New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Unified Notifications

by goern in goern/forgejo-mcp

Fetch and display notifications from both GitHub and Codeberg in a unified markdown view with clickable links.

GPL-3.0Auto-check passed

Install Unified Notifications

skills CLI
$ npx skills add goern/forgejo-mcp --skill unified-notifications -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install goern/forgejo-mcp unified-notifications --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/goern/forgejo-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/unified-notifications .claude/skills/unified-notifications && rm -rf skills-src

Use ~/.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/

Facts

Skill name
unified-notifications
GitHub stars
141
Token cost
~802 tokens
SKILL.md length
233 words
Files
2 (incl. scripts)
Skills in repo
15
Repo updated
First seen
Licence
GPL-3.0

At a glance

Fetch and display notifications from both GitHub and Codeberg in a unified markdown view with clickable links.

  • Requests like check notifications
  • SKILL.md covers Quick Start, Example Output, Modes and Integration with Claude Code, plus 2 more sections
  • Runs Python scripts from its folder; calls python3 and gh; reaches github.com and codeberg.org
  • Show my notifications

What it does

Unified Notifications is an agent skill from goern/forgejo-mcp. Fetch and display notifications from both GitHub and Codeberg in a unified markdown view with clickable links. Two modes: all (58+ notifications) or next-action (top 5 actionable items). Shows notifications sorted by newest first, grouped by platform. Use /unified-notifications for all notifications. Use next-action mode (python3 .claude/skills/unified-notifications/scripts/fetchnotifications.py next-action) to see only the top 5 items needing your attention. Triggers on requests like "check notifications", "show…

Its SKILL.md is about 800 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/fetch_notifications.py`).

It works with GitHub, Python and Model Context Protocol. The repository describes itself as: MIRROR ONLY!! This Model Context Protocol (MCP) server provides tools and resources for interacting with the Forgejo (specifically Codeberg.org) REST API. The licence is GPL-3.0.

When your agent uses it

  • Requests like check notifications
  • Show my notifications
  • Unified notifications
  • What needs attention

Example prompts

  • “check notifications”
  • “show my notifications”
  • “unified notifications”
  • “/unified-notifications”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 7be5d02. 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/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3
    • gh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com
    • codeberg.org

    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

Unified Notifications loads about 802 tokens when it runs. Until then it costs about 164 tokens; SKILL.md has 233 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~164
When it runs · the whole SKILL.md, loaded when a task matches
~802

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 goern/forgejo-mcp at commit 7be5d02, republished under its GPL-3.0 licence (© goern). 233 words, ~802 tokens.

Download SKILL.mdSave it as .claude/skills/unified-notifications/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
unified-notifications
description
Fetch and display notifications from both GitHub and Codeberg in a unified markdown view with clickable links. Two modes: all (58+ notifications) or next-action (top 5 actionable items). Shows notifications sorted by newest first, grouped by platform. Use /unified-notifications for all notifications. Use next-action mode (python3 .claude/skills/unified-notifications/scripts/fetch_notifications.py next-action) to see only the top 5 items needing your attention. Triggers on requests like "check notifications", "show my notifications", "unified notifications", "next actions", "what needs attention", or "/unified-notifications".

Unified Notifications

View all your notifications from GitHub and Codeberg in a single markdown view with clickable links, sorted by newest first.

Quick Start

All notifications
bash
python3 scripts/fetch_notifications.py
Top 5 actionable items (next-action mode)
bash
python3 scripts/fetch_notifications.py next-action

Output shows:

  • Summary counts (total, GitHub, Codeberg)
  • All notifications sorted by newest first
  • Grouped by platform
  • Icons: 🔀 (PR/MR), 📌 (Issue)
  • Direct links to each item
  • In next-action mode: Prioritization reasons for each item

Example Output

# 📬 Unified Notifications
**Total**: 58 | **GitHub**: 38 | **Codeberg**: 20

## GitHub
- 🔀 **[owner/repo](https://github.com/owner/repo)** [PR Title](link)
- 📌 **[owner/repo](https://github.com/owner/repo)** [Issue Title](link)

## Codeberg
- 🔀 **[owner/repo](https://codeberg.org/owner/repo)** [MR Title](link)

Modes

All Mode (default)

Shows all 58+ notifications across GitHub and Codeberg, sorted by newest first.

Next-Action Mode

Intelligently filters to show only the 5 most actionable items:

Prioritization logic:

  • ✅ Excludes dependency updates (chore(deps), renovate, etc.) - too low priority
  • ✅ Prioritizes PRs over issues - more action-oriented
  • ✅ Prioritizes key repos (b4arena, forgejo-mcp, ludus, infra)
  • ✅ Prioritizes feature/fix items over research
  • ✅ Includes a reason for each item's ranking

Example next-action items:

  • Feature PRs in important repos
  • Bug fix PRs
  • Critical issues assigned to you
  • Items requiring your review/action

Integration with Claude Code

Show all notifications (58+ items)
/unified-notifications
python3 .claude/skills/unified-notifications/scripts/fetch_notifications.py next-action

Or use the full path:

python3 /var/home/goern/.claude/skills/unified-notifications/scripts/fetch_notifications.py next-action

Tip: For a quick overview of what needs attention, use the next-action command above. For a comprehensive view of all notifications, use /unified-notifications.

Requirements

  • gh CLI (GitHub) installed and authenticated
  • forgejo-mcp CLI installed and configured
  • Python 3.6+

Troubleshooting

If notifications don't appear:

  • Verify gh api notifications --paginate returns data
  • Verify forgejo-mcp --cli check_notifications returns data
  • Check that both tools are properly authenticated

© goern, GPL-3.0. 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 1 other file (scripts) in .claude/skills/unified-notifications of goern/forgejo-mcp.

  • SKILL.md
  • scripts/fetch_notifications.py

Open the folder on GitHubat commit 7be5d02

Compare with similar skills

Unified Notifications 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.

Unified Notifications compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Unified Notifications this skillgoern/forgejo-mcp141—~802Automated safety check: PassGPL-3.0
Homepage Generatorwanshuiyin/ARIS-in-AI-Offer582—~4.8kAutomated safety check: NotesMIT
Humanizer RuVladimir-Human/humanizer-ru126—~4kAutomated safety check: PassMIT
Open PRArcadeAI/arcade-mcp1k—~2.9kAutomated safety check: PassMIT
Claude Certificationfancyboi999/ai-engineering-from-scratch-zh1.2k—~1.3kAutomated safety check: PassMIT
Os ReleaseCronusL-1141/AI-company371—~2.3kAutomated safety check: PassMIT

Similar skills

  • Homepage Generator

    wanshuiyin/ARIS-in-AI-Offer

    Generate a fact-checked academic personal homepage from a CV, optionally augmented by an existing manual homepage and an assets directory.

    582 GitHub stars~4.8k tokensUpdated 4 days ago
    AI & LLM EngineeringAuto-check: notes

  • Humanizer Ru

    Vladimir-Human/humanizer-ru

    Не для обхода детекторов; не для текста, который тебе не принадлежит.

    126 GitHub stars~4k tokensUpdated yesterday
    Writing & ContentAuto-check passed

  • Open PR

    ArcadeAI/arcade-mcp

    Prepare arcade-mcp changes for review by verifying intended behavior, filling the repository PR template, and creating or updating the PR.

    1k GitHub stars~2.9k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Claude Certification

    fancyboi999/ai-engineering-from-scratch-zh

    AI Engineering from Scratch 中四条独立 Claude 认证路线的 AI 原生导师与入门流程。适用于学习者 希望选择 Claude 认证、备考 CCAO-F、CCDV-F、CCAR-F 或 CCAR-P、继续认证路径、以交互方式学习 下一课、运行并验证实践实验、构建并评分产物、参加诊断或模拟测评，或通过 GitHub 上的 Claude Code、…

    1.2k GitHub stars~1.3k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Os Release

    CronusL-1141/AI-company

    发布 AI Team OS 新版本的完整清单——预检、版本七处锁步、中英双语 CHANGELOG、双份 dist 构建、私有术语扫描、commit/tag、双仓推送、建 GitHub Release 条目并核对 latest 徽章、事后核对。当准备发版、补建漏掉的 Release 条目、或核对已发版本的线上状态时使用。

    371 GitHub stars~2.3k tokensUpdated today
    DevelopmentAuto-check passed

  • Release Changelog

    pipeshub-ai/pipeshub-ai

    Generate an enterprise-style changelog for a PipesHub GitHub release.

    3.8k GitHub stars~2.7k tokensUpdated today
    DevelopmentAuto-check passed

More from goern/forgejo-mcp

All 15 skills in this repo

  • Release Openspec

    goern/forgejo-mcp

    A skill your agent uses when releasing OpenSpec: audit merged work and changeset coverage, decide whether a catch-up changeset PR is needed, prepare or resume the Changesets Version Packages PR, cut…

    141 GitHub starsUsed in 1 repo~3.2k tokens
    Auto-check passed

  • Caveman Compress

    goern/forgejo-mcp

    Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup.

    141 GitHub starsUsed in 1 repo~1.2k tokens
    Auto-check: notes

  • Draft Openspec Docs

    goern/forgejo-mcp

    Collaborative page-drafting mode for the OpenSpec docs. An agent skill from goern/forgejo-mcp.

    141 GitHub starsUsed in 1 repo~815 tokens
    Auto-check passed

  • Verify Openspec Docs

    goern/forgejo-mcp

    Fact-checks OpenSpec user documentation with a fresh-context subagent that re-runs commands and checks claims against source.

    141 GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed

  • Wt Switch Create

    goern/forgejo-mcp

    Create a new worktrunk worktree (optionally in another repo) and switch this session's working directory into it.

    141 GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check passed

  • Caveman Help

    goern/forgejo-mcp

    Quick-reference card for caveman modes, skills and commands.

    141 GitHub stars~564 tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Unified Notifications

What does Unified Notifications do?

Fetch and display notifications from both GitHub and Codeberg in a unified markdown view with clickable links. Unified Notifications is an agent skill from goern/forgejo-mcp. Fetch and display notifications from both GitHub and Codeberg in a unified markdown view with clickable links.

When should I use Unified Notifications?

Unified Notifications fits situations like: requests like check notifications; show my notifications; unified notifications; what needs attention.

How do I install Unified Notifications in Claude Code?

Run `npx skills add goern/forgejo-mcp --skill unified-notifications -a claude-code`. Or copy the skill folder (.claude/skills/unified-notifications in goern/forgejo-mcp) into .claude/skills/unified-notifications in your project. Claude Code loads it when a task matches its description.

How do I install Unified Notifications in Codex?

Run `npx skills add goern/forgejo-mcp --skill unified-notifications -a codex`. Or copy the skill folder (.claude/skills/unified-notifications in goern/forgejo-mcp) into .agents/skills/unified-notifications in your project. Codex loads it when a task matches its description.

Can I use Unified Notifications 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 goern/forgejo-mcp --skill unified-notifications -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/unified-notifications, .gemini/skills/unified-notifications, .github/skills/unified-notifications and .opencode/skills/unified-notifications in your project.

What does Unified Notifications need to run?

Going by SKILL.md and its folder, Unified Notifications needs Python for the scripts in its folder and the command-line tools its instructions call (python3 and gh). Our summary lists: Python 3.

Does Unified Notifications access the network?

SKILL.md names 2 domains. In commands or code: github.com and codeberg.org; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Unified Notifications 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 Unified Notifications use?

Unified Notifications is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Unified Notifications use?

About 802 tokens (SKILL.md is roughly 3.2k 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 Unified Notifications?

Skills that share tags, products or a category with Unified Notifications: Homepage Generator (wanshuiyin/ARIS-in-AI-Offer, 582 stars), Humanizer Ru (Vladimir-Human/humanizer-ru, 126 stars), Open PR (ArcadeAI/arcade-mcp, 1k stars) and Claude Certification (fancyboi999/ai-engineering-from-scratch-zh, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Unified Notifications?

goern (a GitHub user) maintains it in goern/forgejo-mcp, which has 141 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 9, 2026.

Source: goern/forgejo-mcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.