Achievements logo

Achievements

Community
vibeeval
achievements

Steam-style achievement system with XP, levels, streaks, and skill trees. Gamifies the development workflow. 25 achievements across 5 categories.

Overview

Publishervibeeval
Repositoryvibecosystem
Skill nameachievements
Stars
533
Forks
44
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by vibeeval on GitHub. Read the source before you install it.

Installation

Install the Achievements AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/vibeeval/vibecosystem/tree/main/skills/achievements
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/vibeeval/vibecosystem.git /tmp/vibecosystem
mkdir -p .claude/skills
cp -r /tmp/vibecosystem/skills/achievements .claude/skills/achievements
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Achievements in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Achievements on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Achievements is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Achievement System

Steam-style gamification for the development workflow. Earn XP by coding, fixing bugs, shipping features, and collaborating with agents. Level up, maintain streaks, and unlock achievements across 5 skill trees.

XP Level Thresholds

LevelXP RequiredTitle
10Apprentice
2100Developer
3300Engineer
5500Senior Engineer
101000Staff Engineer
203000Principal Engineer
5010000Legendary

Streak System

Consecutive days of coding activity multiply XP earned:

StreakMultiplier
1-2 days1.0x
3-6 days1.25x
7-13 days1.5x
14-29 days2.0x
30+ days3.0x

Missing a day resets the streak to 0.

Skill Trees

Tree 1: Code Warrior

Achievements for writing and shipping code.

First Blood (10 XP)

  • Description: Complete your first code review
  • Unlock: First time a commit or diff is reviewed in a session
  • Badge: Sword icon

Speed Demon (25 XP)

  • Description: Fix a bug in under 2 minutes from identification to resolution
  • Unlock: Bug-fix tool sequence completes in < 120 seconds
  • Badge: Lightning bolt

Polyglot (50 XP)

  • Description: Work in 3 or more programming languages in a single session
  • Unlock: Edit files with 3+ distinct language extensions in one session
  • Badge: Globe

Marathon Runner (100 XP)

  • Description: Sustain an 8-hour coding session without stopping
  • Unlock: Session active for 8+ hours (tracked via tool call timestamps)
  • Badge: Running figure

Perfectionist (50 XP)

  • Description: All tests pass on the very first run after a feature implementation
  • Unlock: Test suite passes immediately after the first Write/Edit sequence with no retries
  • Badge: Gold star

Tree 2: Bug Slayer

Achievements for hunting and eliminating bugs.

Bug Whisperer (25 XP)

  • Description: Fix 5 bugs in a single session
  • Unlock: 5 bug-fix tool sequences detected in one session
  • Badge: Magnifying glass

The Exterminator (75 XP)

  • Description: Fix 25 bugs across your lifetime
  • Unlock: Cumulative bugs-fixed counter reaches 25
  • Badge: Skull

Regression Hunter (40 XP)

  • Description: Catch a bug introduced in the last 24 hours before it ships
  • Unlock: Bug identified and fixed that was introduced in recent session
  • Badge: Net

Flaky Tamer (35 XP)

  • Description: Stabilize a flaky test that was failing intermittently
  • Unlock: A previously failing test now passes consistently across 3 runs
  • Badge: Anchor

Zero to Hero (60 XP)

  • Description: Reduce error count from 10+ to 0 in a single session
  • Unlock: Session starts with 10+ errors, ends with 0
  • Badge: Phoenix

Tree 3: Architecture Master

Achievements for system design and planning.

Architect's Vision (50 XP)

  • Description: Create an implementation plan with 10 or more steps
  • Unlock: Plan document written with 10+ numbered steps or tasks
  • Badge: Blueprint

The Refactorer (45 XP)

  • Description: Reduce a file from 300+ lines to under 200 lines without losing functionality
  • Unlock: File shrinks by 100+ lines in a single edit session
  • Badge: Scissors

Dependency Auditor (30 XP)

  • Description: Audit and clean up project dependencies in one session
  • Unlock: package.json or requirements.txt modified to remove 3+ entries
  • Badge: Package box

API Architect (55 XP)

  • Description: Design and implement a REST or GraphQL API with 5+ endpoints
  • Unlock: 5+ route or resolver definitions written in one session
  • Badge: Cloud diagram

The Modularizer (40 XP)

  • Description: Split a monolithic file into 3+ focused modules
  • Unlock: One file becomes 3+ new files in a refactoring session
  • Badge: Puzzle piece

Tree 4: Security Guardian

Achievements for security-conscious development.

Security Hawk (30 XP)

  • Description: Identify a security vulnerability during review
  • Unlock: Security review flags a CRITICAL or HIGH severity finding
  • Badge: Shield with eye

Secret Keeper (20 XP)

  • Description: Catch and remove a hardcoded credential before it commits
  • Unlock: Credential-deny hook triggers and the file is subsequently fixed
  • Badge: Lock

Input Validator (25 XP)

  • Description: Add Zod or schema validation to an unvalidated input
  • Unlock: Zod schema or validation logic added to an API handler or form
  • Badge: Checklist

Dependency Guardian (35 XP)

  • Description: Identify and update a dependency with a known CVE
  • Unlock: CVE-flagged dependency version bumped in package.json
  • Badge: Shield with checkmark

The Auditor (80 XP)

  • Description: Complete a full security audit with no CRITICAL findings
  • Unlock: security-reviewer agent completes a full sweep and returns clean
  • Badge: Gold shield

Tree 5: Team Player

Achievements for collaboration, mentoring, and cross-agent work.

The Mentor (75 XP)

  • Description: An agent's error triggers cross-training that updates the full team's knowledge
  • Unlock: Canavar cross-training propagates a learning from one agent to all others
  • Badge: Teacher at board

Night Owl (15 XP)

  • Description: Write code after midnight local time
  • Unlock: Tool call timestamp is between 00:00 and 04:00 local time
  • Badge: Owl

The Reviewer (20 XP)

  • Description: Complete 10 code reviews across your lifetime
  • Unlock: Cumulative commits-reviewed counter reaches 10
  • Badge: Magnifying glass over code

Streak Master (50 XP)

  • Description: Maintain a 7-day coding streak
  • Unlock: streak field reaches 7 in achievements.json
  • Badge: Fire

Knowledge Hoarder (65 XP)

  • Description: Store 20 learnings in the memory system across your lifetime
  • Unlock: Cumulative learnings-stored counter reaches 20
  • Badge: Brain

Achievement State File

Achievements are tracked in ~/.claude/achievements.json:

json
{
  "xp": 350,
  "level": 5,
  "streak": 7,
  "lastActive": "2026-04-08",
  "unlocked": {
    "first-blood": { "unlockedAt": "2026-04-01T10:00:00Z", "xp": 10 },
    "bug-whisperer": { "unlockedAt": "2026-04-05T14:22:00Z", "xp": 25 }
  },
  "progress": {
    "bugs-fixed": 3,
    "commits-reviewed": 12,
    "tests-passed": 45,
    "learnings-stored": 8,
    "session-bugs-fixed": 1,
    "session-languages": ["ts", "py"],
    "session-start": "2026-04-08T09:00:00Z"
  }
}

Leaderboard (Team Usage)

When multiple developers use the same vibecosystem config, achievements can be shared via a leaderboard file at ~/.claude/team-leaderboard.json. Each entry includes:

json
{
  "entries": [
    {
      "name": "batuhan",
      "xp": 1250,
      "level": 10,
      "streak": 14,
      "unlockedCount": 18,
      "topAchievement": "Legendary Streak"
    }
  ],
  "updatedAt": "2026-04-08T12:00:00Z"
}

Rankings are sorted by XP descending. Ties are broken by streak length.

Integration Points

  • achievement-tracker.ts (PostToolUse hook): Detects events and awards XP in real time
  • canavar-cross-review: Triggers "The Mentor" achievement on cross-training events
  • session-analytics: Provides session duration for "Marathon Runner"
  • credential-deny: Triggers "Secret Keeper" progress when a credential is blocked
  • passive-learner: Increments the learnings-stored counter for "Knowledge Hoarder"

Frequently asked questions

What does the Achievements AI skill do?

Steam-style achievement system with XP, levels, streaks, and skill trees. Gamifies the development workflow. 25 achievements across 5 categories.

Why use Achievements on TypingMind?

Because you install it once and use it with any model. Achievements is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Achievements in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vibeeval/vibecosystem/tree/main/skills/achievements. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Achievements?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Achievements?

As many as you like. As long as a model supports skills, you can use Achievements with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Achievements AI skill free?

Yes. It is published on GitHub by vibeeval under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇