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

bug-reports

Skill0 starsChanged 21 days agoMITView on GitHub

Turn bug themes from feedback.tools into ready-to-paste bug report drafts. Use when the user asks to triage bugs from customer feedback, prepare issues or tickets from feedback, or find out which reported bugs to fix first.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. gabrielbauman/skills★ 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

5 rules. About 0 are common, 2 are distinctive, and 3 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.

  • 3

    Very specific

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

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

    Pick the period: Use the user's period, or the last 30 days by default, and say which one you used.

    line 13
  2. Very specific:

    read the weekly trend to see if it is new, growing or fading.

    line 16
  3. Very specific:

    read the responses behind it: their text, metadata.page_url (the page the response was left on) and the respondent's browser, os and …

    line 17
  4. Distinctive:

    Check for duplicates: If two themes describe the same problem, merge them into one report and say so.

    line 19
  5. Distinctive:

    After the blocks, add a short priority list: order the bugs by number of affected responses and by trend, and explain the order in one line …

    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

Bug reports from feedback

Turn the bug themes of a feedback.tools survey into bug report drafts the user can paste into their issue tracker. This skill only writes text; it does not create issues anywhere.

Steps

  1. Pick the survey with list_surveys. Ask if it is unclear which one.
  2. Pick the period. Use the user's period, or the last 30 days by default, and say which one you used. Pass it in filters as since / until.
  3. List bugs with list_bugs for the period. Rank by finding_count.
  4. For each bug the user wants (by default the top 5), call get_theme with its id, include_metadata: true and include_device: true:
    • read the weekly trend to see if it is new, growing or fading;
    • read the responses behind it: their text, metadata.page_url (the page the response was left on) and the respondent's browser, os and device_type;
    • open 1-2 of them with get_response only if you need their attachments.
  5. Check for duplicates. If two themes describe the same problem, merge them into one report and say so.

Report format

One block per bug, in the user's language unless they ask otherwise:

Title: <what goes wrong, from the user's side, one line>

Reported by: <N> responses in <period> (<trend>)
Where: <page, feature or flow, if the responses say it>
Environment: <browsers, OS and device types seen in the responses, e.g. "Safari on iOS (mobile) in 7 of 9 responses"; omit if no response has device data>
What users report:
- "<quote>"
- "<quote>"
Steps to reproduce: <only if responses describe them; otherwise "not described in feedback">
Expected: <what users expected, if stated>
Source: feedback.tools theme <id>

After the blocks, add a short priority list: order the bugs by number of affected responses and by trend, and explain the order in one line each.

Use only what the responses say. Do not invent steps, environments or causes: take the environment from the device fields and page_url only, never guess it from the comment text. If the feedback does not contain enough detail to reproduce a bug, say that and suggest asking affected users (responses that left contact details have user_email).

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