Skip to content
Back to skills

Shoal Orchestration

ASecurity

Full shoal orchestration workflow - interaction-shape routing, Plan and approval gates, dispatch brakes, named-role delegation, security separation, verification, recovery, outcome continuation, review intent, decision checkpoints, and blocked-task isolation. Load before deciding delegation, review, or approval for large, architectural, risky, or cross-surface work.

  • 2 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added October 13, 2026
ai-agentssecurity

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned November 11, 2026

npx -y skills add miyago9267/shoal --skill shoal-orchestration --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Shoal Orchestration?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Shoal Orchestration
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/miyago9267-shoal-orchestration/badge)](https://www.skillsdirectory.com/skills/miyago9267-shoal-orchestration)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: shoal-orchestration
description: Full shoal orchestration workflow - interaction-shape routing, Plan and approval gates, dispatch brakes, named-role delegation, security separation, verification, recovery, outcome continuation, review intent, decision checkpoints, and blocked-task isolation. Load before deciding delegation, review, or approval for large, architectural, risky, or cross-surface work.
---
<!-- shoal-claude v3.13.6-beta -->

# Shoal orchestration

This Skill is the detailed procedure behind the always-on shoal bootstrap.
The bootstrap stays authoritative for its invariants; this Skill supplies the
complete contract.

## First move

1. Classify the interaction shape: `co_discover`, `explore_then_plan`, `fan_out`, or
   `execute` (see the policy's routing section).
2. Set `execution_scope`, `review_intent`, and the discovery budget from the
   policy extensions.
3. Apply risk triggers before size, then the phase gate and dispatch brake
   before every Agent call.

An `executor` brief names its file/module bound; work larger than that is split into several executors or routed to `applier`.
## References

Read only the part needed for the current decision:

- [orchestration-policy.md](references/orchestration-policy.md): routing,
  lifecycle gates, dispatch and ownership, severity, recovery, AUTO/ASK,
  parallel and runtime mechanics.
- [workflow-extensions.md](references/workflow-extensions.md): outcome-level
  continuation, turn-scoped review intent, discovery budget, decision
  checkpoint through `AskUserQuestion`, task ledger and blocked-task
  isolation, continuation across user input, review-service circuit breaker,
  and verifier direction checkpoint.

If a reference is unavailable, keep the bootstrap invariants, work fail-soft,
and do not claim full shoal verification.

Files in this skill

  • SKILL.md1.6 KB
  • references/orchestration-policy.md18.6 KB
  • references/workflow-extensions.md9.1 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.