Files
skills/commands/red-team-prd.md
zeekayandHanzo Dev 65c3b27843 160 marketing, growth and PM skills, on our own connectors
Four MIT collections ported — growthOS, openclaw-marketing-skills,
Marketing-Skills and pm-skills — as 160 skills, 12 agents and 45
commands, each naming its origin in its own frontmatter so the tree can
be checked against THIRD_PARTY_NOTICES rather than trusted. Sixteen names
appeared in more than one collection and none of the copies were
identical; the longest wins, which lands on the more developed text where
they genuinely diverge.

A fifth collection is deliberately absent. awesome-growth-hacking-skills
carries NO licence, which leaves its author every right by default — and
it is a list of links rather than a collection of skills, so there is
nothing in it to port and no permission to port it with. It is cited as a
directory to read.

THE CONNECTOR SKILLS ARE REWRITTEN, not ported. They arrived installing
vendor SDKs, running OAuth flows of their own, and ending with long-lived
credentials in JSON files under .agents/ and ~/.growthos/ at mode 600.
That is a secret on a disk with no rotation path, protected from other
users and not from the agent — and one auth implementation per skill.
Hanzo holds these connectors in Go, per user, sealed in KMS, so `connect`
is the one home for the flow and the platform skills defer to it by
provider id: google_ads, meta_ads, x. It is reachable as HTTP or as MCP
tools at api.hanzo.ai/v1/mcp — the same routes, typed once in Go, so a
tool and a curl cannot disagree.

Two had nothing real behind them and now say so. There is no
search_console provider, so that skill names what does answer the same
questions (google_analytics, google_bigquery) and states that the remedy
is a provider in hanzoai/cloud rather than a vendor SDK here. And
getxapi-connect was a wrapper around a paid reseller of X's public data
with the vendor's key in an env var; it is `listen` now, on our own x
connector — a skill named after a vendor makes the vendor the capability
and dies with it.

The skills referenced paths that only existed inside the source repo, so
the shared material they read is ported to reference/ and the paths
rewritten. Three skills need the growthOS APPLICATION rather than its
data; per the estate's own split an application belongs in hanzoai/ads,
social, email or sms as a cloud plugin, so those three say what they need
instead of carrying an import that resolves to nothing.

Third-party product names are out of our prose and kept in the notices,
which is where the licence requires them and the only place they belong.
A skill's persona names a role, not somebody else's product.


Co-authored-by: Hanzo Dev <[email protected]>
2026-09-15 01:27:26 -07:00

2.7 KiB
Raw Permalink Blame History

description, argument-hint, source
description argument-hint source
Red-team a PRD, roadmap, or strategy — attack its load-bearing assumptions and return the cheapest test for each before you commit <PRD, roadmap, strategy, or the current doc> phuryn/pm-skills

/red-team-prd -- Attack the Plan Before Reality Does

Most plans only survived polite feedback. This command finds the assumptions that would make yours fail, attacks them honestly, and hands you the cheapest test for each — so you can kill a bad bet this week instead of at launch.

Invocation

/red-team-prd [paste or upload a PRD, roadmap, or strategy]
/red-team-prd Prioritize AI onboarding — activation is our bottleneck
/red-team-prd the current doc

Workflow

Step 1: Accept the Plan

Take it in any form — PRD, roadmap, strategy memo, one-line bet, or an uploaded doc. If the user says "the current doc," use the document in context.

Step 2: Red-Team It

Apply the strategy-red-team skill:

  • Extract every claim; keep only the load-bearing ones (false → plan dies).
  • Steelman each, then attack the steelman — no strawmen.
  • Write each failure mode as "Fails if ___."
  • Rank by (impact if wrong) × (likelihood wrong) × (cheapness to test).
  • Default "the risk is real" unless the plan cites evidence against it — but say plainly what's well-reasoned, and never fabricate a weakness.

Step 3: Return the Output

## Red-Team: [plan in one line]

### Top Kill-Assumptions (ranked)
- **Claim:** [load-bearing assertion]
  - **Fails if:** [concrete, falsifiable]
  - **Evidence to get this week:** [specific]
  - **Kill criterion:** [threshold]
  - **Cheapest test:** [smallest experiment]
[3–5 max]

### What's Well-Reasoned
[State it explicitly — don't manufacture doubt.]

### What I Couldn't Assess
[Where the plan didn't give enough to judge.]

Step 4: Offer Next Steps

  • "Want me to turn the top kill-assumption into an experiment you can run this week?"
  • "Should I run a pre-mortem to complement this — imagine it already failed and trace the path?"
  • "Want me to rewrite the riskiest section of the plan to address what survived?"

Notes

  • Lead with the ranking — the cheapest high-impact test is the whole point.
  • Five real kill-assumptions with tests beat twenty generic risks. Cut ruthlessly.
  • Distinct from /pre-mortem: pre-mortem narrates failure after the fact; red-team attacks the live assumptions and hands you the test.
  • If the plan is genuinely strong, the most valuable output is saying so — and naming the one thing still worth checking.
  • For a second-opinion pass, ask the user before adding cross-model friction; different model families miss different things, but most plans don't need it.