mirror of
https://github.com/hanzoai/skills.git
synced 2026-11-19 00:47:36 +00:00
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]>
3.7 KiB
3.7 KiB
description, argument-hint, source
| description | argument-hint | source |
|---|---|---|
| Run a pre-mortem risk analysis on a PRD, launch plan, or feature — identify what could go wrong before it does | <PRD, plan, or feature description> | phuryn/pm-skills |
/pre-mortem -- Pre-Launch Risk Analysis
Imagine your launch has failed. Now work backward to figure out why. This command applies the Tigers/Paper Tigers/Elephants framework to surface real risks and create mitigation plans.
Invocation
/pre-mortem [paste or upload a PRD, launch plan, or feature spec]
/pre-mortem We're launching a self-serve billing portal next month
Workflow
Step 1: Accept the Plan
Accept in any format: PRD, feature spec, launch plan, project brief, or verbal description. The more detail provided, the sharper the risk analysis.
Step 2: Risk Identification
Apply the pre-mortem skill:
Imagine the product has launched and failed. Generate risks across categories:
- Technical: Performance, scalability, integration failures, data issues
- User: Adoption barriers, usability problems, unmet expectations
- Business: Revenue impact, competitive response, market timing
- Operational: Support load, documentation gaps, training needs
- Dependencies: Third-party services, cross-team handoffs, regulatory
Step 3: Classify Risks
Categorize each risk:
Tigers — Real, substantive risks that could cause failure
- Assess severity: Launch-blocking / Fast-follow / Track
- For launch-blocking Tigers: immediate mitigation required
- For fast-follow Tigers: plan to address within first sprint post-launch
- For track Tigers: monitor but don't delay launch
Paper Tigers — Risks that feel scary but are overblown
- Explain why the concern is manageable
- Note what would need to change for this to become a real Tiger
Elephants — Unspoken risks the team knows about but avoids discussing
- Surface political, organizational, or uncomfortable risks
- Frame constructively with suggested conversation starters
Step 4: Generate Pre-Mortem Report
## Pre-Mortem: [Feature/Launch]
**Date**: [today]
**Status**: [Draft / Reviewed]
### Risk Summary
- **Tigers**: [count] ([launch-blocking], [fast-follow], [track])
- **Paper Tigers**: [count]
- **Elephants**: [count]
### Launch-Blocking Tigers
| # | Risk | Likelihood | Impact | Mitigation | Owner | Deadline |
|---|------|-----------|--------|-----------|-------|----------|
### Fast-Follow Tigers
| # | Risk | Likelihood | Impact | Planned Response | Owner |
|---|------|-----------|--------|-----------------|-------|
### Track Tigers
[Risks to monitor post-launch with trigger conditions]
### Paper Tigers
[Concerns that seem big but are manageable — with reasoning]
### Elephants in the Room
[Uncomfortable truths the team should discuss]
### Go/No-Go Checklist
- [ ] All launch-blocking Tigers mitigated
- [ ] Fast-follow plan documented and assigned
- [ ] Monitoring in place for Track Tigers
- [ ] Rollback plan defined
- [ ] Support team briefed
Save as markdown.
Step 5: Offer Next Steps
- "Want me to update the PRD with risk mitigations?"
- "Should I create test scenarios for the riskiest areas?"
- "Want me to draft a launch checklist from these findings?"
Notes
- The best pre-mortems happen when the plan is 80% done — early enough to change course, late enough to have substance
- Push past the obvious risks — the most dangerous risks are the ones nobody mentions
- Elephants are the highest-value output — surfacing what the team avoids discussing
- For each Tiger, the mitigation should be specific and assignable, not "be careful"
- If the pre-mortem reveals too many launch-blocking Tigers, recommend delaying or phasing the launch