Soft launch

Skill pagoda111king/claude-code-pack/template/.claude/skills/soft-launch

Pilot customer tracking · Solo Founder edition of canary-watch. Used to track feedback and make GO/NO-GO decisions after delivering the product to the first 1-3 pilot customers. Triggered when the founder says "product delivered / launched / given to a customer."From its SKILL.md

Install

npx -y skills add pagoda111king/claude-code-pack --skill soft-launch

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.9 KB, 740 tokens by cl100k_base, as published. Nobody here has run it

Soft-Launch Monitor · Pilot Customer Tracking

When to Trigger

Founder says:

"Product delivered to customer X"
"Y started using our tool"
"How's the first week of pilot going"

Or dashboard pipeline Stage 6 triggers.

Inputs

customers/<name>/ (customer folder)
docs/ideas/<slug>/ (product pipeline artifacts · for cross-referencing original assumptions)
Founder's verbal supplement: specific customer feedback (WeChat screenshots / emails / call transcripts)

Output

customers/<name>/pilot-tracking.md, structured as follows:

---
stage: pilot
customer: <name>
product: <slug>
startDate: 2026-04-25
deadline: 2026-05-09     # default 14-day pilot cycle
status: monitoring        # monitoring / GO / NO-GO / extended
goNoGoCheckpoints:
  - day7: pending
  - day14: pending
exitCriteria:
  GO:
    - "Customer uses product 5 consecutive workdays"
    - "At least 1 proactive positive feedback"
    - "Verbal renewal intent confirmed"
  NO_GO:
    - "Zero active logins in first week"
    - "Explicitly says 'not a fit' or 'too complex'"
    - "Data / privacy incident occurs"
---

# Pilot Tracking · <customer> · <product>

## Feedback Log

### Day 1-3
- 2026-04-25 · Customer first login + used feature X · Feedback: ...

### Day 4-7
- 2026-04-28 · ...

## Current GO/NO-GO Assessment

[Fill in at day 7 / day 14 checkpoint]

## Risks & Mitigations

- Risk 1: ...
- Mitigation: ...

Core Rules

Default pilot period is 14 days · exceeding without clear renewal = implicit NO-GO
GO/NO-GO criteria are locked in on day 0 · not adjusted mid-course
Every feedback entry includes date + source (WeChat / email / call) · no memory-based recall
Day 7 is a mandatory checkpoint · if criteria aren't met, proactively schedule a 1-on-1 with the customer
NO-GO still produces a case study (anonymized internal version) · honest failure builds trust

Collaboration with Other Skills

Before evaluation, use idea-eval existing 6-dimension scores · cross-reference with actual feedback ("assumed pain points vs real customer pain points")
After pilot ends, use case-study-gen to feed this back into 6-platform content (regardless of GO or NO-GO)
After multiple pilots complete, use eval-refine to adjust the idea-eval rubric

Solo Founder Specific Constraints

No more than 3 concurrent pilots · attention gets diluted · none succeed
Customer pays before pilot · free pilot customers don't actually use the product · feedback is invalid
Fixed 1-hour weekly proactive check-in · don't wait passively for feedback

Prohibited

❌ Adding new features mid-pilot (breaks the baseline)
❌ Automated DMs / automated follow-ups (violates TOS · destroys trust)
❌ Treating vague feedback as a GO signal ("it's okay" / "pretty good" = implicit NO-GO)

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most product growth skills give in 740 tokens

Counted across 728 of the 1,010 authors here whose files we hold, read 2026-08-07

Read product marketing context before asking questionsin 24 of 728, across 18 files
Define the ideal customer profilein 21 of 728, across 3 files
Document a rollback plan before deploymentin 21 of 728, across 12 files
Analyze the codebase to understand the productin 19 of 728, across 1 file
Ask clarifying questions about the value propositionin 19 of 728, across 1 file
Search for companies matching the criteriain 19 of 728, across 1 file
Look for signals of immediate needin 19 of 728, across 1 file
Assign a fit score from one to tenin 19 of 728, across 1 file
Identify the target decision-maker rolein 19 of 728, across 1 file
Suggest a personalized contact strategyin 19 of 728, across 1 file
Provide conversation starters for outreachin 19 of 728, across 1 file
Format results in a scannable markdown templatein 19 of 728, across 1 file

Said here and by no other author read

use a 14-day default pilot period
lock GO/NO-GO criteria on day 0
include date and source for every feedback entry
schedule a 1-on-1 for day 7 if criteria are unmet
produce a case study after a NO-GO
cross-reference idea-eval scores before evaluation

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.