orchestration-protocols

Coordinate multiple agents: parallel spawning, health monitoring, circuit breakers, escalation. Use for parallel agents, agent timeouts, fan-out tasks, multi-agent delegation.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable and well-sequenced with explicit validation checkpoints for batch agent operations. Its main weakness is progressive disclosure: it relies on a ./REFERENCE.md link that resolves to no file, leaving referenced detail stranded.

Suggestions

Add the missing ./REFERENCE.md (containing health thresholds, escalation path, Error Recovery Playbook, and Circuit Breaker details) or remove the dangling link so the offloaded content is actually reachable.

Verify every relative path in the body against the bundle before shipping — the single reference being broken undermines the one-level-deep disclosure structure the section headers otherwise support.

Consider moving the Validation & Verification Checkpoints table into REFERENCE.md to keep SKILL.md a lean overview, consistent with how Health & Recovery detail is already offloaded.

Dimension	Reasoning	Score
Conciseness	The body is table- and template-driven and assumes Claude's competence (no padding about what agents are), but a few prose passages like the steering quote and CLI commentary could be trimmed, matching anchor 4 rather than the every-token-earns-its-place anchor 5.	4 / 5
Actionability	It provides copy-paste-ready CLI commands ("opencastle convoy run --file convoy.yml --dry-run", "tail -n 50 .opencastle/logs/events.ndjson \| jq …"), a concrete research prompt template, and verification commands covering the common spawn/monitor/verify cases, matching anchor 5.	5 / 5
Workflow Clarity	Multi-step processes are explicitly sequenced with checkpoints — the Result Merge Protocol is a numbered 1–6 list with two "Checkpoint" gates, and the Validation & Verification Checkpoints table adds feedback/blocker recovery — satisfying anchor 5 and the batch-operation validation requirement.	5 / 5
Progressive Disclosure	Sections are clearly organized, but the only external reference — "see [REFERENCE.md](./REFERENCE.md)" — points to a file that does not exist in the bundle, so the offloaded health/circuit-breaker detail is unreachable; a clearly-signaled but broken reference lands at anchor 3 rather than 4.	3 / 5
	Total	17 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, concrete description that pairs a clear capability statement with an explicit "Use for…" trigger clause. It is specific and well-triggered, with only minor synonym/overlap gaps keeping it just below the top anchor on two dimensions.

Dimension	Reasoning	Score
Specificity	Names the domain (multi-agent coordination) and four concrete actions — "parallel spawning, health monitoring, circuit breakers, escalation" — which is several specific actions with only minor coverage gaps, matching the anchor 4 rather than the fully comprehensive anchor 5.	4 / 5
Completeness	It explicitly answers both "what" ("Coordinate multiple agents: parallel spawning, health monitoring, circuit breakers, escalation") and "when" ("Use for parallel agents, agent timeouts, fan-out tasks, multi-agent delegation") with concrete trigger phrases, matching anchor 5 exactly.	5 / 5
Trigger Term Quality	Natural trigger phrases include "parallel agents, agent timeouts, fan-out tasks, multi-agent delegation" — good keyword coverage a user would actually say, but missing some synonyms (e.g. "concurrent agents", "distributed agents") that anchor 5 requires.	4 / 5
Distinctiveness Conflict Risk	The multi-agent orchestration niche is clear with distinct triggers (fan-out tasks, multi-agent delegation), but terms like "parallel agents" carry minor overlap risk with general parallelism skills, placing it at anchor 4 rather than the minimal-conflict anchor 5.	4 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: monkilabs/opencastle
Path: src/orchestrator/skills/orchestration-protocols/SKILL.md
Commit: f297837

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.