Skip to content
Skills Library
AI & agents · Planning

parallelize

/parallelize

Use when several tasks are going out to separate agents at once and the work needs splitting into what can run simultaneously and what has to wait, before any of it is kicked off.

Licence
MIT
Last repository change
27.10.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
2
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 27.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Use when several tasks are going out to separate agents at once and the work needs splitting into what can run simultaneously and what has to wait, before any of it is kicked off.

Original author description

Use when several tasks are going out to separate agents at once and the work needs splitting into what can run simultaneously and what has to wait, before any of it is kicked off.

How it works

  1. Workflow
  2. Rationalizations
Original SKILL.md headings · 24 lines, 325 words
SKILL.md preview
---
name: parallelize
description: Use when several tasks are going out to separate agents at once and the work needs splitting into what can run simultaneously and what has to wait, before any of it is kicked off.
---

# Parallelize

Turn a set of tasks into an ordered set of stages: what can run at the same time, and what has to wait for something else to land first. The goal is the most parallelism the dependencies allow, with no two agents doing overlapping work.

## Workflow

1. Gather the tasks. Where they are Linear issues, fetch them with the Linear MCP server so each one carries its own description rather than a title.
2. Copy `assets/parallelization.md` to `/tmp/[title].md`, slugifying the title.
3. Fill in the tasks, then sort them into stages. A task belongs in the earliest stage whose predecessors have all finished.
4. Look for overlaps: two tasks that would edit the same files, or that both have to add the same thing before they can start. Split, merge, or sequence them so no two agents in the same stage collide.
5. Present the stages to the user as a table (columns: Stage, Tasks, Waiting On).
6. Invoke the `ls-interactivity:interactive-edit` skill with the file so the user can adjust it, then read their changes back. Where that skill isn't available, post the file's contents in the conversation instead, wait for the user's reply, and update the file with their changes.

## Rationalizations

| Thought                                      | Reality                                                                     |
| -------------------------------------------- | --------------------------------------------------------------------------- |
| "I'll start the first stage while we talk"   | This skill only plans. Executing the stages is a separate step.             |
| "Everything looks independent, one stage"    | Check what they edit. Shared files are a dependency you missed.             |
| "I'll assign branches while I'm in here"     | Not this skill's call. The agent executing a task decides where work lands. |
| "Two tasks overlap, I'll let them race"      | Two agents editing one file is a conflict you chose. Sequence them.         |
| "The table is approved, the file can differ" | The file is what gets executed. Fix it, not just the table.                 |
Files in this package (2)
  • SKILL.md 2 KB
  • assets/parallelization.md 1 KB

Versions

The database has no other skills named parallelize.

Database snapshot: 13.11.2026 · package version 23c87c585643 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100teams
    Use this skill when the user asks to orchestrate a team, use multiple agents, or parallelize work across Claude Code sessions. Decomposes tasks, spawns teammates, and coordinates execution.
  • 100planning
    Plan multi-step AI agent work: decompose goals, sequence agents, define handoffs, and handle failure. Use when orchestrating agents through complex tasks that need structure before execution.
  • 100agent-orchestration
    Plans and runs work across several agents. Use whenever a request says split across agents, run in parallel, fan out, one agent per task, delegate, subagents, or merge their findings, before spawning any agent. Covers briefs, isolation, merging, and when not to parallelize.
  • 90fk-parallel
    Run several fast-kernel agents at once on one campaign - in-session engineers in private worktrees whose proposals are measured serially by `fast-kernel inbox`, or headless workers (`fast-kernel auto --agents N`). Use for "use multiple agents", "parallelize the search", "run 3 engineers".
  • 100claude-code-agent-teams
    This skill should be used when the user asks to "create an agent team", "run a multi-agent team", "coordinate multiple Claude sessions", "use agent teams", or wants to parallelize work across multiple Claude Code instances.
  • 100parallel-agent-work
    Decide whether to split work across subagents or agent teams, and run the split safely. Use when dispatching parallel agents, or when deciding whether to parallelize at all. Covers branch isolation, when not to split, and what a dispatched agent owes when it finishes.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.