CtrlK
BlogDocsLog inGet started
Tessl Logo

orchestration-protocols

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

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 content is lean, highly actionable, and excels at sequenced workflows with validation checkpoints and feedback loops. Its main weakness is progressive disclosure: the body references a REFERENCE.md that is not present in the bundle, breaking navigation to the delegated Health/Recovery material.

Suggestions

Add the missing ./REFERENCE.md (or a references/ bundle file) containing the Health thresholds, escalation path, Error Recovery Playbook, and Circuit Breaker content the body promises, so the one-level-deep reference resolves.

Tighten the CLI section by collapsing the redundant bare 'opencastle convoy' invocations into a single documented form, and trim the post-run verification block to the essential checks to push conciseness toward 5.

For actionability, convert remaining policy heuristics (e.g. 'Max 3-5 researchers', 'steer within first 5 min') into concrete decision rules or commands where possible to reduce guidance-only sections.

DimensionReasoningScore

Conciseness

The body is dense and mostly lean — tables, tight bullets, no over-explanation of concepts Claude already knows — but a few spots could be trimmed (repeated bare 'opencastle convoy' invocations, the somewhat long post-run verification block), fitting score 4 rather than a flawless 5.

4 / 5

Actionability

Provides copy-paste-ready bash and jq verification commands, a prompt template, a compaction template, and a concrete redirect example with real file paths, but some sections are policy heuristics ('Max 3-5 researchers', 'steer within first 5 min') rather than executable code, leaving minor gaps relative to score 5.

4 / 5

Workflow Clarity

Multi-step processes are explicitly sequenced with validation checkpoints — the numbered Result Merge Protocol has two Checkpoint steps, the Validation & Verification Checkpoints table is a phase-by-phase checklist, and feedback loops (validate-fix-retry, re-run failures, block-merge-reopen) cover the batch and destructive operations, matching the score-5 anchor and avoiding the missing-validation cap.

5 / 5

Progressive Disclosure

Sectioning is well-organized with a clearly signaled one-level-deep reference ('see [REFERENCE.md](./REFERENCE.md)'), but that referenced file does not exist anywhere in the bundle, creating a navigation dead-end for promised Health/Circuit-Breaker/Error-Recovery content — a real organization defect beyond the 'minor gap' of score 4.

3 / 5

Total

16

/

20

Passed

Description

92%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.

The description is specific, complete, and distinctive, with an explicit 'Use for' trigger clause covering both what the skill does and when to invoke it. Trigger-term coverage is strong but not exhaustive of all synonyms.

DimensionReasoningScore

Specificity

Names the multi-agent domain and lists multiple concrete capabilities — 'parallel spawning, health monitoring, circuit breakers, escalation' — for comprehensive coverage, matching the score-5 anchor rather than the 1-2-action or minor-gap anchors.

5 / 5

Completeness

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'), matching the score-5 anchor with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural trigger terms ('parallel agents', 'agent timeouts', 'fan-out tasks', 'multi-agent delegation') give good coverage, but a few common synonyms (e.g. 'spawn agents', 'agent failures') are absent, fitting score 4 rather than the exhaustive 5.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — multi-agent orchestration with distinct triggers (fan-out, timeouts, circuit breakers) — giving minimal conflict risk with other skills, matching the score-5 anchor.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
monkilabs/opencastle
Reviewed

Table of Contents

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.