agentleFS
Sign inStart free
brittbritt/agent-skills/skills/build-faq-from-issues/SKILL.md

build-faq-from-issues

Skill11 starsChanged 6 days agoMITView on GitHub

Use when building or updating an FAQ from closed GitHub issues, documenting recurring support questions, or reducing repeat questions - extracts common questions from resolved issues and generates a categorized FAQ document with synthesized answers and source links

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When NOT to use: not for open-issue triage, changelogs or release notes, or repos with too few closed issues to find recurring patterns.

    line 18
  2. Very specific:

    Read resolutions for candidate issues with gh issue view <n> --comments to find the accepted answer or fix.

    line 25
  3. Distinctive:

    Write standalone answers (don't require reading the issue)

    line 87
  4. Distinctive:

    Keep answers concise but complete

    line 89
  5. Distinctive:

    Put most common questions first within each category

    line 95
  6. Distinctive:

    Use consistent question phrasing ("How do I..." vs "Why does...")

    line 96
  7. Distinctive:

    When multiple issues ask the same thing:

    line 101
  8. Distinctive:

    Use the clearest answer from any of them

    line 104

≈ “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

Build FAQ from Issues Skill

Extract common questions from closed GitHub issues and generate a structured FAQ document with answers and source links.

When to Use

Activate when:

  • Creating or updating a project FAQ
  • Documenting common support questions
  • Reducing repeat questions in issues
  • Onboarding new users/contributors

When NOT to use: not for open-issue triage, changelogs or release notes, or repos with too few closed issues to find recurring patterns.

Workflow

Prerequisite: requires the gh CLI authenticated to the target repository.

  1. List closed issues: gh issue list --state closed --limit 200 --json number,title,labels,url. Optionally filter by question/support labels (e.g. --label question).
  2. Read resolutions for candidate issues with gh issue view <n> --comments to find the accepted answer or fix.
  3. Group recurring questions — cluster issues that ask the same thing into a single candidate FAQ entry.
  4. Synthesize a standalone answer for each entry from the clearest resolution.
  5. Emit the FAQ using the template below.

Output Structure

## FAQ: [Project/Topic]

**Generated from**: [X closed issues] | **Labels**: [question, help, support]

### General

#### Q: [Common question]

[Answer synthesized from issue resolution]

— See #123

#### Q: [Another question]

[Answer]

— See #456

### Setup & Installation

#### Q: [Setup question]

[Answer with steps if needed]

— See #789

### Troubleshooting

#### Q: [Error or problem question]

[Answer with solution]

— See #101

### Configuration

#### Q: [Config question]

[Answer]

— See #202

Guidelines

Question Selection

  • Focus on closed/resolved issues
  • Prioritize issues labeled: question, help, support, faq
  • Include frequently recurring questions
  • Skip one-off bugs or feature requests

Answer Quality

  • Write standalone answers (don't require reading the issue)
  • Include concrete steps when applicable
  • Keep answers concise but complete
  • Link to docs if more detail exists elsewhere

Organization

  • Group by logical categories
  • Put most common questions first within each category
  • Use consistent question phrasing ("How do I..." vs "Why does...")
  • Deduplicate similar questions into single entry

Deduplication

When multiple issues ask the same thing:

  • Combine into one FAQ entry
  • Reference all related issues: "See #123, #456"
  • Use the clearest answer from any of them

Maintenance Notes

  • Note when FAQ was last generated
  • Flag answers that may be outdated
  • Suggest issues that should be added to FAQ

Common Mistakes

  • Copying issue text verbatim instead of writing a standalone answer a reader can use without opening the issue.
  • Including one-off bugs that will never recur as FAQ entries.
  • Embedding version-specific commands or config without noting which version they apply to.

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