ready: [what is missing and has no plan]
Function Readiness criteria Status Owner Evidence Must-pass? RACI

Scorecard verdict rule: any must-pass "Not ready" means no-go.

6. Risks and dependencies

Risk Cause / trigger Consequence Response Owner Exposure remaining

7. Premortem record

Scene: "It is [horizon] after launch and it failed."

Failure story (by function owner) Cause Likelihood / Impact Landed as (criterion # / risk)

8. Pre-approval check

Point Holds? Gap named (not filled)
Owners (delivery, adoption, operation, measurement)
Dependencies and critical path
Risks fully specified
Adoption owned
Evidence, not just dates
Rollback and pause conditions

9. Riskiest assumptions (committed copy)

  1. [the AI-suggested row or unagreed date that would most hurt if wrong]

Quality checks

  • Tier stated with scores, a lighter-tier trade-off named, and confirmed by the forum
  • All four dates present, and each gap is a decision
  • Every row has a named owner who agreed the date
  • Support (and spare parts, if hardware) has its own dated milestone
  • Go/no-go criteria are measurable, owned, and marked must-pass or watch, written before status
  • One approver per gate
  • Every "Ready" cites evidence
  • Every premortem driver landed in the plan
  • No invented dates, quantities, or owners

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning7d3 checks · Risk SAFE
  • Gen Agent Trust Hub7d

    The skill is a set of documentation and templates for creating product launch plans. It contains no executable code, network operations, or sensitive data access, and functions solely as a guided text-based workflow.

  • Socket7d

    No alerts

  • Snyk7d

    Risk: MEDIUM · 1 issue

Signed by skilld at 476ae12. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated last week
argument-hint
[what is launching, and the date that drives it]
type
workflow
theme
strategy-positioning
Other metadata
intent
Make a launch a coordinated business event instead of a ship date, so every function that touches the customer is ready, the effort fits the size of the launch, and the go/no-go call is made on criteria the team agreed before anyone saw the status. Right-sized so a minor variant gets a short punch list and a platform launch gets the full cross-functional plan.
best_for
[
  "Planning a launch across Sales, Support or Service, Marketing, Legal, and Operations",
  "Deciding how much launch effort an offering deserves before the work starts",
  "Writing go/no-go criteria before the gate, not after the status is known",
  "Reviewing a launch plan for the function everyone forgot"
]
scenarios
[
  "We launch the route optimizer in six weeks and Support has not seen it yet. Build the plan",
  "Is this a Tier 1 or Tier 2 launch, and what does each function owe us?",
  "Review our launch plan. I think we forgot the distributors and the spare parts",
  "Help me write go/no-go criteria for a hardware launch with a trade-fair date"
]
estimated_time
30-60 min to plan; weeks to execute

README badge

README badge for deanpeters/product-manager-skills/launch-plan