agentleFS
Sign inStart free
feedback-tools-platformfeedback-tools-platform/feedback-tools-mcp/skills/feedback-digest/SKILL.md

feedback-digest

Skill0 starsChanged 21 days agoMITView on GitHub

Summarize customer feedback from a feedback.tools survey for a period. Use when the user asks for a feedback digest, a weekly or monthly review, "what are customers saying", how the score changed, or the top bugs, feature requests and emotions.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. composio-community/support-skills★ 18same name
    2. AndyMelnykov/pm-loops★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Pick the survey: Call list_surveys. If the user named a survey, match it by title.

    line 12
  2. Very specific:

    Pick the period: Use the period the user gave.

    line 13
  3. Very specific:

    Themes: Call list_bugs, list_feature_requests and list_emotions for the current period.

    line 18
  4. Distinctive:

    Write the digest in the user's language, in this order:

    line 23
  5. Very specific:

    Keep it under one screen. Use only numbers returned by the tools.

    line 34
  6. Distinctive:

    If a call fails because the survey has no active subscription or trial, tell the user and give the survey link from the error.

    line 36

≈ “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 digest

Build a short digest of one feedback.tools survey for one period, using the feedback.tools MCP tools.

Steps

  1. Pick the survey. Call list_surveys. If the user named a survey, match it by title. If there is more than one candidate, ask which one. Note the survey type (csat_2, csat_5, ces_7, nps_10, general).
  2. Pick the period. Use the period the user gave. If none, use the last 7 days and say so. Also take the previous period of the same length for comparison. Pass dates in filters as since / until (ISO dates).
  3. Score and volume (skip the score for general surveys, they have no scale):
    • get_csat_score for the current and the previous period.
    • get_stats for response counts, responses with a comment and response ratio.
    • get_score_distribution only if the score moved noticeably.
  4. Themes. Call list_bugs, list_feature_requests and list_emotions for the current period. Take the top 3-5 of each by finding_count. For the 1-2 biggest bugs, call get_theme to see the weekly trend and a few responses behind it.
  5. Quotes. Take 2-4 short, representative comments from get_theme or get_responses (text_only: true). Quote them as written, do not edit them.

Output

Write the digest in the user's language, in this order:

  • Headline: one sentence with the main change of the period.
  • Score: current value, previous value, direction. For NPS give the number, for CSAT and CES the percentage.
  • Volume: responses and responses with a comment.
  • Top bugs: name, number of responses, trend (growing, stable, new).
  • Top feature requests: name and number of responses.
  • Mood: the leading emotions with counts.
  • Quotes: 2-4 comments.
  • Worth a look: 1-3 items that grew the most or appeared for the first time.

Keep it under one screen. Use only numbers returned by the tools; do not estimate or invent them. Responses marked is_ignored: true are already excluded from scores and themes; do not add them back.

If a call fails because the survey has no active subscription or trial, tell the user and give the survey link from the error.

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.

Check your setup, free