agentleFS
Sign inStart free
brittbritt/agent-skills/skills/summarize-conversation-thread/SKILL.md

summarize-conversation-thread

Skill11 starsChanged 6 days agoMITView on GitHub

Use when catching up on a long GitHub issue or PR discussion thread, or asked to summarize a thread, extract key decisions, or list action items - produces a structured summary with TL;DR, decisions, action items, open questions, and next steps

The file

We split this skill into the rules it gives an agent

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

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read long GitHub issue or PR threads and produce concise summaries highlighting what matters.

    line 8
  2. Distinctive:

    No gh CLI or no repo access: Ask the user to paste the thread content

    line 26

≈ “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

Summarize Conversation Thread Skill

Read long GitHub issue or PR threads and produce concise summaries highlighting what matters.

When to Use

Activate when:

  • Catching up on a lengthy discussion
  • Preparing to contribute to an existing thread
  • Extracting decisions from a closed issue
  • Identifying action items from a discussion

When NOT to use: Skip for short threads (fewer than ~5 comments) — just read them directly.

Getting the Thread

First, obtain the full thread content:

  • Issues: gh issue view <number> --comments (requires the gh CLI, authenticated)
  • PRs: gh pr view <number> --comments
  • No gh CLI or no repo access: Ask the user to paste the thread content

Output Structure

## Summary: [Issue/PR Title]

**Status**: [Open/Closed] | **Comments**: [X] | **Last Activity**: [date]

### TL;DR

[2-3 sentence summary of the core discussion]

### Key Decisions

- **[Decision]**: [context and who decided]

### Action Items

- [ ] [Action] — @[owner]

### Open Questions

- [Unresolved question needing input]

### Next Steps

[What should happen next]

Guidelines

What to Include

  • Decisions made and who made them
  • Action items with clear owners
  • Unresolved questions or blockers
  • Changes in direction or scope
  • Links to key comments

What to Skip

  • Redundant "+1" or "me too" comments
  • Off-topic tangents
  • Superseded proposals
  • Resolved sub-discussions

Handling Edge Cases

  • Stale threads (>30 days inactive): Note this and flag if decisions may be outdated
  • Heated discussions: Present all perspectives neutrally
  • No resolution: Clearly state "No decision reached" and summarize options discussed
  • Long threads (50+ comments): Break into phases if discussion evolved significantly

Example

## Summary: Add dark mode support (#142)

**Status**: Open | **Comments**: 23 | **Last Activity**: 2 days ago

### TL;DR

Team agreed to implement dark mode using CSS variables. Debate on whether to auto-detect system preference or default to light mode resolved in favor of auto-detect.

### Key Decisions

- **Use CSS variables**: Easier to maintain than separate stylesheets — @sarah
- **Auto-detect system preference**: Better UX, users can override — @mike

### Action Items

- [ ] Create color token system — @sarah
- [ ] Add toggle to settings page — @alex

### Next Steps

Sarah to submit initial PR with color variables by Friday.

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