lark-okr

飞书 OKR：管理目标与关键结果。查看和编辑 OKR 周期、目标、关键结果、对齐关系、量化指标和进展记录。当用户需要查看或创建 OKR、管理目标和关键结果、查看对齐关系时使用。不负责：待办任务管理（lark-task）、日程/会议安排（lark-calendar）、绩效评估

Quality

83%

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

80%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 operational overview: actionable CLI examples, clear decision routing, and one-level-deep references that all exist. Its main weakness is the absence of explicit validation/retry feedback loops for destructive and batch operations, which caps workflow clarity.

Suggestions

Add explicit verify-then-retry checkpoints for destructive and batch operations — e.g. after +batch-create, list the created objectives to confirm; before +progress-delete, +progress-get to confirm the target — to lift workflow clarity above 3.

For +reorder and +weight, add a one-line validation note: fetch current KRs first and confirm all IDs are included (reorder) or weights sum to 1 (weight) before submitting, since the body already warns these fail param validation.

Consolidate the score-vs-progress guidance into a single section to remove the duplicated explanation in the '快速决策' table and the standalone paragraph after the examples.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational — decision tables, ready-to-run CLI examples, terse routing rules — with only minor over-explanation such as the score-vs-progress distinction restated across two adjacent sections.	4 / 5
Actionability	It provides copy-paste-ready, fully-parameterized `lark-cli` commands (e.g. `+cycle-list --user-id "ou_xxx" --as user`, `+batch-create --input '[...]'`) with concrete flag values and example payloads covering the common cases.	5 / 5
Workflow Clarity	The '快速决策' table sequences the main view/create flows and includes an error-recovery loop for categories ('invalid parameters' → list categories → retry), but destructive and batch operations (batch-create, progress-delete marked 不可恢复, reorder, weight) lack explicit verify-then-retry checkpoints, triggering the rubric's cap at 3.	3 / 5
Progressive Disclosure	All 18 referenced paths under references/ resolve to real files, are one level deep, consistently linked, and clearly signaled via decision tables, a Shortcut table, and '操作指南' callouts — SKILL.md is a lean overview pointing to detailed per-operation references.	5 / 5
	Total	17 / 20 Passed

Description

87%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, trigger-rich, and clearly bounds its scope with both positive triggers and negative-boundary routing to sibling skills. It cleanly answers what it does and when to invoke it.

Dimension	Reasoning	Score
Specificity	The description enumerates the concrete OKR entity types it manages ('周期、目标、关键结果、对齐关系、量化指标和进展记录') with view/edit actions, giving broad entity coverage, though the action vocabulary stays at the 查看/编辑 level rather than naming individual operations.	4 / 5
Completeness	It explicitly answers 'what' (manage OKR cycles, objectives, KRs, alignments, indicators, progress) and 'when' ('当用户需要查看或创建 OKR...时使用') with concrete trigger phrases, plus a '不负责' exclusion clause bounding scope.	5 / 5
Trigger Term Quality	It covers the main natural triggers ('查看或创建 OKR、管理目标和关键结果、查看对齐关系') plus the domain term OKR, but omits natural terms for progress (进展) and indicators (指标) that the body treats as first-class features.	4 / 5
Distinctiveness Conflict Risk	The explicit '不负责' clause routing 待办→lark-task, 日程→lark-calendar, 绩效→lark-openapi-explorer establishes a clear niche with minimal conflict risk against sibling skills.	5 / 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: 4 suspicious	Warning

	Total	12 / 16 Passed

Repository: larksuite/cli
Path: skills/lark-okr/SKILL.md
Commit: 6646386

Reviewed: ~20 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.