basecamp/house-skills/github-activity
Claude Code and agent skill by basecamp/house-skills
- community
Checking that the SKILL.md file is still in the repository.
Fetch GitHub PRs, reviews, issues, and commits into day-cached JSON atoms. Uses the gh CLI for authentication and API calls. Part of the recap plugin's activity fetcher pipeline.
Install
npx vskill@latest install basecamp/house-skills/github-activitySKILL.md
GitHub Activity Fetcher
Fetch GitHub activity — PRs authored, PRs reviewed, issues created, commit contributions — into per-day cached JSON atoms at ~/.cache/recap/github/{user}/{YYYY-MM-DD}/activity.json.
Invocation
Contract
- Idempotent: same input produces same output, safe to re-run
- Day-cached: one JSON file per user per day
- `--reuse`: skip fetch if cache exists and is marked complete
- Rate-limit aware: uses
gh api --paginatewith built-in backoff
Quick Run
Where $SKILL_DIR = directory containing this SKILL.md.
Output Format
Each activity.json contains:
Commit contributions are cached separately as an aggregate at ~/.cache/recap/github/{user}/commits-{since}-{until}.json since GitHub's GraphQL API returns them as a period summary, not per-day.
Arguments
| Argument | Required | Description | |
|---|---|---|---|
--since | Yes | Start date (YYYY-MM-DD) | |
--until | No | End date (default: today) | |
--user | No | GitHub username (default: authenticated user) | |
--org | No | Filter to a specific GitHub org | |
--reuse | No | Skip fetch if cache exists and is complete |
Cache Structure
Prerequisites
ghCLI installed and authenticated (gh auth login)jqfor JSON parsing
Failure Modes
| Symptom | Cause | Fix | |
|---|---|---|---|
| "gh: not logged in" | Token expired | gh auth login | |
| Empty results | No activity in range | Expected — empty days cached as complete | |
| Rate limit (403) | Too many API calls | Wait ~1hr and retry | |
| >1000 PRs | Search API limit | Narrow date range or add --org filter |
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingplugins/recap/skills/github-activity/SKILL.md
Popularity
- Repository stars
- 73
- Repository forks
- 3
- 7-day trend score
- 22
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 29 Sep 2026, a month ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/basecamp/house-skills/github-activity)