complex-task

长程/复杂任务编排工作指导。接收复杂任务后，依次完成验收标准确认、计划拆分与自审、项目文件初始化、子任务文档创建、执行者-评估者 subagent 并行迭代、主 agent 巡检协调、聚合与整体评估，直至满足验收标准后交付。

Quality

72%

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 ./skills/complex-task/SKILL.md

Quality

Content

77%

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

The content is highly actionable with clear sequencing and strong validation feedback loops across its eight phases. Its main weaknesses are verbosity from duplicated anti-pattern content and a monolithic structure with no progressive disclosure via separate reference files.

Suggestions

Deduplicate the anti-pattern material — keep one canonical table (3-3 or the Anti-patterns section) and reference it from the other location.

Extract the reusable templates (PROJECT.md, tasks.json, task.md, acceptance.md) into reference files under references/ and link to them, enabling progressive disclosure.

Tighten the巡检 and status-update sections, which restate similar纪律 across multiple subsections.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient procedural guidance without explaining concepts Claude already knows, but at ~530 lines it carries redundancy — the anti-pattern table appears both in 3-3 and again in the Anti-patterns section, and templates repeat similar structure — so it could be tightened rather than earning the lean level-3 anchor.	2 / 3
Actionability	It provides concrete, copy-paste-ready templates (PROJECT.md, tasks.json, task.md, acceptance.md), explicit verdict formats, status-transition rules, and spawn constraints, matching the fully-executable level-3 anchor.	3 / 3
Workflow Clarity	The eight phases are clearly sequenced with explicit validation checkpoints — planning-reviewer GAN loop (Phase 3), evaluator verdict gates (Phase 5), and the independent overall-evaluator rework loop (Phase 7) — providing the feedback loops the level-3 anchor expects.	3 / 3
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) and the skill is a single monolithic ~530-line document; while sections are well-organized, content that could live in separate reference files (templates, anti-pattern catalogs) is inline, fitting the level-2 anchor.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 and occupies a distinct niche, but it lacks an explicit 'Use when' trigger clause and leans on internal process jargon over natural user-facing keywords. Adding an explicit trigger sentence would raise completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' sentence stating when to invoke this skill (e.g., long-running multi-phase tasks, multi-crew coordination).

Replace internal process terms with natural keywords a user would actually say, such as '复杂任务', '多阶段任务', '长程任务'.

Keep the concrete action list but front-load a one-line trigger so 'when to use' is unambiguous.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete orchestration actions ('验收标准确认、计划拆分与自审、项目文件初始化、子任务文档创建、执行者-评估者 subagent 并行迭代、主 agent 巡检协调、聚合与整体评估'), matching the level-3 anchor that lists several specific concrete actions.	3 / 3
Completeness	It clearly answers 'what' (the orchestration steps) but provides no explicit 'Use when...' trigger clause; per the judging guidelines, a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	It includes the relevant natural term '长程/复杂任务' a user might say, but the remaining vocabulary ('编排工作指导', '验收标准确认', '并行迭代') is process-jargon rather than natural user phrasing, and common trigger variations are absent.	2 / 3
Distinctiveness Conflict Risk	The niche — long-range complex-task orchestration with executor/evaluator subagent pairs — is distinct and unlikely to conflict with typical domain skills; not the 2-anchor because the scope is narrowly scoped rather than broadly overlapping.	3 / 3
	Total	10 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (535 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	13 / 16 Passed

Repository: TeamWiseFlow/xiaobei
Path: skills/complex-task/SKILL.md
Commit: bcef823

Reviewed: 3 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.