borghei/Claude-Skills / project-management/execution/customer-feedback-triage
customer-feedback-triage
VerifiedCluster, score and route inbound feature requests from support, sales, NPS and exec asks, and draft honest replies. Use when a feedback queue needs triaging or a customer needs a defensible yes, no or exploring answer.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 11.8 KB |
| assets/kano_quick_reference.md | markdown | 3.9 KB |
| assets/response_templates.md | markdown | 7.3 KB |
| assets/sample_feedback_queue.json | config | 3.7 KB |
| assets/triage_template.md | markdown | 3.9 KB |
| examples/triaging-30-requests.md | markdown | 10.5 KB |
| references/customer-feedback-triage-guide.md | markdown | 17.7 KB |
| references/kano-model-deep-dive.md | markdown | 9.5 KB |
| references/red-flags.md | markdown | 20.0 KB |
| references/tool-reference.md | markdown | 3.7 KB |
| scripts/feedback_triage.py | script | 26.2 KB |
references/tool-reference.md
View on GitHub# Feedback Triage Tool Reference
> Read this when you need the `feedback_triage.py` flags, the input JSON schema, or the output schemas (JSON / Markdown / Mermaid / Confluence / Notion / Linear).
## feedback_triage.py
Ingest a JSON queue of inbound feedback. Produce deduplicated clusters, Kano categorization, priority scores, and suggested response templates.
| Flag | Type | Default | Description |
|---|---|---|---|
| `--input` | string | (required unless `--demo`) | Path to JSON file with feedback items |
| `--demo` | flag | off | Run with built-in 12-item sample queue |
| `--format` | choice | `markdown` | One of `json`, `markdown`, `mermaid`, `confluence`, `notion`, `linear` |
| `--output` | string | stdout | File path to write output |
| `--segment-weights` | string | `enterprise=4,mid_market=2,smb=1,prosumer=1` | Override default segment weights |
| `--threshold` | float | `4.0` | Minimum priority score to route into prioritization-frameworks |
## Input schema
```json
{
"items": [
{
"id": "FB-2026-0001",
"channel": "support",
"customer_id": "cust-1234",
"segment": "enterprise",
"raw_text": "We really need a way to export results to PDF for our weekly board pack",
"received_at": "2026-05-12T14:23:00Z",
"submitter": "support-agent-jane",
"opportunity_area": "reporting",
"customer_name": "Priya",
"opportunity_label": "Share results with people who have no login",
"decision": "will-build"
}
]
}
```
Required: `id`, `channel`, `customer_id`, `raw_text`, `received_at`. Optional fields the tool honours:
- `opportunity_label` — the job this ask serves, written by a person. The first one in a cluster becomes the cluster label; without it the label is `[write the job] keywords: ...`, a placeholder to replace.
- `decision` — `will-build` or `won't-build`, recorded after the triage meeting. Without it every reply is drafted as `exploring`; the score only fills `suggested_tier`.
- `customer_name` — used in the greeting ("Hi there," otherwise).
Routing: bug-like clusters (including slowness and timeouts) go to the bug tracker and get a `bug-acknowledged` reply (logged as a defect, no roadmap promise); Basic and Performance clusters go to prioritization even below the threshold; only low-scoring Delight, Indifferent or Reverse asks are archived.
**Exit codes:** 0 report written; 2 missing file, invalid JSON, wrong shape, empty queue or missing required fields.
## Output schemas
**JSON** (`pm/customer-feedback-triage/v1`):
```json
{
"schema": "pm/customer-feedback-triage/v1",
"generated_at": "2026-05-22T00:00:00Z",
"data": {
"clusters": [
{
"cluster_id": "C-001",
"opportunity_label": "Share results with non-licensed stakeholders",
"kano_category": "performance",
"category": "feature_request",
"request_count": 5,
"distinct_customers": 4,
"segment_breakdown": {"enterprise": 2, "mid_market": 2},
"priority_score": 12.4,
"above_threshold": true,
"items": ["FB-2026-0001", "FB-2026-0007", "..."]
}
],
"routing": {
"to_prioritization": ["C-001"],
"to_bug_tracker": ["C-008"],
"to_strategy": ["C-012"],
"to_docs": ["C-005"]
},
"responses": [
{
"item_id": "FB-2026-0001",
"template": "exploring",
"suggested_tier": "will-build candidate",
"body_markdown": "..."
}
]
}
}
```
**Markdown** (default): a triage-board document with sections per cluster, routing summary, and response drafts.
**Mermaid**: a `flowchart TD` of clusters → routing destinations.
**Confluence / Notion / Linear**: storage-format-appropriate variants of the markdown output.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |