Agent skill · Backend & API

analyse

Analyze GitHub issues, Pull Requests (PRs), Discussions, and repo health for an Open Source Software (OSS) project. Summarizes long threads, assesses PR readiness, detects duplicates, extracts reproduction steps, and generates repo health stats. Uses gh Command Line Interface (CLI) for GitHub Application Programming Interface (API) access. Complements oss-maintainer agent.

majiayu000github.com/majiayu000GitHub ↗
claude-codecan modify filesMIT
Install
npx skills add majiayu000/claude-skill-registry --skill analyse-borda-home --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 20 KB
Bundled scripts: none
Allowed tools: ReadBashWriteAgent
Path: skills/analysis/analyse-borda-home/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

<objective> Analyze GitHub issues and PRs to help maintainers triage, respond, and decide quickly. Produces actionable, structured output — not just summaries. </objective> <inputs> - **$ARGUMENTS**: one of: - Number (e.g. `42`) — issues, PRs, and discussions share a unified index; auto-detects the type - `health` — generate repo issue/PR health overview - `dupes [keyword]` — find potential duplicate issues - `contributors` — top contributor activity and release cadence - `ecosystem` — downstream consumer impact analysis for library maintainers - `--reply`: after analysis, spawn oss-maintainer to draft a contributor-facing reply from the report. Valid for issue, PR, and discussion modes only — silently ignored for health/dupes/contributors/ecosystem. </inputs> <workflow> ## Flag parsing If `$ARGUMENTS` contains `--reply`, strip it and set `REPLY_MODE=true`. Pass the remaining arguments into the mode-dispatch below. If the resolved mode is health/dupes/contributors/ecosystem, `REPLY_MODE` is silently ignored. ## Auto-Detection (for numeric arguments) Issues, PRs, and discussions share a unified running index — a given number can only be one type. Detect in two steps: ```bash # Step

What's inside
Steps it walks through
  1. Flag parsing
  2. Auto-Detection (for numeric arguments)
  3. Mode: Issue Analysis
  4. Mode: PR Analysis
  5. Mode: Discussion Analysis
  6. Mode: Repo Health Overview
  7. Mode: Duplicate Detection
  8. Mode: Contributor Activity
  9. Mode: Ecosystem Impact (for library maintainers)
  10. Draft contributor reply (--reply only)
Ships with 1 file
  • metadata.json
Commands it runs
Step 1: try the issues API (covers both issues and PRs)
if [ -n "$ITEM" ]; then
else
fi
unknown → print "Item #N not found" and stop
Fetch issue details
gh issue view $ARGUMENTS --json number,title,body,labels,comments,createdAt,author,state
Fetch all comments
gh issue view $ARGUMENTS --comments
PR metadata
More from claude-skill-registry
All skills →
About this skill
What does the analyse skill do?

Analyze GitHub issues, Pull Requests (PRs), Discussions, and repo health for an Open Source Software (OSS) project. Summarizes long threads, assesses PR readiness, detects duplicates, extracts reproduction steps, and generates repo health stats. Uses gh Command Line Interface (CLI) for GitHub Application Programming Interface (API) access. Complements oss-maintainer agent.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill analyse-borda-home --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going