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

88%

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

92%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.

An exemplarily lean and actionable skill body with explicit checkpoints and feedback loops for risky parallel operations. Its one real defect is that the deferred REFERENCE.md bundle file is missing, which both breaks navigation and strands the health/recovery/circuit-breaker content.

Suggestions

Add the referenced REFERENCE.md (health thresholds, escalation path, Error Recovery Playbook, Circuit Breaker) to the bundle, or inline the essential thresholds into SKILL.md if the detail is small.

If REFERENCE.md cannot be shipped, remove or rewrite the "Health & Recovery Reference" section so it does not point readers at a nonexistent file.

Consider moving the copy-paste verification commands from the CLI section into the Validation & Verification table so all checks live in one navigable place.

Dimension	Reasoning	Score
Conciseness	The body is dense and lean: signal/action tables, a redirect example, prompt templates, and compaction templates with no filler or explanation of concepts Claude already knows. Even the note that there is no plain-text log to tail is load-bearing guidance, so every token earns its place.	5 / 5
Actionability	Guidance is copy-paste ready: concrete CLI commands with flags ("opencastle convoy run --file convoy.yml --dry-run", "opencastle convoy --json \| jq -e '.failed == 0'", the events.ndjson tail pipeline) plus filled-in prompt and compaction templates. Not 4: no gaps between instruction and execution for the common cases.	5 / 5
Workflow Clarity	Multi-step processes are explicitly sequenced with validation checkpoints and feedback loops: the Result Merge Protocol checkpoints ("verify every researcher returned a result... re-run failures", "confirm synthesized block covers every original question") and the full Validation & Verification table (pre-spawn, during-run, pre-merge, dead letters, post-merge, blocker) cover this batch/parallel-operation skill appropriately.	5 / 5
Progressive Disclosure	The overview structure is good and the "Health & Recovery Reference" section correctly defers detail to a separate file, but the referenced ./REFERENCE.md does not exist in the bundle (no references/ directory), so navigation to the health-threshold, escalation, and circuit-breaker content fails. Not 4: a dangling reference is more than a minor organization gap; not 2: the in-body structure and signaling are otherwise sound.	3 / 5
	Total	18 / 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 description that clearly and concisely states both capabilities and explicit trigger conditions in third person. Minor gains available from adding natural trigger synonyms and tightening distinctiveness against adjacent delegation-focused skills.

Dimension	Reasoning	Score
Specificity	"Coordinate multiple agents: parallel spawning, health monitoring, circuit breakers, escalation" names the domain and several concrete actions. Not 5 because coverage of orchestration capabilities is not comprehensive (no result merging, retries, or load concerns); not 3 because it lists more than 1-2 actions.	4 / 5
Completeness	Explicitly answers "what" (coordinate multiple agents via 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. Not 4 because the "when" clause is explicit rather than weakly implied.	5 / 5
Trigger Term Quality	"Use for parallel agents, agent timeouts, fan-out tasks, multi-agent delegation" provides good natural keyword coverage. Not 5 because common variations like "subagents", "spawn agents", "run agents in background", or "agent failures" are missing.	4 / 5
Distinctiveness Conflict Risk	The multi-agent orchestration niche with terms like "circuit breakers" and "fan-out" is mostly distinct. Not 5 because generic phrasing like "parallel agents" and "multi-agent delegation" could overlap with general delegation or background-agent skills.	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: c0f4566

Reviewed: 1 day 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.