summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
82
Quality
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 effectively communicates core capabilities and includes good natural trigger terms, especially the YouTube/video fallback note. However, it lacks an explicit 'Use when...' clause and could be more specific about what distinguishes it from general summarization or text extraction skills.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to transcribe, summarize, or extract content from web pages, audio files, podcasts, or video URLs.'
Clarify the scope to improve distinctiveness, e.g., specify supported formats (.mp3, .wav) or platforms (YouTube, Spotify podcasts) to reduce overlap with generic text extraction skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names domain (URLs, podcasts, local files) and some actions (summarize, extract text/transcripts), but lacks comprehensive detail about specific capabilities like format handling or output options. | 2 / 3 |
Completeness | Clearly answers 'what' (summarize/extract from various sources) but lacks an explicit 'Use when...' clause. The parenthetical hint about YouTube/video is helpful but doesn't constitute explicit trigger guidance. | 2 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'summarize', 'extract text', 'transcripts', 'URLs', 'podcasts', 'YouTube', 'video', 'transcribe'. The parenthetical note adds valuable trigger terms. | 3 / 3 |
Distinctiveness Conflict Risk | Somewhat specific to transcription/summarization of media content, but 'summarize' and 'extract text' could overlap with general text processing or document skills. The YouTube/video mention helps but scope is still broad. | 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 skill that efficiently documents a CLI tool with concrete, executable examples. The content is appropriately concise and assumes Claude's competence. Minor improvement could be made to the workflow around handling large YouTube transcripts, which is mentioned but not fully sequenced.
Suggestions
Add explicit steps for the large transcript workflow: 1) attempt extraction, 2) if >X chars, summarize first, 3) ask user for section/time range, 4) re-extract with range
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient - no unnecessary explanations of what summarization is or how CLIs work. Every section delivers actionable information without padding. | 3 / 3 |
Actionability | Provides copy-paste ready commands for all common use cases. Concrete examples with real flags, environment variable names, and config file format are all executable. | 3 / 3 |
Workflow Clarity | For a simple CLI wrapper this is mostly clear, but the YouTube transcript workflow could benefit from explicit steps for handling the 'huge transcript' scenario mentioned. The trigger phrases section is helpful but the decision flow between summary vs transcript isn't fully sequenced. | 2 / 3 |
Progressive Disclosure | Well-organized with clear sections progressing from quick start to specific use cases to configuration. For a simple CLI skill under 50 lines, the structure is appropriate without needing external file references. | 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
50ef2f3
- 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.