Parallel Task Executor

VerifiedCaution

Orchestrator for subagents to execute development plans in parallel with dependency management. Coordinates tasks in waves, validates completion, and updates plan documentation.

Sby Skills Guide Bot
DevelopmentAdvanced
3/4/2026
Claude Code
#parallel-agents#orchestration#task-dependencies#plan-execution#subagents

Recommended for

Automated summary

This skill acts as an orchestrator: it reads a markdown plan file, groups tasks into waves based on their dependencies, and delegates each unblocked task to a parallel subagent until the whole plan is complete and validated.

Strengths

  • Wave-based scheduling driven by each task's `depends_on` list, preventing work from starting before its prerequisites finish
  • A thorough subagent prompt template covering context, acceptance criteria, validation, plan-file logging, and an atomic commit
  • A validation checkpoint after every wave (inspect, verify, retry or escalate) before moving on
  • Supports running a task subset (T1 T2 T4) while automatically pulling in the required dependencies

Limitations

  • Only fires on an explicit `/parallel-task` command, never automatically
  • Assumes a strict plan format (`### T1:`, `- **depends_on**: [...]`); malformed plans break parsing
  • No real conflict handling between parallel agents beyond telling each one to stage only its own files, and pushing is forbidden entirely
When to use it

Use it when an existing development plan is already split into tasks with declared dependencies and should be executed in parallel by multiple subagents.

When not to use it

Avoid it for unstructured plans or tightly coupled tasks that cannot be implemented atomically and independently.

Security analysis

Caution
Quality score78/100

There is no obfuscation, no curl|sh, no credential or secret exfiltration, and no destructive filesystem commands. The risk is operational rather than malicious: the skill spawns parallel subagents that autonomously edit code, run validation, and make git commits, with only a weak 'NEVER PUSH' guardrail and an ambiguous instruction about committing 'to github'. That is a legitimate but powerful workflow deserving a caution rating and human oversight, not a risky one.

Findings
  • •Orchestrates autonomous subagents that edit files and create git commits without human review between waves
  • •Inconsistent git guidance: instructs agents to 'ensure that wave of work has been committed to github' while also saying 'NEVER PUSH' — ambiguous scope of repository operations
  • •No declared allowed-tools, yet the workflow implicitly requires file writes, shell/git execution, and subagent spawning
  • •Prompt template instructs agents to run validation/tests of unknown provenance and to modify arbitrary plan/files referenced by user input
How this analysis is made

Examples

Run a full plan
/parallel-task ./plans/auth-plan.md
Run selected tasks only
/parallel-task ./plans/auth-plan.md T1 T2 T4
Flag-based task selection
/parallel-task user-profile-plan.md --tasks T3 T7

name: parallel-task description: > Only to be triggered by explicit /parallel-task commands.

Parallel Task Executor

You are an Orchestrator for subagents. Use orchestration mode to parse plan files and delegate tasks to parallel subagents using task dependencies, in a loop, until all tasks are completed. Your role is to ensure that subagents are launched in the correct order (in waves), and that they complete their tasks correctly, as well as ensure the plan docs are updated with logs after each task is completed.

Process

Step 1: Parse Request

Extract from user request:

  1. Plan file: The markdown plan to read
  2. Task subset (optional): Specific task IDs to run

If no subset provided, run the full plan.

Step 2: Read & Parse Plan

  1. Find task subsections (e.g., ### T1: or ### Task 1.1:)
  2. For each task, extract:
    • Task ID and name
    • depends_on list (from - **depends_on**: [...])
    • Full content (description, location, acceptance criteria, validation)
  3. Build task list
  4. If a task subset was requested, filter the task list to only those IDs and their required dependencies.

Step 3: Launch Subagents

For each unblocked task, launch subagent with:

  • description: "Implement task [ID]: [name]"
  • prompt: Use template below

Launch all unblocked tasks in parallel. A task is unblocked if all IDs in its depends_on list are complete.

Task Prompt Template

You are implementing a specific task from a development plan.

## Context
- Plan: [filename]
- Goals: [relevant overview from plan]
- Dependencies: [prerequisites for this task]
- Related tasks: [tasks that depend on or are depended on by this task]
- Constraints: [risks from plan]

## Your Task
**Task [ID]: [Name]**

Location: [File paths]
Description: [Full description]

Acceptance Criteria:
[List from plan]

Validation:
[Tests or verification from plan]

## Instructions
1. Examine working plan and any relevant or dependent files
2. Implement changes for all acceptance criteria
3. Keep work **atomic and committable**
4. For each file: read first, edit carefully, preserve formatting
5. Run validation if feasible
6. **ALWAYS mark completed tasks IN THE *-plan.md file AS SOON AS YOU COMPLETE IT!** and update with:
    - Concise work log
    - Files modified/created
    - Errors or gotchas encountered
7. Commit your work
   - Note: There are other agents working in parallel to you, so only stage and commit the files you worked on. NEVER PUSH. ONLY COMMIT.
8. Double Check that you updated the *-plan.md file and committed your work before yielding
9. Return summary of:
   - Files modified/created
   - Changes made
   - How criteria are satisfied
   - Validation performed or deferred

## Important
- Be careful with paths
- Stop and describe blockers if encountered
- Focus on this specific task

Ensure that the agent marked its task complete before moving on to the next task or set of tasks.

Step 4: Check and Validate.

After a wave of subagents complete their work:

  1. Inspect their outputs for correctness and completeness.
  2. Validate the results against the expected outcomes.
  3. If the task is truly completed correctly, ENSURE THAT TASK WAS MARKED COMPLETE WITH LOGS.
  4. If a task was not successful, have the agent retry or escalate the issue.
  5. Ensure that that wave of work has been committed to github before moving on to the next wave of tasks.

Step 5: Repeat

  1. Review the plan again to see what new set of unblocked tasks are available.
  2. Continue launching unblocked tasks in parallel until plan is done.
  3. Repeat the process until all* tasks are both complete, validated, and working without errors.

Error Handling

  • Task subset not found: List available task IDs
  • Parse failure: Show what was tried, ask for clarification

Example Usage

/parallel-task plan.md
/parallel-task ./plans/auth-plan.md T1 T2 T4
/parallel-task user-profile-plan.md --tasks T3 T7

Execution Summary Template

# Execution Summary

## Tasks Assigned: [N]

### Completed
- Task [ID]: [Name] - [Brief summary]

### Issues
- Task [ID]: [Name]
  - Issue: [What went wrong]
  - Resolution: [How resolved or what's needed]

### Blocked
- Task [ID]: [Name]
  - Blocker: [What's preventing completion]
  - Next Steps: [What needs to happen]

## Overall Status
[Completion summary]

## Files Modified
[List of changed files]

## Next Steps
[Recommendations]

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/parallel-task-executor-mmbizkv2/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/parallel-task-executor-mmbizkv2' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/parallel-task-executor-mmbizkv2/download' --output '.skill-downloads/parallel-task-executor-mmbizkv2/SKILL.md.part' && mv '.skill-downloads/parallel-task-executor-mmbizkv2/SKILL.md.part' '.skill-downloads/parallel-task-executor-mmbizkv2/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/parallel-task-executor-mmbizkv2/SKILL.md' && test -s '.skill-downloads/parallel-task-executor-mmbizkv2/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/parallel-task' && cp -R '.skill-downloads/parallel-task-executor-mmbizkv2' '.claude/skills/parallel-task'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/parallel-task-executor-mmbizkv2'

openskills read 'parallel-task-executor-mmbizkv2'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/parallel-task-executor-mmbizkv2/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills