scriptoriumadmin/claude-skills
1
0
Fork 0
mirror of https://github.com/alirezarezvani/claude-skills.git synced 2026-10-09 03:17:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
claude-skills/docs/commands/cs-pmf-check.md
Claude 2c09797115
docs(andreessen): run update-docs sync pipeline + mkdocs nav for v2.8.3 
- Bump headline counts: 329 -> 330 skills, ~448 -> ~451 tools, ~586 -> ~590
  references, 49+ -> 50+ agents, 79+ -> 81+ commands across CLAUDE.md, README,
  docs/index.md, docs/getting-started.md, mkdocs.yml.
- README productivity row 5 -> 6; add andreessen entry.
- CLAUDE.md: v2.8.3 highlights section + version/status/date footer.
- marketplace.json metadata + top-level description counts incremented.
- mkdocs.yml nav: add andreessen skill page, cs-andreessen agent,
  /cs:andreessen + /cs:pmf-check commands.
- Regenerate docs pages via generate-docs.py (andreessen skill/agent/commands;
  also reconciles claude-coach pages + dev-drift on code-reviewer/role-skill pages).
- mkdocs build verified clean (only pre-existing unrelated relative-link warnings).

https://claude.ai/code/session_01SF6MzfjHurZMt5JUFET9h3
2026-05-24 01:52:12 +00:00

2.6 KiB
Raw Permalink Blame History

title description
/cs-pmf-check — Slash Command for AI Coding Agents /cs:pmf-check — Are you before or after product/market fit? A focused Andreessen-mode interrogation that scores the felt signals + the Sean Ellis 40%. Slash command for Claude Code, Codex CLI, Gemini CLI.

/cs-pmf-check

:material-console: Slash Command :material-github: Source

Command: /cs:pmf-check

A focused slice of the cs-andreessen persona aimed at one question: are you before or after product/market fit? Per Andreessen, PMF is the only milestone that matters and it is not subtle — if you have to squint to see it, you don't have it.

When to Run

  • "Are we at product/market fit?"
  • You're deciding whether to scale (spend on growth/sales) or keep iterating on the product.
  • You're tempted to raise/hire/expand and want a hard read on whether the fit is real first.

What You Get

A focused interrogation, then a deterministic verdict:

  1. The felt-signal test (Andreessen): are customers buying as fast as you can make it? Is usage growing as fast as you can add servers? Is money piling up? Are you hiring support as fast as you can?
  2. The Sean Ellis 40% gate (Ellis, not Andreessen): do ≥40% of users say they'd be "very disappointed" without you?
  3. Verdict: BEFORE-PMF / APPROACHING-PMF / AFTER-PMF + explicit confidence.
  4. One next move: before PMF → what to change (product/segment/team). After PMF → pour fuel, stop deliberating, feed demand.

Discipline

  • PMF is not subtle. "Approaching" is the honest verdict for warm-but-ambiguous signals; don't inflate it to "after."
  • Retention is the strongest single signal. A leaky bucket means you are before PMF no matter how good acquisition looks.
  • Label the Ellis test as Ellis's, not Andreessen's. Confidence levels mandatory.
  • No capitulation to wishful reads without new evidence.

Workflow

python ../skills/andreessen/scripts/pmf_signal_scorer.py \
  --ellis-pct 45 --retention 8 --organic 7 --demand 8 --frequency 7

Related

Version: 1.0.0