Setup
Prorise-cool/Claude-Code-Multi-Agent
Complete guide to installing Git and performing basic configuration across all platforms (Windows, macOS, Linux, WSL).
Comprehensive GitHub contribution analysis for any time period.
Install GitHub Activity Analyzer
$ npx skills add changkun/dotfiles --skill github-activity-analyzer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install changkun/dotfiles github-activity-analyzer --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/changkun/dotfiles.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/github-activity-analyzer .claude/skills/github-activity-analyzer && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "github-activity-analyzer" agent skill from https://github.com/changkun/dotfiles/tree/main/.claude/skills/github-activity-analyzer into .claude/skills/github-activity-analyzer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "github-activity-analyzer", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/changkun/dotfiles/tree/main/.claude/skills/github-activity-analyzerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add changkun/dotfiles --skill github-activity-analyzer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install changkun/dotfiles github-activity-analyzer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/changkun/dotfiles.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/github-activity-analyzer .agents/skills/github-activity-analyzer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "github-activity-analyzer" agent skill from https://github.com/changkun/dotfiles/tree/main/.claude/skills/github-activity-analyzer into .agents/skills/github-activity-analyzer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "github-activity-analyzer", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add changkun/dotfiles --skill github-activity-analyzer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install changkun/dotfiles github-activity-analyzer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/changkun/dotfiles.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/github-activity-analyzer .cursor/skills/github-activity-analyzer && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "github-activity-analyzer" agent skill from https://github.com/changkun/dotfiles/tree/main/.claude/skills/github-activity-analyzer into .cursor/skills/github-activity-analyzer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "github-activity-analyzer", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/changkun/dotfiles.git --path .claude/skills/github-activity-analyzer--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add changkun/dotfiles --skill github-activity-analyzer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install changkun/dotfiles github-activity-analyzer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/changkun/dotfiles.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/github-activity-analyzer .gemini/skills/github-activity-analyzer && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "github-activity-analyzer" agent skill from https://github.com/changkun/dotfiles/tree/main/.claude/skills/github-activity-analyzer into .gemini/skills/github-activity-analyzer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "github-activity-analyzer", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install changkun/dotfiles github-activity-analyzerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add changkun/dotfiles --skill github-activity-analyzer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/changkun/dotfiles.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/github-activity-analyzer .github/skills/github-activity-analyzer && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "github-activity-analyzer" agent skill from https://github.com/changkun/dotfiles/tree/main/.claude/skills/github-activity-analyzer into .github/skills/github-activity-analyzer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "github-activity-analyzer", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add changkun/dotfiles --skill github-activity-analyzer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install changkun/dotfiles github-activity-analyzer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/changkun/dotfiles.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/github-activity-analyzer .opencode/skills/github-activity-analyzer && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "github-activity-analyzer" agent skill from https://github.com/changkun/dotfiles/tree/main/.claude/skills/github-activity-analyzer into .opencode/skills/github-activity-analyzer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "github-activity-analyzer", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
github-activity-analyzer- GitHub stars
- 151
- Token cost
- ~1.6k tokens
- SKILL.md length
- 772 words
- Files
- 5 (incl. scripts)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Comprehensive GitHub contribution analysis for any time period.
- Works in 5 steps: Event Analysis: Fetches and categorizes… → Content Deep Dive: Extracts PR titles,… → Theme Identification: Groups… → …
- User asks about recent work
- SKILL.md covers When to Use This Skill, Capabilities, How It Works and Technical Requirements, plus 1 more section
- Runs Shell scripts from its folder; calls gh
What it does
GitHub Activity Analyzer is an agent skill from changkun/dotfiles. Comprehensive GitHub contribution analysis for any time period. Use when user asks about recent work, wants to review their contributions, needs a status update, or requests activity summary. Supports flexible formats: relative time (days/weeks/months/years), full years (2025), specific date ranges (2024-10-01 to 2024-12-31), and from-date-to-today. Provides detailed insights into PRs, commits, code reviews, and technical themes.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts (for example `EXAMPLES.md`, `README.md` and `commands/github-activity.md`).
It sits in Development, covering Code review. It works with GitHub, Linux and macOS. The repository describes itself as: personal development settings. The licence is MIT.
When your agent uses it
- User asks about recent work
- Wants to review their contributions
- Needs a status update
- Requests activity summary
Example prompts
- “/github-activity-analyzer”
Requirements
- A Bash shell
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Event Analysis: Fetches and categorizes all GitHub events (pushes, PRs, reviews, comments, releases)
- Content Deep Dive: Extracts PR titles, descriptions, commit messages, and review comments
- Theme Identification: Groups contributions by technical domain (e.g., performance, infrastructure, features)
- Impact Assessment: Highlights most significant contributions and their business value
- Statistics: Provides counts and trends across repositories
What it can do on your machine
Read from SKILL.md and the folder at commit 97dd127. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Shell), which the agent can run.
Shell commands in SKILL.md call:
gh
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use gh, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
GitHub Activity Analyzer loads about 1.6k tokens when it runs. Until then it costs about 115 tokens; SKILL.md has 772 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from changkun/dotfiles at commit 97dd127, republished under its MIT licence (© changkun). 772 words, ~1,580 tokens.
Download SKILL.mdSave it as
.claude/skills/github-activity-analyzer/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- github-activity-analyzer
- description
- Comprehensive GitHub contribution analysis for any time period. Use when user asks about recent work, wants to review their contributions, needs a status update, or requests activity summary. Supports flexible formats: relative time (days/weeks/months/years), full years (2025), specific date ranges (2024-10-01 to 2024-12-31), and from-date-to-today. Provides detailed insights into PRs, commits, code reviews, and technical themes.
GitHub Activity Analyzer Skill
Analyzes comprehensive GitHub activity for any specified time period with deep technical insights. Supports arbitrary time frames from days to full years.
When to Use This Skill
Use this skill when the user:
- Asks "what have I been working on?"
- Requests a summary of recent contributions (any time period)
- Wants to review their GitHub activity
- Needs to prepare a status update or report
- Says "show me my recent work" or "what did I do last week/month/year"
- Asks about contribution statistics for a specific period
- Wants insights into their coding patterns over time
- Requests activity analysis with various time formats:
- Relative: "last 7 days", "past month", "last year"
- Full years: "2025", "year 2024", "all of 2023"
- Date ranges: "2024-10-01 to 2024-12-31", "Q4 2024", "October 2024"
- From date: "since 2024-10-01", "from October"
Capabilities
- Event Analysis: Fetches and categorizes all GitHub events (pushes, PRs, reviews, comments, releases)
- Content Deep Dive: Extracts PR titles, descriptions, commit messages, and review comments
- Theme Identification: Groups contributions by technical domain (e.g., performance, infrastructure, features)
- Impact Assessment: Highlights most significant contributions and their business value
- Statistics: Provides counts and trends across repositories
How It Works
Time Period Parsing
Extract and parse time period from user's request in multiple formats:
A. Relative time (days back from today):
- "last week", "7 days", "1w" → 7 days
- "last 2 weeks", "14 days", "2w" → 14 days (default if not specified)
- "last month", "30 days", "1m" → 30 days
- "last 6 months" → 180 days
- "last year", "365 days", "1y" → 365 days
- Custom: "45 days" → 45 days
B. Full year:
- "2025", "year 2025", "all of 2024" → Date range: YYYY-01-01 to YYYY-12-31
- Parse the year and set as full calendar year
C. Specific date range:
- "2024-10-01 to 2024-12-31" → Exact date range
- "from October 1st to December 31st 2024" → Parse natural language to YYYY-MM-DD
- "Q4 2024" → 2024-10-01 to 2024-12-31
- "October 2024" → 2024-10-01 to 2024-10-31
- "Q1 2025" → 2025-01-01 to 2025-03-31
D. From date to today:
- "since 2024-10-01" → From that date to today
- "from October 2024" → From 2024-10-01 to today
Default to 14 days (2 weeks) if no time period mentioned
Data Collection
- Uses
gh api users/{username}/eventsto fetch activity - For relative time: Dynamically calculates date N days ago from today
- For date ranges: Uses the parsed start and end dates directly
- Filters events within the date range (inclusive)
- Fetches detailed PR information for opened/merged PRs
- Retrieves commit messages from most active repositories
- Samples code review comments to understand review style
Important Note: GitHub's events API only returns the last 90 days of events. For time periods beyond 90 days:
- Use GitHub Search API for issues and PRs:
gh api search/issues - Query specific repository commits:
gh api repos/{owner}/{repo}/commits - Fetch data from multiple endpoints and aggregate
- Focus on major contributions and highlights for longer periods
Show full SKILL.md (309 more words)Show less
Analysis
- Groups work by repository and technical theme
- Identifies patterns (e.g., VAT integration, performance optimization)
- Extracts technical details (formulas, benchmarks, metrics)
- Summarizes code review leadership
Output Format
- Executive summary
- Activity breakdown by theme
- Technical highlights with specifics
- Statistics table
- Impact assessment
Technical Requirements
- GitHub CLI (
gh) must be installed and authenticated - Access to user's GitHub events via API
- Ability to fetch PR and commit details from repositories
Implementation Guidelines
Time Period Handling:
- Always parse the user's requested time period from natural language
- Support all formats: relative days, full years, specific ranges, from-date-to-today
- Default to 14 days (2 weeks) if no period specified
- Calculate dates dynamically from today's date for relative periods
- Be flexible: "last week", "7 days", "1w" should all work the same
- Convert natural language dates: "October 2024" → "2024-10-01 to 2024-10-31"
- Handle quarters: "Q1 2025" → "2025-01-01 to 2025-03-31"
- For periods >90 days, acknowledge API limitations and use alternative approaches
API Strategy for Different Time Periods:
- 0-90 days: Use events API directly (
gh api users/{username}/events) - >90 days or specific old dates: Combine multiple approaches:
- Search API:
gh api search/issues?q=author:{username}+created:>=YYYY-MM-DD - Search API for PRs:
gh api search/issues?q=is:pr+author:{username}+created:>=YYYY-MM-DD - Repo commits: Identify active repos and query commits
- Focus on major milestones and highlights
- Search API:
- 0-90 days: Use events API directly (
Content Adaptation by Period Length:
- <30 days: Full detailed analysis with all PRs, commits, reviews
- 30-90 days: Detailed with slight summarization of minor items
- 3-6 months: Focus on major contributions, monthly themes
- Full year: Quarterly breakdown, key highlights, statistics, major impact
Technical Details:
- Include ticket numbers (e.g., RMC-XXX, YIELD-XXXX) when present in commits/PRs
- Provide specific technical details with formulas, benchmarks, and metrics - not generic summaries
- Balance breadth (number of repos) with depth (technical implementation details)
- Preserve context like performance gains, schema changes, integration specifics
Performance:
- Use parallel API calls where possible for better performance
- For very long periods, paginate and aggregate strategically
- Cache intermediate results if processing multiple endpoints
© changkun, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 4 other files (scripts) in .claude/skills/github-activity-analyzer of changkun/dotfiles.
- SKILL.md
- EXAMPLES.md
- README.md
- commands/github-activity.md
- scripts/fetch-github-activity.sh
Open the folder on GitHubat commit 97dd127
Compare with similar skills
GitHub Activity Analyzer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| GitHub Activity Analyzer this skillchangkun/dotfiles | 151 | — | ~1.6k | Automated safety check: Pass | MIT | |
| SetupProrise-cool/Claude-Code-Multi-Agent | 305 | — | ~3k | Automated safety check: Notes | None | |
| Gitcrawlopenclaw/gitcrawl | 124 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Release NotesMikalaiBarysevich/CleverSwitch | 116 | — | ~975 | Automated safety check: Pass | GPL-3.0 | |
| Git ConfigProrise-cool/Claude-Code-Multi-Agent | 305 | — | ~4.4k | Automated safety check: Notes | None | |
| Debug Os Failure On GitHubstrands-agents/box | 110 | — | ~1.3k | Automated safety check: Notes | Apache-2.0 |
Similar skills
Gitcrawl
openclaw/gitcrawl
A skill your agent uses for local GitHub issue/PR archive search, sync freshness, clusters, durable maintainer triage, handoff to Octopool-backed gh reads, and Gitcrawl repo/release work.
Release Notes
MikalaiBarysevich/CleverSwitch
Generate GitHub release notes for unreleased CleverSwitch tags in the established repo format.
Git Config
Prorise-cool/Claude-Code-Multi-Agent
Comprehensive Git configuration guide covering global settings, aliases, performance tuning, credential management, maintenance, .gitattributes, clone shortcuts, and troubleshooting.
Debug Os Failure On GitHub
strands-agents/box
Debug a CI failure on an OS you are not on (you are on Linux, it fails on macos-latest, or the reverse) without opening a pull request per attempt.
Gui Tools
Prorise-cool/Claude-Code-Multi-Agent
Provides guidance for installing, configuring, and choosing Git graphical interface clients (GitKraken, Sourcetree, GitHub Desktop) across platforms.
Related
Categories
Questions about GitHub Activity Analyzer
What does GitHub Activity Analyzer do?
Comprehensive GitHub contribution analysis for any time period. GitHub Activity Analyzer is an agent skill from changkun/dotfiles. Comprehensive GitHub contribution analysis for any time period.
When should I use GitHub Activity Analyzer?
GitHub Activity Analyzer fits situations like: user asks about recent work; wants to review their contributions; needs a status update; requests activity summary.
How do I install GitHub Activity Analyzer in Claude Code?
Run `npx skills add changkun/dotfiles --skill github-activity-analyzer -a claude-code`. Or copy the skill folder (.claude/skills/github-activity-analyzer in changkun/dotfiles) into .claude/skills/github-activity-analyzer in your project. Claude Code loads it when a task matches its description.
How do I install GitHub Activity Analyzer in Codex?
Run `npx skills add changkun/dotfiles --skill github-activity-analyzer -a codex`. Or copy the skill folder (.claude/skills/github-activity-analyzer in changkun/dotfiles) into .agents/skills/github-activity-analyzer in your project. Codex loads it when a task matches its description.
Can I use GitHub Activity Analyzer in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add changkun/dotfiles --skill github-activity-analyzer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/github-activity-analyzer, .gemini/skills/github-activity-analyzer, .github/skills/github-activity-analyzer and .opencode/skills/github-activity-analyzer in your project.
What does GitHub Activity Analyzer need to run?
Going by SKILL.md and its folder, GitHub Activity Analyzer needs a shell for the scripts in its folder and the command-line tools its instructions call (gh). Our summary lists: A Bash shell.
Does GitHub Activity Analyzer access the network?
SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is GitHub Activity Analyzer safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does GitHub Activity Analyzer use?
GitHub Activity Analyzer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does GitHub Activity Analyzer use?
About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to GitHub Activity Analyzer?
Skills that share tags, products or a category with GitHub Activity Analyzer: Setup (Prorise-cool/Claude-Code-Multi-Agent, 305 stars), Gitcrawl (openclaw/gitcrawl, 124 stars), Release Notes (MikalaiBarysevich/CleverSwitch, 116 stars) and Git Config (Prorise-cool/Claude-Code-Multi-Agent, 305 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains GitHub Activity Analyzer?
changkun (a GitHub user) maintains it in changkun/dotfiles, which has 151 GitHub stars. The repository was last updated on September 27, 2026.
Source: changkun/dotfiles on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.