summarizer

Use when the user asks for a summary, TL;DR, or condensed version of any content.

Quality

76%

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 ./agentscope-examples/documentation/src/main/resources/skills/summarizer/SKILL.md

Quality

Content

85%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.

An appropriately minimal body for a simple skill: perfectly lean, clear, and unambiguous about its single task. The only weakness is actionability — the guidance would be materially stronger with one worked example of the expected output and brief handling of edge cases like very long or structured content.

Suggestions

Include one short worked example (input snippet and the 3-5 bullet output) so the expected output shape is unambiguous.

Add one line for edge cases, e.g. how to handle very long documents (chunk-then-merge) or structured content like tables and dialogue.

Dimension	Reasoning	Score
Conciseness	Two lean sentences with zero padding and no explanation of concepts Claude already knows. Every token earns its place — a direct match for the anchor-5 example.	5 / 5
Actionability	'Summarize the given content into 3-5 bullet points. Focus on key takeaways.' gives a concrete output format and focus directive, but there is no example of expected output and no guidance for edge cases (very long content, structured data, dialogue). This is 'some concrete guidance but incomplete' — anchor 3 — rather than the mostly-executable guidance of anchor 4.	3 / 5
Workflow Clarity	This is a simple single-purpose skill and the single action is unambiguous: produce 3-5 bullets of key takeaways. Per the rubric's simple-skill exception, workflow clarity scores 5 without a multi-step workflow.	5 / 5
Progressive Disclosure	The skill is under 50 lines, needs no external references, and none are referenced (no bundle files exist in references/, scripts/, or assets/). The heading-plus-instruction structure is well-organized, satisfying the simple-skill exception for a score of 5.	5 / 5
	Total	18 / 20 Passed

Description

56%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 well-formed trigger clause with natural synonyms, but the description is only a 'when' sentence — it never states what the skill actually does. Adding a concrete capability statement (e.g., 'Condenses any content into 3-5 key bullet points. Use when...') would raise both specificity and completeness.

Suggestions

Add an explicit capability statement before the trigger clause, e.g. 'Condenses any text or document into 3-5 bullet points highlighting key takeaways. Use when the user asks for a summary, TL;DR, or condensed version.'

Broaden trigger coverage with natural variations such as 'recap', 'shorten this', or 'summarize this article/email/thread' to catch phrasings the current description misses.

Narrow 'any content' or name typical content types (articles, emails, transcripts, documents) to reduce overlap with research and analysis skills.

Dimension	Reasoning	Score
Specificity	The description names the summarization domain ('summary, TL;DR, or condensed version') but states no concrete capability actions — the only verb appears in the trigger clause. This matches 'names the domain but actions are minimal or generic', and is below anchor 3 which requires 1-2 explicitly stated actions.	2 / 5
Completeness	The 'when' is explicit and well-formed ('Use when the user asks for...'), but the 'what' is never stated as a capability — it can only be inferred from the trigger nouns, and the rubric says to score only what is explicitly stated. This sits between anchor 2 (only 'when' present without 'what') and anchor 3 (clear 'what' with weak 'when'), with more informational content than the anchor-2 example 'Use when working with documents'.	3 / 5
Trigger Term Quality	'asks for a summary, TL;DR, or condensed version' covers the main natural synonyms users would actually say for this task. It falls short of anchor 5 because common variations like 'recap', 'summarize this', or format-specific triggers are absent.	4 / 5
Distinctiveness Conflict Risk	The triggers 'summary, TL;DR, condensed version' form a recognizable niche distinct from most skills. However, 'any content' is broad and 'summary' is an extremely common request that could overlap with research or analysis skills, so it is not the clear niche of anchor 5.	4 / 5
	Total	13 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: agentscope-ai/agentscope-java
Path: agentscope-examples/documentation/src/main/resources/skills/summarizer/SKILL.md
Commit: 9e43ed8

Reviewed: 2 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.