Skills parallel-task
📦

parallel-task

Content revision r2 Safe ⚙️ External commands

Execute Development Plans in Parallel

Large development plans are slow and difficult to coordinate across dependent tasks. This skill schedules subagents in dependency-aware waves, validates their work, commits changes, and updates plan logs.

Supports: Claude Codex Code(CC)
🥉 78 Bronze

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "parallel-task" from https://skillstore.io/skills/am-will-parallel-task.md and its manifest at https://skillstore.io/api/skills/am-will-parallel-task/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/am-will-parallel-task.md Signed manifest GET /api/skills/am-will-parallel-task/manifest Signed lockfile GET /api/skills/am-will-parallel-task/lockfile

Test it

Using "parallel-task". Execute the complete authentication plan.

Expected outcome:

  • Wave 1 completed: T1 added failing authentication tests, implemented the change, and recorded passing results.
  • Wave 2 completed: T2 and T3 ran in parallel after T1.
  • All task commits remain local, and the plan log contains completion evidence.

Using "parallel-task". Run tasks T3 and T7 from the user profile plan, including prerequisites.

Expected outcome:

T3 completed with RED-to-GREEN evidence and a local commit. T7 remains blocked because its required dependency is incomplete.

Using "parallel-task". Run a documentation task that cannot use automated tests.

Expected outcome:

The task recorded reason_not_testable and defined a static documentation check. The check passed, the task was committed locally, and the plan log was updated.

Security Audit

Safe
v5 • 7/23/2026 Open versioned report

All ten static findings are false positives caused by Markdown inline-code markers or fenced blocks in SKILL.md. The reviewed skill contains orchestration instructions but no Ruby, shell, or other executable command invocation.

1
Files scanned
159
Lines analyzed
0
Review items
0
False positives ignored

Risk Factors

⚙️ External commands (10)
SKILL.md:23 SKILL.md:26 SKILL.md:41-66 SKILL.md:66-70 SKILL.md:70 SKILL.md:80-96 SKILL.md:96-123 SKILL.md:123-128 SKILL.md:128-132 SKILL.md:132-158
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
Audited by: codex View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/am-will-parallel-task/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/am-will-parallel-task/security.svg)](https://skillstore.io/skills/am-will-parallel-task?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/am-will-parallel-task?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/am-will-parallel-task/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/am-will-parallel-task.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

am-will. (2026). parallel-task security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/am-will-parallel-task/audits/5

BibTeX citation

@techreport{am-will-am-will-parallel-task-2026, author = {am-will}, title = {parallel-task security audit report (audit version 5)}, institution = {Skillstore}, year = {2026}, number = {5}, url = {https://skillstore.io/skills/am-will-parallel-task/audits/5}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "parallel-task security audit report (audit version 5)" version: "unspecified" type: report authors: - name: "am-will" date-released: "2026-07-23" url: "https://skillstore.io/skills/am-will-parallel-task/audits/5" identifiers: - type: other value: "skillstore:am-will-parallel-task:audit:5" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
85
Maintainability
87
Content
69
Community
83
Spec Compliance

What You Can Build

Dependency-Aware Feature Delivery

Run a multi-task feature plan while preserving prerequisite order and parallelizing independent implementation work.

Parallel Refactor Coordination

Coordinate separate refactor tasks, local commits, validation evidence, and plan updates across several subagents.

Auditable TDD Execution

Require failing tests, passing results, or documented alternative checks before each planned task is completed.

Try These Prompts

Run a Complete Plan 
/parallel-task [plan-file]. Execute every task, honor dependencies, validate each result, commit task changes locally, and update the plan log.
Run Selected Tasks 
/parallel-task [plan-file] [task-ids]. Run only these tasks and required dependencies, then report completed, blocked, and deferred work.
Enforce TDD Evidence 
/parallel-task [plan-file]. Require failing tests before implementation, passing tests afterward, and documented alternative checks for tasks that cannot use TDD.
Coordinate a Complex Delivery 
/parallel-task [plan-file] [task-ids]. Build dependency waves, run unblocked work in parallel, retry incomplete tasks, and summarize commits, evidence, and blockers.

Best Practices

  • Use task IDs and explicit depends_on lists so the skill can build accurate execution waves.
  • Give every task concrete acceptance criteria and exact validation steps.
  • Review local commits and plan logs before integrating or pushing changes.

Avoid

  • Do not invoke the skill without a structured plan file.
  • Do not run tightly coupled tasks in parallel when dependencies are missing.
  • Do not treat a task as complete without test evidence or a documented alternative check.

Frequently Asked Questions

What plan format does this skill expect?
It expects Markdown task sections with task IDs, dependency lists, descriptions, acceptance criteria, and validation steps.
Can I execute only selected tasks?
Yes. Provide task IDs, and the skill includes their required dependencies.
Does the skill run every task in parallel?
No. It runs only unblocked tasks in parallel and waits for dependencies before starting later waves.
Does every task require automated tests?
The skill defaults to TDD. Unsuitable tasks need a reason and an exact alternative verification method.
Does the skill push commits to a remote repository?
No. It creates local task commits and explicitly prohibits pushing them.
What happens when a task fails?
The skill requests a retry or escalation, records the blocker, and delays dependent work.

Developer Details

Author

am-will

License

MIT

Skillstore revision

r2

Version notice

The author did not declare a version.

Repository

https://github.com/am-will/codex-skills/tree/main/skills/parallel-task/

Ref

31bc7611b504c197d3e993aef7943461c871616f

Maintenance freshness

7/26/2026

Usage

8 downloads · 104 views

File structure

📄 SKILL.md

More from am-will

View all

Related Skills

View all