Find Code Tasks logo

Find Code Tasks

CommunityPopular
mikeyobrien
find-code-tasks

Lists all code tasks in the repository with their status, dates, and metadata. Useful for getting an overview of pending work or finding specific tasks.

Overview

Publishermikeyobrien
Repositoryralph-orchestrator
Skill namefind-code-tasks
Stars
3.2K
Forks
299
Bundled files
1
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Find Code Tasks 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/mikeyobrien/ralph-orchestrator/tree/main/.claude/skills/find-code-tasks
  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/mikeyobrien/ralph-orchestrator.git /tmp/ralph-orchestrator
mkdir -p .claude/skills
cp -r /tmp/ralph-orchestrator/.claude/skills/find-code-tasks .claude/skills/find-code-tasks
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Find Code Tasks 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 Find Code Tasks 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 Find Code Tasks 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.

Find Code Tasks

Overview

This skill finds and displays all code tasks (.code-task.md files) in the repository, showing their frontmatter status and metadata. Use it to get a quick overview of pending work, find tasks by status, or check the state of the task backlog.

When to Use

  • Starting a work session to see what tasks are available
  • Checking status of tasks before/after running code-assist
  • Finding tasks by status (pending, in_progress, completed)
  • Getting a summary of task backlog
  • Exporting task data for reporting

Parameters

  • filter (optional): Filter tasks by status

    • pending - Show only pending tasks
    • in_progress - Show only in-progress tasks
    • completed - Show only completed tasks
    • (none) - Show all tasks
  • format (optional, default: "table"): Output format

    • table - Human-readable table with status symbols
    • json - JSON array for programmatic use
    • summary - Counts by status only
  • tasks_dir (optional, default: ".ralph/tasks/"): Directory to search for tasks

Usage Examples

bash
# Show all tasks in table format
/find-code-tasks

# Show only pending tasks
/find-code-tasks filter:pending

# Get JSON output for tooling
/find-code-tasks format:json

# Quick summary of task counts
/find-code-tasks format:summary

# Search custom directory
/find-code-tasks tasks_dir:tools/

Steps

1. Run Task Status Script

The script is colocated with this skill at .claude/skills/find-code-tasks/task-status.sh.

Execute it with appropriate arguments:

bash
# Default: table format, all tasks
.claude/skills/find-code-tasks/task-status.sh

# With filter
.claude/skills/find-code-tasks/task-status.sh --pending
.claude/skills/find-code-tasks/task-status.sh --in_progress
.claude/skills/find-code-tasks/task-status.sh --completed

# With format
.claude/skills/find-code-tasks/task-status.sh --json
.claude/skills/find-code-tasks/task-status.sh --summary

# Custom tasks directory
TASKS_DIR=tools/ .claude/skills/find-code-tasks/task-status.sh

2. Present Results

Display the output to the user. For table format, the output includes:

SymbolStatus
○pending
●in_progress
✓completed
■blocked

3. Suggest Next Actions

Based on the results, suggest relevant actions:

  • If there are pending tasks: "Run /code-assist .ralph/tasks/<task-name>.code-task.md to start a task"
  • If there are in_progress tasks: "There are tasks already in progress - consider completing those first"
  • If all tasks are completed: "All tasks are done! Use /code-task-generator to create new tasks"

Output Examples

Table Format (default)

TASKS STATUS
════════════════════════════════════════════════════════════════
    TASK                                     STATUS       DATE
────────────────────────────────────────────────────────────────
○ add-task-frontmatter-tracking            pending      2025-01-15
○ enhance-headless-tool-output             pending      -
● fix-ctrl-c-freeze                        in_progress  2025-01-14
✓ replay-backend                           completed    2025-01-13
────────────────────────────────────────────────────────────────
Total: 4 tasks

Summary Format

Task Summary
────────────
○ Pending:     10
● In Progress: 2
✓ Completed:   5
────────────
  Total:       17

JSON Format

json
[
  {"task": "add-task-frontmatter-tracking", "status": "pending", "created": "2025-01-15", "started": null, "completed": null},
  {"task": "fix-ctrl-c-freeze", "status": "in_progress", "created": "2025-01-14", "started": "2025-01-14", "completed": null}
]

Frontmatter Schema

Tasks with frontmatter tracking have this structure:

yaml
---
status: pending | in_progress | completed | blocked
created: YYYY-MM-DD    # Date task was created
started: YYYY-MM-DD    # Date work began (null if not started)
completed: YYYY-MM-DD  # Date work finished (null if not done)
---

Tasks without frontmatter are shown as pending with null dates.

Integration with Other Skills

  • code-task-generator: Creates new tasks with frontmatter
  • code-assist: Updates task status when starting/completing work
  • ralph-code-assist: Runs tasks through Ralph orchestrator

Troubleshooting

No Tasks Found

If no tasks are displayed:

  • Verify the tasks directory exists: ls .ralph/tasks/
  • Check file extension is .code-task.md
  • Try specifying directory: /find-code-tasks tasks_dir:./

Script Not Found

If the task-status.sh script is not found:

  • Ensure you're in the repository root
  • Check the script exists: ls .claude/skills/find-code-tasks/task-status.sh
  • Make it executable: chmod +x .claude/skills/find-code-tasks/task-status.sh

Frontmatter Not Parsed

If dates show as - for tasks with frontmatter:

  • Ensure frontmatter starts with --- on line 1
  • Check YAML syntax is valid
  • Verify field names match: status, created, started, completed

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Find Code Tasks AI skill do?

Lists all code tasks in the repository with their status, dates, and metadata. Useful for getting an overview of pending work or finding specific tasks.

Why use Find Code Tasks on TypingMind?

Because you install it once and use it with any model. Find Code Tasks 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 Find Code Tasks in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mikeyobrien/ralph-orchestrator/tree/main/.claude/skills/find-code-tasks. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Find Code Tasks?

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 Find Code Tasks?

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

Is the Find Code Tasks AI skill free?

Yes. It is published on GitHub by mikeyobrien 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 👇