lark-task

飞书任务：管理任务、清单和任务智能体。创建待办任务、查看和更新任务状态、拆分子任务、组织任务清单、分配协作成员、上传任务附件、注册或注销任务智能体、更新任务智能体的主页数据、写入智能体任务记录。当用户需要创建待办事项、查看任务列表、跟踪任务进度、管理项目清单或给他人分配任务、为任务上传附件文件、注册注销任务智能体、更新智能体主页数据、写入任务记录时使用。

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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 body is a well-structured, highly actionable overview that delegates shortcut detail to one-level-deep references and provides validated multi-step workflows for capability discovery and task modification. Its main weakness is repetition across the search-tip blockquotes, which inflates token cost without adding new guidance.

Suggestions

Consolidate the three overlapping search-guidance blockquotes (任务搜索技巧, 任务清单搜索技巧, 意图区分补充) into a single rule about 'specified search skill vs. query keyword vs. range-only conditions', then give compact task/tasklist examples once each, to cut repetition.

Add one inline copy-paste example for the most common shortcut (e.g. +create minimal flags) so the highest-frequency action does not require opening a reference file.

Move the long permission table into a separate reference file (e.g. references/permissions.md) and keep only a pointer, reducing the overview's token footprint while preserving the detail.

Dimension	Reasoning	Score
Conciseness	Most content is high-value domain knowledge Claude would not know (API quirks, disambiguation, constraints), but the search-guidance blockquotes restate the same 'distinguish specified-search-skill vs. query-keyword' logic three times (tasks, tasklists, and the 补充 restatement), which could be tightened into one rule plus examples.	3 / 5
Actionability	Provides concrete executable commands throughout ('lark-cli task --help', 'lark-cli schema task.tasklists.tasks', 'lark-cli task tasklists tasks --params "{...}" --as user') and a linked shortcut table; minor gap is that per-shortcut flag usage lives in the reference files rather than inline, which is appropriate but leaves a few common cases one hop away.	4 / 5
Workflow Clarity	The 命令选择与渐进式发现 workflow is a clear 5-step sequence with explicit validation checkpoints and a feedback loop ('遇到 unknown_subcommand 时必须停止...回到第 2 步'), and the 从任务清单定位并修改任务的最短路径 gives another sequenced, validated path with a禁止客户端编号 guardrail.	5 / 5
Progressive Disclosure	SKILL.md is an overview with a shortcut table linking to 18 one-level-deep reference files (all verified present in ./references/), plus cleanly separated API Resources and 权限表 sections; references are clearly signaled via markdown links and content is appropriately split.	5 / 5
	Total	17 / 20 Passed

Description

88%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 strong: it concisely states a comprehensive set of concrete capabilities and pairs them with an explicit 'use when...' trigger clause. It is mostly distinct from sibling skills, with only minor overlap risk on the overloaded term '待办'.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — '创建待办任务、查看和更新任务状态、拆分子任务、组织任务清单、分配协作成员、上传任务附件、注册或注销任务智能体、更新任务智能体的主页数据、写入智能体任务记录' — giving comprehensive coverage rather than generic verbs.	5 / 5
Completeness	Explicitly answers both what ('飞书任务：管理任务、清单和任务智能体...') and when ('当用户需要...时使用') with concrete trigger phrases, matching the anchor for a complete what+when statement.	5 / 5
Trigger Term Quality	Natural trigger phrases like '创建待办事项、查看任务列表、跟踪任务进度、管理项目清单、给他人分配任务' map well to what users say, with synonyms (待办/任务); a few natural variations are missing and no file extensions apply to this domain, so it stops just short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	Names a clear niche ('飞书任务', '任务清单', '任务中心') that is largely distinct from other Feishu skills, but the bare term '待办/todo' creates minor overlap risk with the related lark-meeting minutes+todo skill, which the body — not the description — must disambiguate.	4 / 5
	Total	18 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 suspicious	Warning

	Total	12 / 16 Passed

Repository: larksuite/cli
Path: skills/lark-task/SKILL.md
Commit: ceace6d

Reviewed: 4 hours 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.