summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
82
76%
Does it follow best practices?
Impact
100%
3.44xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./openclaw/skills/summarize/SKILL.mdQuality
Discovery
64%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 has good trigger term coverage, especially with the parenthetical YouTube/video fallback note that captures common user language. However, it lacks an explicit 'Use when...' clause, which limits completeness, and the actions described (summarize, extract) are somewhat broad. Adding explicit trigger guidance and slightly more specific capability details would strengthen it.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to summarize a URL, transcribe a podcast or video, or extract text from a media file.'
Specify supported file types or formats more concretely (e.g., '.mp3, .mp4, YouTube links, web articles') to improve distinctiveness and reduce overlap with generic summarization skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names specific actions ('summarize', 'extract text/transcripts') and specific input types ('URLs, podcasts, local files'), but doesn't list comprehensive concrete actions beyond summarize/extract. | 2 / 3 |
Completeness | The 'what' is reasonably clear (summarize/extract text from URLs, podcasts, files), but there is no explicit 'Use when...' clause. The parenthetical hint about being a fallback for YouTube/video partially implies when, but doesn't constitute an explicit trigger guidance, capping this at 2. | 2 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'summarize', 'extract text', 'transcripts', 'URLs', 'podcasts', 'YouTube', 'video', 'transcribe'. The parenthetical fallback note adds excellent coverage of common user phrasing. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of summarization + transcription + URLs/podcasts/files is somewhat distinctive, but 'summarize' and 'extract text from URLs' could overlap with general web scraping or summarization skills. The YouTube/video fallback note helps but doesn't fully eliminate conflict risk. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted, concise skill that provides immediately actionable CLI commands with clear organization. Its main weakness is the lack of error handling or fallback guidance when commands fail, which is relevant given the 'best-effort' nature of YouTube transcript extraction and dependency on external API keys. Overall it's a strong skill that efficiently teaches Claude how to use the summarize CLI.
Suggestions
Add brief error handling guidance: what to do if the command fails (e.g., missing API key, blocked URL, empty YouTube transcript), especially since YouTube extraction is described as 'best-effort'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and purposeful. No unnecessary explanations of what URLs, PDFs, or YouTube are. The trigger phrases section is useful context for Claude, and flag/config sections are tightly formatted. | 3 / 3 |
Actionability | Provides fully executable bash commands for all common use cases, specific flag names with allowed values, exact environment variable names, and a concrete config file example. Copy-paste ready throughout. | 3 / 3 |
Workflow Clarity | The skill is relatively simple (single CLI tool), but the YouTube transcript workflow has a useful conditional ('if huge, summarize first then ask'), which is good. However, there's no validation/error handling guidance—e.g., what happens if the command fails, if a key is missing, or if YouTube extraction returns nothing. For a tool that's described as 'best-effort,' error recovery guidance would strengthen this. | 2 / 3 |
Progressive Disclosure | For a skill under 50 lines with a single CLI tool, the content is well-organized into logical sections (trigger phrases, quick start, YouTube specifics, model/keys, flags, config) with clear headers. No external references needed and none artificially created. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 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 |
Total | 8 / 11 Passed | |
- Repository
- trpc-group/trpc-agent-go
- Commit
af8bd5f
- Reviewed
Table of Contents
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.