lark-demo

Demo skill

Quality

23%

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

Fix and improve this skill with Tessl

tessl review fix ./internal/qualitygate/skillscan/testdata/skills/lark-demo/SKILL.md

Quality

Content

47%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 terse, mostly-concrete set of lark-cli command examples but lacks any structure, sequencing, validation, or context. Placeholder values and a dummy 'npx other-tool' line reduce executability and clarity.

Suggestions

Add a brief header and one-line purpose so Claude knows when to run these commands, and remove the placeholder '# comment' and 'npx other-tool' lines.

Replace placeholder values ('oc_xxx', 'A3Ijdemo') with guidance on where to obtain them, or mark them explicitly as values to substitute.

If these commands form a sequence, number the steps and add a verification step (e.g. checking the fetched doc or the returned message list) so the workflow has a checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is a lean code block with no padding or over-explanation, but it carries wasted placeholder tokens ('# comment' and 'npx other-tool') that do not earn their place, keeping it just below a 5.	4 / 5
Actionability	It shows concrete lark-cli commands with real flags, but key values are placeholders ('oc_xxx', 'A3Ijdemo'), one line is a dummy ('npx other-tool'), and there is no explanation of what the commands do or how to fill in the values.	3 / 5
Workflow Clarity	The commands are not sequenced into a workflow and there is no validation or checkpoints for the CLI operations, matching the 'rough/no sequence, validation absent' anchor rather than a fully incoherent one.	2 / 5
Progressive Disclosure	The body is a single unstructured code block with no section headers, no prose framing, and no references — minimal structure rather than the well-organized sections a simple skill needs to score higher.	2 / 5
	Total	11 / 20 Passed

Description

0%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 a bare placeholder ('Demo skill') that conveys no capability, trigger, or purpose. It fails every dimension by providing essentially no information.

Suggestions

Replace 'Demo skill' with a concrete statement of what the skill does, e.g. 'Fetch Lark docs and list IM messages via lark-cli'.

Add an explicit 'Use when...' clause naming natural trigger phrases users would say (e.g. 'Use when the user asks to fetch Lark docs or list Lark IM messages').

Include domain-specific keywords (Lark, lark-cli, docs, IM messages, container-id) so the skill is distinguishable from unrelated skills.

Dimension	Reasoning	Score
Specificity	The description is literally 'Demo skill', which names no concrete action or domain — pure abstract placeholder language matching the 'entirely vague' anchor.	1 / 5
Completeness	Both 'what it does' and 'when to use it' are missing — the text is an extremely vague placeholder, so it sits at the lowest anchor.	1 / 5
Trigger Term Quality	'Demo skill' contains no natural keywords a user would actually say when they need this skill; it is entirely generic placeholder text.	1 / 5
Distinctiveness Conflict Risk	'Demo skill' is entirely generic and would overlap with virtually any other skill, offering no niche or distinct trigger.	1 / 5
	Total	4 / 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
description_field	'description' is very short (10 chars), consider making it more detailed	Warning

	Total	15 / 16 Passed

Repository: larksuite/cli
Path: internal/qualitygate/skillscan/testdata/skills/lark-demo/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.