My personal AI Agent devtools/dev UX set.
Custom skills for Claude Code that extend its capabilities.
| Skill | Description | Trigger Examples |
|---|---|---|
| interview | Socratic interviewer for requirements elicitation. Probes blind spots, challenges assumptions, synthesizes understanding. | /interview auth system, "help me think through this feature", vague requirements |
| lazy-skill | On-demand skill loader to reduce context bloat. Browse and load skills from ~/.claude/lazy-skills/ only when needed. |
/lazy-skill, /lazy-skill docker |
| mattermost-cli | Fetch and search Mattermost messages. Auto-redacts secrets for safe LLM processing. Maintained in its own repo. | "check my messages", "what did alice say about X", /mattermost |
# Skills from this repo
bunx skills@latest add ardasevinc/agent-devtools --skill <skill-name>
# mattermost-cli is maintained separately
bunx skills@latest add ardasevinc/mattermost-cli --skill mattermost-cli
bun i -g mattermost-cli # also requires the CLI tool (npm/pnpm also work)Custom statusline for Claude Code CLI showing hostname, directory, git status, context usage, model, and time.
macbook │ anthropics/claude-code │ ⎇ main*↑1 │ ctx:52% │ opus-4.5 │ 20260130 16:00
Requires Bun runtime.
# Symlink to Claude config
ln -sf /path/to/agent-devtools/claudecode/statusline.ts ~/.claude/statusline.ts
# Add to ~/.claude/settings.json{
"statusLine": {
"type": "command",
"command": "bun ~/.claude/statusline.ts",
"padding": 0
}
}- Hostname: Machine name
- Directory: Last 2 path components
- Git: Branch, worktree (⎇), dirty (*), ahead (↑n), behind (↓n)
- Context: Usage percentage from session files
- Model: Current Claude model (opus-4.5, sonnet-4, etc.)
- Time: yyyymmdd HH:MM format
Interactive fzf picker to browse and resume Claude Code sessions by their task lists. Launches Claude with CLAUDE_CODE_TASK_LIST_ID set, enabling task sharing/resumption across sessions.
agent-devtools (3 tasks) - 2h ago │ ✓ Add skills catalog to README
vyvo-app (12 tasks) - 1d ago │ → Implement auth flow
mattermost-cli (5 tasks) - 3d ago │ ○ Add rate limiting
# Add to PATH
ln -sf /path/to/agent-devtools/claudecode/claude-tasks.ts ~/.local/bin/claude-tasks
# Make executable
chmod +x ~/.local/bin/claude-tasksclaude-tasks # Pick a task list, launches claude
claude-tasks --resume # Pass flags through to claude- Project detection: Resolves project path from session files
- Task preview: Shows tasks with status (✓ done, → in progress, ○ pending)
- Recency sorting: Most recent sessions first
- Seamless launch: Opens Claude in the correct directory with task context
Reduce context bloat by loading skills on-demand instead of always injecting them. Skills in ~/.claude/lazy-skills/ are only read when you invoke /lazy-skill.
# Create the lazy skills directory
mkdir -p ~/.claude/lazy-skills
# Install the meta-skill
bunx skills@latest add ardasevinc/agent-devtools --skill lazy-skill- Place skill file at
~/.claude/lazy-skills/<name>.mdor clone a skill repo to~/.claude/lazy-skills/<name>/ - Edit the index in the installed skill (
~/.claude/skills/lazy-skill/SKILL.md):
## Index
- **skillname**: keyword1, keyword2 - "Brief description"
- **reponame** [collection]: keywords - "Description" # for skill repos~/.claude/lazy-skills/
├── stripe.md # single file
├── dokploy/ # single skill repo
│ └── SKILL.md
└── threejs-skills/ # skill collection (multiple skills)
├── README.md # shows available skills
└── skills/
├── threejs-fundamentals/
│ └── SKILL.md
└── ...
- Single skills: auto-detects
<name>.mdor<name>/SKILL.md - Collections: mark with
[collection]in index, reads README first