Skills orchestration
📦

orchestration

Content revision r1 Safe ⚙️ External commands

Coordinate Orca Agent Workflows

Multi-agent coding tasks can lose ownership, status, and completion signals. This skill guides Claude, Codex, and Claude Code through Orca orchestration commands for supervised dispatch, gates, and worker completion.

Supports: Claude Codex Code(CC)
🥉 77 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 "orchestration" from https://skillstore.io/skills/stablyai-orchestration.md and its manifest at https://skillstore.io/api/skills/stablyai-orchestration/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.

Test it

Using "orchestration". Use Orca orchestration to have a worker review a branch and report findings.

Expected outcome:

The coordinator creates a tracked review task, dispatches a worker, waits for completion, and summarizes confirmed findings and open questions.

Using "orchestration". Coordinate two workers, then ask before applying risky fixes.

Expected outcome:

The workflow separates review and fix ownership, collects worker results, opens a decision gate, and waits for approval before continuing.

Using "orchestration". Hand this project to another agent without supervision.

Expected outcome:

The skill directs the agent to use a full handoff path and stop monitoring after prompt delivery.

Security Audit

Safe
v2 • 7/6/2026 Open versioned report

The static findings are false positives caused by Markdown backticks and documented Orca CLI examples in SKILL.md. I found no prompt injection attempt, malware intent, data exfiltration behavior, or hidden executable code in the reviewed skill file.

1
Files scanned
242
Lines analyzed
0
Review items
0
False positives ignored
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/stablyai-orchestration/audits/2?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/stablyai-orchestration/security.svg)](https://skillstore.io/skills/stablyai-orchestration?utm_source=security_passport_badge)

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/stablyai-orchestration.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

stablyai. (2026). orchestration security audit report (audit version 2) [Author version unspecified]. Skillstore. https://skillstore.io/skills/stablyai-orchestration/audits/2

BibTeX citation

@techreport{stablyai-stablyai-orchestration-2026, author = {stablyai}, title = {orchestration security audit report (audit version 2)}, institution = {Skillstore}, year = {2026}, number = {2}, url = {https://skillstore.io/skills/stablyai-orchestration/audits/2}, 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: "orchestration security audit report (audit version 2)" version: "unspecified" type: report authors: - name: "stablyai" date-released: "2026-07-06" url: "https://skillstore.io/skills/stablyai-orchestration/audits/2" identifiers: - type: other value: "skillstore:stablyai-orchestration:audit:2" description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score
stablyai Recommended Current

stablyai-orchestration

Skillstore Score 77
Evidence Confidence High
Skillstore usage 5
Updated

2026-08-21

consiliency-orchestration

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 5
Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
85
Maintainability
87
Content
65
Community
83
Spec Compliance

What You Can Build

Supervise Parallel Coding Tasks

Create tracked tasks, dispatch workers, wait for worker_done messages, and summarize results without losing ownership.

Run Decision-Gated Workflows

Use gates when a coordinator or user decision must happen before downstream tasks continue.

Separate Handoffs From Supervision

Choose full handoff flows when another agent owns the work, and orchestration only when active supervision is required.

Try These Prompts

Start One Supervised Worker
Use Orca orchestration to create one worker for this task: [task]. Wait for worker_done and summarize the result.
Coordinate Review And Fixes
Use Orca orchestration to dispatch a review worker and a fix worker. Ask me before any scope changes.
Manage A Decision Gate
Use Orca orchestration for this multi-step plan. Create a decision gate before merging outputs or assigning follow-up work.
Run A Parallel DAG
Use Orca orchestration to decompose this project into dependent tasks. Dispatch ready tasks in waves, handle escalations, and report final results.

Best Practices

  • Use orchestration only when the user wants supervision, monitoring, results, gates, or a task DAG.
  • Verify task and dispatch state before claiming work was orchestrated.
  • Keep worker ownership clear, especially when review results require follow-up fixes.

Avoid

  • Using orchestration for a full ownership handoff without user supervision requirements.
  • Monitoring a handoff worker after prompt delivery when the user did not ask for supervision.
  • Sending dispatch lifecycle messages to groups instead of the concrete coordinator handle.

Frequently Asked Questions

What does this skill coordinate?
It coordinates Orca tasks, dispatches, messages, worker completion, gates, and supervised multi-agent workflows.
When should I use it?
Use it when you need active supervision, worker completion tracking, decision gates, or a task DAG.
When should I avoid it?
Avoid it for full handoffs where another agent owns the work and no monitoring is requested.
Does it require Orca?
Yes. It requires a running Orca runtime, the Orca CLI, and the orchestration feature.
Does it work with Claude, Codex, and Claude Code?
Yes. The skill is documented for Claude, Codex, and Claude Code workflows inside Orca.
Can it run commands by itself?
No. It provides orchestration guidance. The agent still runs commands according to user intent and environment policy.

Developer Details

Author

stablyai

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Ref

e82d22ace449afa2495e5c931b687eb19f360093

Maintenance freshness

7/18/2026

Usage

2 downloads · 0 views

File structure

📄 SKILL.md