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

Task Decomposition

by aiming-lab in aiming-lab/MetaClaw

A skill your agent uses when a user presents a large, vague goal.

MITAuto-check passedAgent Workflows

Install Task Decomposition

skills CLI
$ npx skills add aiming-lab/MetaClaw --skill task-decomposition -a claude-code

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

GitHub CLI
$ gh skill install aiming-lab/MetaClaw task-decomposition --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/aiming-lab/MetaClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/memory_data/skills/task-decomposition .claude/skills/task-decomposition && 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
task-decomposition
GitHub stars
3.5k
Token cost
~185 tokens
SKILL.md length
72 words
Files
1
Skills in repo
36
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when a user presents a large, vague goal.

  • Works in 5 steps: Restate the end goal in one sentence. → List the concrete sub-tasks needed to… → Identify dependencies (which tasks block… → …
  • A user presents a large
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Task breakdown

What it does

Task Decomposition is an agent skill from aiming-lab/MetaClaw. Use this skill when a user presents a large, vague goal. Break it into concrete, ordered sub-tasks before starting any work. Apply whenever the request is larger than a single focused action.

Its SKILL.md is about 190 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Task breakdown. The repository describes itself as: 🦞 Just talk to your agent — it learns and EVOLVES 🧬. The licence is MIT.

When your agent uses it

  • A user presents a large
  • Tasks that involve Task breakdown

Example prompts

  • “/task-decomposition”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Restate the end goal in one sentence.
  2. List the concrete sub-tasks needed to reach it, in order.
  3. Identify dependencies (which tasks block others).
  4. Estimate relative complexity and flag any unknowns.
  5. Confirm the breakdown with the user before executing.

What it can do on your machine

Read from SKILL.md and the folder at commit 922caf3. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

Task Decomposition loads about 185 tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 72 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~185

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from aiming-lab/MetaClaw at commit 922caf3, republished under its MIT licence (© aiming-lab). 72 words, ~185 tokens.

Download SKILL.mdSave it as .claude/skills/task-decomposition/SKILL.md (or your agent's skills folder).
name
task-decomposition
description
Use this skill when a user presents a large, vague goal. Break it into concrete, ordered sub-tasks before starting any work. Apply whenever the request is larger than a single focused action.
category
productivity

Task Decomposition

Before starting a large goal, decompose it.

Steps:

  1. Restate the end goal in one sentence.
  2. List the concrete sub-tasks needed to reach it, in order.
  3. Identify dependencies (which tasks block others).
  4. Estimate relative complexity and flag any unknowns.
  5. Confirm the breakdown with the user before executing.

Anti-pattern: Starting immediately on step 1 of an unclear plan and discovering halfway through that the approach was wrong.

© aiming-lab, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in memory_data/skills/task-decomposition of aiming-lab/MetaClaw.

Open the folder on GitHubat commit 922caf3

Compare with similar skills

Task Decomposition 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.

Task Decomposition compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Task Decomposition this skillaiming-lab/MetaClaw3.5k—~185Automated safety check: PassMIT
Swarm Parallel Dispatchlangchain-ai/langchain-skills1.3k—~3kAutomated safety check: PassMIT
Deepagents Planning Todossoba-labs/langchain-agent-skills107—~2.3kAutomated safety check: PassMIT
Procrastination Busterhidai25/eval-view1371 repos~837Automated safety check: PassApache-2.0
Context Budgetericrisco/rsc-harness167—~2.4kAutomated safety check: PassMIT
MemPalace Task HandoffMemPalace/mempalace59k—~1.9kAutomated safety check: PassMIT

Similar skills

  • Swarm Parallel Dispatch

    langchain-ai/langchain-skills

    Official

    Fans a list of independent items out to subagents in parallel, merges the results back into a table and supports retrying only the rows that failed.

    1.3k GitHub stars~3k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

  • Deepagents Planning Todos

    soba-labs/langchain-agent-skills

    Use the writetodos tool effectively for task planning and decomposition in Deep Agents.

    107 GitHub stars~2.3k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • Procrastination Buster

    hidai25/eval-view

    Beat procrastination with task breakdown, 2-minute starts, and accountability tracking

    137 GitHub starsUsed in 1 repo~837 tokens
    Agent WorkflowsAuto-check passed

  • Context Budget

    ericrisco/rsc-harness

    A skill your agent uses when a long-horizon task is filling the context window and you must decide what to keep, offload, drop, or hand off to a fresh window — when to compact, what the summary must…

    167 GitHub stars~2.4k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • MemPalace Task Handoff

    MemPalace/mempalace

    Creates, hands off, claims, executes and closes agent tasks through the MemPalace logstream, with approval of the exact task before it is recorded.

    59k GitHub stars~1.9k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Planning And Task Breakdown

    abashev/vfs-s3

    Breaks work into ordered tasks. An agent skill from abashev/vfs-s3.

    106 GitHub starsUsed in 8 repos~1.9k tokens
    Agent WorkflowsAuto-check passed

More from aiming-lab/MetaClaw

All 36 skills in this repo

  • Data Validation First

    aiming-lab/MetaClaw

    Use this skill before any data analysis, transformation, or modeling.

    3.5k GitHub stars~230 tokensUpdated 4 mo ago
    Auto-check passed

  • Input Validation And Sanitization

    aiming-lab/MetaClaw

    A skill your agent uses when implementing any endpoint, form handler, CLI tool, or function that accepts external input.

    3.5k GitHub stars~251 tokensUpdated 4 mo ago
    Auto-check passed

  • Robust Error Handling In Scripts

    aiming-lab/MetaClaw

    A skill your agent uses when writing shell scripts, Python automation, or any unattended batch job.

    3.5k GitHub stars~225 tokensUpdated 4 mo ago
    Auto-check passed

  • Structured Logging And Observability

    aiming-lab/MetaClaw

    A skill your agent uses when building production services, pipelines, or automation that needs to be debugged, monitored, or audited.

    3.5k GitHub stars~247 tokensUpdated 4 mo ago
    Auto-check passed

  • Agent Task Handoff

    aiming-lab/MetaClaw

    A skill your agent uses when delegating a subtask to a sub-agent, spawning a parallel worker, or handing off work across sessions.

    3.5k GitHub stars~258 tokensUpdated 4 mo ago
    Auto-check passed

  • Async Communication Etiquette

    aiming-lab/MetaClaw

    A skill your agent uses when writing messages in async channels (Slack, GitHub issues, email threads) where the reader may not have context and cannot ask follow-up questions immediately.

    3.5k GitHub stars~224 tokensUpdated 4 mo ago
    Auto-check passed

Categories

Questions about Task Decomposition

What does Task Decomposition do?

A skill your agent uses when a user presents a large, vague goal. Task Decomposition is an agent skill from aiming-lab/MetaClaw. Use this skill when a user presents a large, vague goal.

When should I use Task Decomposition?

Task Decomposition fits situations like: A user presents a large; tasks that involve Task breakdown.

How do I install Task Decomposition in Claude Code?

Run `npx skills add aiming-lab/MetaClaw --skill task-decomposition -a claude-code`. Or copy the skill folder (memory_data/skills/task-decomposition in aiming-lab/MetaClaw) into .claude/skills/task-decomposition in your project. Claude Code loads it when a task matches its description.

How do I install Task Decomposition in Codex?

Run `npx skills add aiming-lab/MetaClaw --skill task-decomposition -a codex`. Or copy the skill folder (memory_data/skills/task-decomposition in aiming-lab/MetaClaw) into .agents/skills/task-decomposition in your project. Codex loads it when a task matches its description.

Can I use Task Decomposition 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 aiming-lab/MetaClaw --skill task-decomposition -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/task-decomposition, .gemini/skills/task-decomposition, .github/skills/task-decomposition and .opencode/skills/task-decomposition in your project.

What does Task Decomposition need to run?

SKILL.md names no scripts, command-line tools or credentials: Task Decomposition is instructions for the agent only.

Does Task Decomposition access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Task Decomposition 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. Review the folder before installing.

What licence does Task Decomposition use?

Task Decomposition is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Task Decomposition use?

About 185 tokens (SKILL.md is roughly 740 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 Task Decomposition?

Skills that share tags, products or a category with Task Decomposition: Swarm Parallel Dispatch (langchain-ai/langchain-skills, 1.3k stars), Deepagents Planning Todos (soba-labs/langchain-agent-skills, 107 stars), Procrastination Buster (hidai25/eval-view, 137 stars) and Context Budget (ericrisco/rsc-harness, 167 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Task Decomposition?

aiming-lab (a GitHub organization) maintains it in aiming-lab/MetaClaw, which has 3,458 GitHub stars. The repository holds 36 skills in this directory. The repository was last updated on June 7, 2026.

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