agentleFS
CharleneTStrainCharleneTStrain/product-ops-skills/skills/feedback-tagging/SKILL.md

feedback-tagging

Skill0 starsChanged 17 days agoMITView on GitHub

Classify raw customer feedback from calls, tickets, surveys, reviews, or interviews into a consistent set of tags (theme, sentiment, type, product area, customer segment) so it can be counted and compared. Use when someone pastes a pile of feedback, a survey export, call notes, or support tickets and wants it organized, coded, or turned into something countable.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the person has an existing tag list, use it exactly.

    line 18
  2. Distinctive:

    If there's no list, build one from a first read of the feedback, then confirm it before tagging everything.

    line 20
  3. Distinctive:

    Write a one-line definition for every theme so the boundaries are clear.

    line 28
  4. Distinctive:

    Keep the verbatim excerpt short and exact.

    line 38
  5. Distinctive:

    If a comment doesn't fit any theme, tag it "Other" and list it separately.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Feedback tagging

Tagging turns opinions into data. It only works if the tags are consistent: the same kind of comment gets the same tag every time, no matter who tags it or when.

Before you start

If .agents/product-ops-context.md exists (or .claude/product-ops-context.md), read it first. Use the team, owners, tools, meetings, and metric definitions it already has, and only ask for what's missing or specific to this task. If it doesn't exist, go ahead with what you're given, and suggest running product-ops-context once so the next skill doesn't have to ask.

Step 1: Set the tag list before tagging

If the person has an existing tag list, use it exactly. Don't invent new tags without flagging them.

If there's no list, build one from a first read of the feedback, then confirm it before tagging everything. Keep it small:

  • Type: problem, request, praise, question, churn signal
  • Product area: 5 to 10 areas, named the way the team names them
  • Theme: 8 to 15 themes, each a specific job or pain ("exporting reports," "permissions setup"), not a vague category ("usability")
  • Sentiment: positive, neutral, negative, mixed
  • Segment: whatever the source provides (plan, company size, role, industry)

Write a one-line definition for every theme so the boundaries are clear. Two themes that keep overlapping should be merged.

Step 2: Tag each piece of feedback

IDSourceCustomer / segmentVerbatim (short excerpt)TypeAreaTheme(s)Sentiment

Rules:

  • One comment can have more than one theme if it truly raises two separate issues. Most should have one.
  • Tag what the customer said, not what you think they meant. "It's slow" is a performance comment, not a request for caching.
  • Keep the verbatim excerpt short and exact. Never paraphrase inside the verbatim column.
  • If a comment doesn't fit any theme, tag it "Other" and list it separately. If several land in Other, that's a new theme.
  • Strip personal details (emails, phone numbers) from excerpts.

Step 3: Summarize the counts

# Feedback tagging — [Source] — [Date range] — [N] items

## Top themes
| Theme | Count | % | Sentiment mix | Segments most affected |

## New or emerging
- [Theme from "Other," with count]

## Tag definitions used
- **[Theme]:** [one-line definition]

Counts describe what was said in this batch, not the whole customer base. Say so if the sample is small or comes from one channel.

Related skills

  • voice-of-customer-digest — summarize the tagged feedback for leadership
  • support-escalation-patterns — go deeper on ticket themes
  • duplicate-request-merging — merge requests that show up in the feedback

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.