Files
skills/commands/triage-requests.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

4.4 KiB

description, argument-hint, source
description argument-hint source
Analyze, categorize, and prioritize a batch of feature requests from customers or stakeholders <feature requests as text, file, or paste> phuryn/pm-skills

/triage-requests -- Feature Request Triage

Take a pile of feature requests — from support tickets, sales calls, surveys, or Slack — and turn them into a prioritized, actionable backlog.

Invocation

/triage-requests                           # asks for input
/triage-requests [paste a list of requests]
/triage-requests [upload a CSV/spreadsheet]

Workflow

Step 1: Accept Feature Requests

Accept requests in any format:

  • Pasted text: List of requests, one per line or paragraph
  • Uploaded file: CSV, Excel, or text file with request data
  • Structured data: If the input has columns (requester, request, date, etc.), preserve them

If no input is provided, ask the user to paste or upload their feature requests.

Parse each request to extract:

  • The core ask (what the user wants)
  • Context (who asked, when, why — if available)
  • Frequency signals (how many people asked for similar things)

Step 2: Gather Prioritization Context

Ask the user (conversationally, not all at once):

  • What is the product? What stage is it in?
  • What are the current strategic goals or OKRs? (helps assess alignment)
  • Any constraints to consider? (team size, technical debt, upcoming deadlines)
  • Are there segments whose requests should carry more weight? (enterprise, churning users, power users)

Step 3: Categorize and Analyze

Apply the analyze-feature-requests skill:

  • Theme clustering: Group similar requests into themes (e.g., "reporting & analytics", "collaboration", "mobile experience")
  • Request count per theme: How many unique requests map to each theme
  • Strategic alignment: Rate each theme against stated goals (High/Medium/Low/None)
  • Segment analysis: Which user segments are driving which themes
  • Sentiment signals: Are requests accompanied by frustration, churn threats, or delight?

Step 4: Prioritize

Apply the prioritize-features skill:

For each theme (and the top individual requests within each theme):

Factor Assessment
Impact How many users affected? How severely?
Strategic alignment Does it serve current goals?
Effort estimate T-shirt size (S/M/L/XL)
Risk What happens if we don't do this?
Revenue signal Is this tied to deals, retention, or expansion?

Rank themes and produce a prioritized list.

Step 5: Generate Triage Report

## Feature Request Triage Report

**Date**: [today]
**Requests analyzed**: [count]
**Themes identified**: [count]

### Theme Summary
| # | Theme | Requests | Top Ask | Alignment | Impact | Effort | Priority |
|---|-------|----------|---------|-----------|--------|--------|----------|

### Priority 1: Act Now
[Themes/requests to include in near-term planning]
- **[Theme]**: [X] requests — [why it's urgent]
  - Top requests: [list]
  - Recommended action: [build / prototype / investigate]

### Priority 2: Plan Next
[Themes worth planning but not urgent]

### Priority 3: Collect More Signal
[Themes with potential but insufficient evidence]

### Priority 4: Decline or Defer
[Requests that don't align with strategy — with rationale]

### Notable Individual Requests
[High-value one-off requests that didn't cluster into themes]

### Patterns and Insights
- [Key insight about what users are telling you]
- [Segment-specific patterns]
- [Gaps between what users ask for and underlying needs]

Save the report as a markdown file to the user's workspace.

Step 6: Offer Next Steps

  • "Want me to create user stories for the top-priority items?"
  • "Should I brainstorm solutions for any of these themes?"
  • "Want me to design experiments to validate demand before building?"
  • "Should I draft a stakeholder update summarizing this analysis?"

Notes

  • If the user provides a CSV with columns, preserve the data structure and enrich it
  • Look for the need behind the request — "add dark mode" might really mean "reduce eye strain during long sessions"
  • Flag requests that conflict with each other (e.g., "simplify the UI" vs. "add more configuration options")
  • If request volume is large (50+), summarize themes first and offer to drill into specific themes on request
  • Output the enriched data as a downloadable CSV if the input was structured data