Skip to content
Agentmart
Submit a tool

creating-tasks

Break a plan, spec, or conversation into tracer-bullet tasks with blocking edges.

Skill by supagetto

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/supagetto-creating-tasks

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Break a plan, spec, or conversation into tracer-bullet tasks with blocking edges. Use when the user says "to tasks".

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/creating-tasks

What's inside

Skill name
creating-tasks
Description
Break a plan, spec, or conversation into tracer-bullet tasks with blocking edges. Use when the user says "to tasks".
License
MIT
Instructions
79 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

Break a plan, spec, or conversation into a set of **tasks**: tracer-bullet vertical slices, each declaring the tasks that **block** it.

## Process

### 1. Gather context

Work from whatever is already in the conversation context. If the user passes a reference (a spec path) as an argument, fetch it and read its full body.

Done when the relevant spec (or other input) is fully in context.

### 2. Explore the codebase (optional)

If you have not already explored the codebase, do so to understand the current state of the code. Task titles and descriptions should use the project's domain glossary vocabulary.

Look for opportunities to prefactor the code to make the implementation easier. "Make the change easy, then make the easy change."

Done when you understand the domain vocabulary and have identified any prefactoring opportunities.

### 3. Draft vertical slices

Break the work into **tracer bullet** tasks.

<vertical-slice-rules>

- Each slice cuts a narrow but COMPLETE path through every layer (schema, API, UI, tests): vertical, NOT a horizontal slice of one layer
- A completed slice is demoable or verifiable on its own
- Each slice is sized to fit in a single fresh context window
- Any prefactoring should be done first

</vertical-slice-rules>

Give each task its **blocking edges**: the other tasks that must complete before it can start. A task with no blockers can start immediately.

Done when each slice has a title, blocking edges, and a clear deliverable.

> **Frontier note:** when ordering tasks, work the frontier — any task whose blockers are all done. For a purely linear chain that means blockers first (top to bottom).

**Wide refactors are the exception to vertical slicing.** A **wide refactor** is one mechanical change (rename a column, retype a shared symbol) whose **blast radius** fans across the whole codebase, so a single edit breaks thousands of call sites at once and no vertical slice can land green. Don't force it into a tracer bullet; sequence it as **expand–contract**. First expand: add the new form beside the old so nothing breaks. Then migrate the call sites over in batches sized by blast radius (per package, per directory), each batch its own task blocked by the expand, keeping CI green batch to batch because the old form still exists. Finally contract: delete the old form once no caller remains, in a task blocked by every migrate batch. When even the batches can't stay green alone, keep the sequence but let them share an integration branch that all block a final integrate-and-verify task; green is promised only there.

### 4. Quiz the user

Present the proposed breakdown as a numbered list. For each task, show:

- **Title**: short descriptive name
- **Blocked by**: which other tasks (if any) must complete first
- **What it delivers**: the end-to-end behaviour this task makes work

Ask the user:

- Does the granularity feel right? (too coarse / too fine)
- Are the blocking edges correct: does each task only depend on tasks that genuinely gate it?
- Should any tasks be merged or split further?

Iterate until the user approves the breakdown.

### 5. Save the tasks as local files

Save the approved tasks as local files under the spec directory's `tasks/` subdirectory. Follow the naming and path conventions in the using-workbench skill. Number files from `01` in dependency order (blockers first). Each file's "Blocked by" lists the numbers/titles it depends on. Use the per-task file template below: one task per file, never a single combined file.

Do NOT close or modify the parent spec file.

<local-task-template>

# <number>: <Task title>

**What to build:** the end-to-end behaviour this task makes work, from the user's perspective, not a layer-by-layer implementation list.

**Blocked by:** the numbers/titles of the tasks that gate this one, or "None (can start immediately)".

**Status:** ready-for-agent

- [ ] Acceptance criterion 1
- [ ] Acceptance criterion 2

</local-task-template>

Avoid specific file paths or code snippets: they go stale fast. Exception: if a prototype produced a snippet that encodes a decision more precisely than prose can (state machine, reducer, schema, type shape), inline it and note briefly that it came from a prototype. Trim to the decision-rich parts, not a working demo, just the important bits.

From supagetto/README.ai, MIT.

More from supagetto/README.ai

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 5, 2026 (25 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from supagetto

Cite this page

creating-tasks skill. Agent Mart. https://agentmart.dev/skills/supagetto-creating-tasks (last updated 2026-10-24)