orchestration

协同编排知识域。多Agent协同、任务分解、并行执行、冲突解决。当魔尊需要多Agent协作、任务编排、并行处理时使用。

Quality

65%

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

Fix and improve this skill with Tessl

tessl review fix ./templates/skills/domains/orchestration/SKILL.md

Quality

Content

61%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 admirably lean and gestures at concrete tooling, but it is a stub: its single deep-dive reference is a broken link, and the orchestration workflow is never spelled out with validation steps for parallel writes. The skill currently points at knowledge it does not actually ship.

Suggestions

Ship the referenced multi-agent.md (or inline its content) so the sole reference link resolves — as written, the skill promises coverage it cannot deliver.

Enumerate the orchestration loop as explicit numbered steps (spawn → assign → send_input → wait → close) with a validation checkpoint after parallel writes, e.g., verifying each file's changes before closing agents.

Add one concrete spawn_agent/send_input usage example showing how task decomposition and the per-file write lock are actually applied.

Dimension	Reasoning	Score
Conciseness	The body is a lean topic table, a short use-case list, and three bullet points with no padding or explanation of concepts Claude already knows — every token earns its place. It clearly matches the 'lean and efficient' anchor rather than 4, which tolerates trimmable over-explanation.	5 / 5
Actionability	Concrete elements exist — named tool APIs ("spawn_agent/send_input/wait/close_agent") and role assignments ("explorer", "worker", "awaiter") plus one concrete rule ("每个文件同一时刻仅允许一个 Agent 写入") — but there are no usage examples, parameter details, or concrete steps. This fits 'some concrete guidance but incomplete' rather than 4, whose guidance is mostly executable, and exceeds 2, which lacks any specific hooks.	3 / 5
Workflow Clarity	A rough sequence is implied by the tool loop ("spawn_agent/send_input/wait/close_agent 形成闭环") and the lock-before-parallel rule acts as a checkpoint, but the steps are never enumerated as a workflow and there are no validation/feedback checkpoints for parallel write operations. That matches 'steps present but checkpoints missing/implicit', not 4, which requires most checkpoints to be explicit.	3 / 5
Progressive Disclosure	The body's only content reference, [multi-agent.md](multi-agent.md), does not exist in the bundle (no references/ directory and no multi-agent.md anywhere), so the promised '角色定义、任务分解、通信协议、冲突解决、状态共享' material is unreachable and navigation is broken. This fits 'minimal structure / references buried or broken' rather than 3, where references at least resolve.	2 / 5
	Total	13 / 20 Passed

Description

70%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 compact bilingual-appropriate description that answers both what and when with explicit trigger keywords. Its main weaknesses are the abstractness of the stated capabilities and the trigger clause being framed around a persona name rather than natural user phrasing.

Suggestions

Replace abstract capability nouns with concrete operations (e.g., '分解任务为子任务并通过 spawn_agent 并行执行') to lift specificity.

Reframe the trigger clause around the user's natural phrasing (e.g., '当用户要求多Agent协作、任务分解或并行处理时使用') and add common synonyms.

Dimension	Reasoning	Score
Specificity	The description names the domain ("协同编排知识域") and lists capability areas ("多Agent协同、任务分解、并行执行、冲突解决"), which sits at the 'names domain and 1-2 concrete actions' level rather than 4 because these are abstract capability nouns, not concrete operations like the anchor examples. It is above score 2 since it goes beyond a bare domain label with a specific enumerated list.	3 / 5
Completeness	Both 'what' ("多Agent协同、任务分解、并行执行、冲突解决") and an explicit 'when' ("当魔尊需要多Agent协作、任务编排、并行处理时使用") are present. Not 5 because the 'when' clause is less concrete than the anchor's trigger-phrase style and the 'what' remains a list of abstract nouns; not 3 because both halves are explicitly stated.	4 / 5
Trigger Term Quality	Good keyword coverage with natural phrases users would say: "多Agent协作", "任务编排", "并行处理", "任务分解". Not 5 because common variations/synonyms (e.g., English terms, "并行开发", "多智能体") are missing, and the trigger clause is anchored to a persona name ("魔尊") rather than user phrasing.	4 / 5
Distinctiveness Conflict Risk	Multi-agent orchestration/task decomposition is a distinct niche with its own triggers, so conflict risk is low. Not 5 because the domain borders on general task-management/agent-tooling skills where mild overlap is possible.	4 / 5
	Total	15 / 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: fengshao1227/ccg-workflow
Path: templates/skills/domains/orchestration/SKILL.md
Commit: f349e3d

Reviewed: 5 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.