summarize

Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).

2.63x

Quality

80%

Does it follow best practices?

Impact

87%

2.63x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./nanobot/skills/summarize/SKILL.md

Quality

Content

68%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.

A compact, well-structured CLI skill sheet with executable commands and a good flag reference. It scores lower on workflow clarity because the transcript-handling flow lacks explicit validation/decision checkpoints for large outputs, and minor conciseness/organization gains remain.

Suggestions

Add an explicit decision/checkpoint for huge transcripts (e.g. 'If transcript exceeds N chars, summarize first and confirm the section/time range before expanding') to give the workflow a validation gate.

Move the full provider key-alias list and flag semantics into a short references/ file, keeping SKILL.md to the most-used flags.

Drop the repeated default-model note (it appears in both Quick start and Model + keys) and tighten the 'YouTube: summary vs transcript' explanation.

Dimension	Reasoning	Score
Conciseness	Lean and mostly efficient — flag tables and quick-start commands are scannable — though the 'YouTube: summary vs transcript' and 'Model + keys' sections could be trimmed slightly and the default-model note repeated.	4 / 5
Actionability	Provides concrete, executable commands (e.g. `summarize "https://youtu.be/..." --youtube auto --extract-only`) and a full flag reference, with only minor gaps such as not showing a podcast or local-file transcript example.	4 / 5
Workflow Clarity	Sequencing for the transcript-vs-summary flow is implicit ('return a tight summary first, then ask which section/time range to expand') and there are no validation checkpoints for batch/multi-step extraction; the skill is simple but lacks explicit verify steps for potentially large/huge outputs.	3 / 5
Progressive Disclosure	Well-organized sections with clear headers and a one-level reference to the optional `~/.summarize/config.json`; no bundle files exist so structure stays appropriately flat, though a couple of inline details (full flag semantics, provider key aliases) could live in a reference file.	4 / 5
	Total	15 / 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.

A strong, concise description that pairs a clear 'what' with concrete trigger phrases and natural synonyms, closely matching the rubric's good examples. It loses only a little on specificity and distinctiveness because 'summarize' is a broadly-used term.

Dimension	Reasoning	Score
Specificity	Names the domain (URLs, podcasts, local files, transcripts) and concrete actions ('Summarize or extract text/transcripts'), covering several specific capabilities with minor gaps (e.g. no mention of meeting notes or translation).	4 / 5
Completeness	Explicitly answers 'what' ('Summarize or extract text/transcripts from URLs, podcasts, and local files') and 'when' via the parenthetical trigger guidance ('great fallback for "transcribe this YouTube/video"'), giving both with concrete triggers.	5 / 5
Trigger Term Quality	Embeds natural trigger phrases users would say — 'summarize this URL/article', 'transcribe this YouTube/video', 'what's this link/video about?' — with synonyms (URL, article, video, link, podcast).	5 / 5
Distinctiveness Conflict Risk	The summarize.sh CLI niche is fairly distinct and its YouTube/transcript framing differentiates it from generic summarizers, but 'summarize' is a broad term with some overlap risk against other text/summarization 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
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	13 / 16 Passed

Repository: HKUDS/nanobot
Path: nanobot/skills/summarize/SKILL.md
Commit: c27b1f1

Reviewed: about 18 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.