summarize-pro

When user asks to summarize text, articles, documents, meetings, emails, YouTube transcripts, books, PDFs, reports, conversations, or any long content. Also handles bullet points, key takeaways, action items, TL;DR, ELI5, executive summaries, chapter summaries, comparison summaries, translation summaries, thread summaries, and custom-length summaries. 20-feature AI summarizer with multiple formats, languages, and export options. All processing happens locally — NO external API calls, NO network requests, NO data sent to any server.

Quality

68%

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 ./configs/microservice/bff-service/configs/agent-skills/clawhub/summarize-pro/SKILL.md

Quality

Content

46%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 content is highly actionable with concrete templates, paths, and JSON schemas, but it is markedly verbose and monolithic — 20 features, duplicated command lists, and gamification fluff are all inlined in one file with no reference split. Workflow validation is implicit rather than checkpointed.

Suggestions

Move the 20 format templates and gamification achievements into reference files (e.g., FORMATS.md, ACHIEVEMENTS.md) and have SKILL.md point to them, cutting the inline token load.

Remove the duplicated 'Updated Commands' section — it repeats 'When To Activate'; keep one consolidated trigger/command list.

Add an explicit validation checkpoint in the save/auto-trim workflow (e.g., verify word counts and back up history.json before trimming) instead of relying on implicit rules.

Dimension	Reasoning	Score
Conciseness	A 670-line body inlines 20 feature templates with repeated emoji/box boilerplate, duplicates trigger lists across 'When To Activate' and 'Updated Commands', and adds gamification achievements that pad tokens without aiding execution.	2 / 5
Actionability	Concrete file paths (~/.openclaw/summarize-pro/), JSON schemas for settings/history/saved, and exact per-feature output templates give mostly executable guidance, though templates use placeholders rather than worked input→output examples.	4 / 5
Workflow Clarity	Setup is sequenced and error/corruption handling is mentioned, but the core summarize→save→auto-trim workflow relies on implicit rules ('Never fabricate', 'Back up before any destructive operation') rather than explicit checkpoints, and the destructive auto-trim lacks a verify step.	3 / 5
Progressive Disclosure	A monolithic 670-line file inlines all 20 format templates, command references, and achievement lists that belong in separate reference files; no external references or navigation exist despite the size.	2 / 5
	Total	11 / 20 Passed

Description

91%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 explicitly covers both what the skill does and when to trigger it, with comprehensive natural trigger terms and synonyms. The main weakness is that all enumerated capabilities are variations of a single 'summarize' action rather than distinct operations.

Dimension	Reasoning	Score
Specificity	Lists many concrete capabilities — 'action items', 'ELI5', 'comparison summaries', 'translation summaries', 'thread summaries', 'custom-length summaries' — but they are all variants of the single 'summarize' action rather than distinct operations, so it sits just below the comprehensive multi-action anchor.	4 / 5
Completeness	Explicitly answers both what ('20-feature AI summarizer with multiple formats, languages, and export options') and when ('When user asks to summarize text, articles, documents, meetings, emails...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including synonyms ('summarize'/'summary', 'TL;DR') and phrases users actually say — 'eli5', 'key takeaways', 'action items', 'executive summary', 'chapter summary' — across the summarization domain.	5 / 5
Distinctiveness Conflict Risk	The summarization niche is mostly distinct, but terms like 'eli5', 'compare', and 'action items' carry minor overlap risk with explanation, comparison, and task-management skills.	4 / 5
	Total	18 / 20 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 (679 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: UnicomAI/wanwu
Path: configs/microservice/bff-service/configs/agent-skills/clawhub/summarize-pro/SKILL.md
Commit: 99df6e4

Reviewed: 9 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.