Files
skills/commands/analyze-feedback.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

3.6 KiB

description, argument-hint, source
description argument-hint source
Analyze user feedback at scale — sentiment analysis, theme extraction, and segment-level insights <feedback data as CSV, text, or file> phuryn/pm-skills

/analyze-feedback -- User Feedback Analysis

Process large volumes of user feedback (reviews, surveys, support tickets, NPS responses) into structured insights with sentiment analysis and segment-level patterns.

Invocation

/analyze-feedback [upload a CSV of NPS responses]
/analyze-feedback [paste app store reviews or survey responses]
/analyze-feedback [upload support ticket export]

Workflow

Step 1: Accept Feedback Data

Accept in any format:

  • CSV/Excel with feedback text (and optional metadata: date, segment, rating)
  • Pasted text (reviews, survey responses, Slack messages)
  • Uploaded documents or exports from feedback tools

Ask:

  • What kind of feedback is this? (NPS, reviews, support tickets, survey, etc.)
  • Any segments to analyze separately? (user tier, plan, geography)
  • What are you looking for? (general themes, specific issues, trends over time)

Step 2: Analyze

Apply the sentiment-analysis skill:

  • Sentiment scoring: Classify each piece of feedback (positive, neutral, negative)
  • Theme extraction: Identify recurring topics and cluster related feedback
  • Frequency analysis: Count how often each theme appears
  • Segment analysis: Break down sentiment and themes by user segment (if data available)
  • Trend detection: If dates are available, identify sentiment shifts over time

Step 3: Generate Analysis Report

## Feedback Analysis Report

**Date**: [today]
**Feedback analyzed**: [count] responses
**Source**: [NPS survey / app reviews / support tickets / etc.]
**Period**: [date range if available]

### Overall Sentiment
- Positive: [X%] | Neutral: [Y%] | Negative: [Z%]
- Average sentiment score: [X/10]
- Trend: [improving / stable / declining]

### Top Themes
| # | Theme | Mentions | Sentiment | Segments Most Affected |
|---|-------|----------|-----------|----------------------|

### Theme Deep-Dive

#### Theme 1: [Name] — [X] mentions, [sentiment]
- **What users are saying**: [summary with representative quotes]
- **Root cause**: [what's driving this feedback]
- **Impact**: [how this affects retention, satisfaction, or revenue]
- **Recommendation**: [what to do about it]

[Repeat for top 5-8 themes]

### Segment Analysis
| Segment | Volume | Avg Sentiment | Top Theme | Key Difference |
|---------|--------|-------------|-----------|---------------|

### Notable Quotes
> "[quote]" — [segment, sentiment]

### Trends Over Time
[If date data available: chart-ready data showing sentiment shifts]

### Actionable Insights
1. [Insight + recommended action]
2. ...

### Gaps
[What this feedback doesn't tell you — suggested follow-up research]

Save as markdown. If input was structured data (CSV), also save enriched data with sentiment scores as CSV.

Step 4: Offer Next Steps

  • "Want me to create user personas from these feedback patterns?"
  • "Should I triage the top themes as feature requests?"
  • "Want me to design an interview script to go deeper on a specific theme?"

Notes

  • Sentiment analysis is approximate — flag edge cases (sarcasm, mixed sentiment, non-English text)
  • Theme extraction should look for needs behind requests, not just surface-level topics
  • If sample sizes are small per segment, note limited confidence
  • For NPS data specifically, analyze Detractors (0-6), Passives (7-8), and Promoters (9-10) separately
  • Output enriched CSV when input is structured, so the user can use it in their own tools