Tessl • The management layer for AI agent skills

The body is an exemplar of a lean, single-purpose CLI skill: executable quick-start commands, complete flag and environment-variable references, and a clear transcript-vs-summary workflow with a sensible checkpoint for oversized transcripts. Sections are well organized with no padding and no unnecessary external references. No changes needed.

Dimension	Reasoning	Score
Conciseness	Every section carries information Claude could not know (CLI flags, env vars, config path) with zero conceptual padding — 'Useful flags', 'Model + keys', and 'Config' are pure reference. It matches the 'lean and efficient; every token earns its place' anchor, and there is nothing to trim that would justify 4.	5 / 5
Actionability	The Quick start gives three copy-paste-ready commands covering the main cases (URL, local PDF, YouTube), plus an executable transcript command and concrete flags with enumerated values. Guidance is fully executable and covers the common cases, matching the level-5 anchor.	5 / 5
Workflow Clarity	This is a simple single-purpose skill where the single action (run `summarize <target> [flags]`) is unambiguous, which the guidelines allow to score 5. It also includes a decision checkpoint for the large-transcript case ('return a tight summary first, then ask which section/time range to expand'), and no destructive or batch operations apply.	5 / 5
Progressive Disclosure	There are no bundle files (no references/, scripts/, or assets/), and the body is a short, well-organized single-file overview for a simple CLI wrapper — nothing that belongs in a separate file is inlined. Per the guidelines, a short skill with no need for external references and well-organized sections scores 5.	5 / 5
	Total	20 / 20 Passed

Description

61%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 concise and concrete, clearly stating what the tool does across specific source types with good natural trigger terms. Its main weakness is the missing explicit 'when to use' clause, which caps completeness and keeps trigger guidance only implied. Adding a 'Use when...' sentence would lift it into the top tier.

Suggestions

Append an explicit trigger clause, e.g., 'Use when the user asks to summarize a URL, article, YouTube video, or podcast, or to extract a transcript from a video.'

Broaden natural trigger synonyms (e.g., 'transcribe', 'article', 'links', '.pdf') to improve trigger term coverage and distinctiveness.

Mention one or two more concrete capabilities (e.g., machine-readable JSON output, length control) to raise specificity from two actions to several.

Dimension	Reasoning	Score
Specificity	The description names its domain ("URLs, YouTube videos, podcasts, and local files") and two concrete actions ("Summarize or extract text and transcripts"), matching the anchor for naming the domain with 1-2 concrete actions but not comprehensive coverage. It does not reach 4 because there are only two verb phrases, fewer than the 'several specific actions' the level-4 anchor requires.	3 / 5
Completeness	The 'what' is clear ("Summarize or extract text and transcripts from URLs, YouTube videos, podcasts, and local files"), but there is no 'Use when...' clause or equivalent explicit trigger guidance; the 'when' is only weakly implied by the source list. Per the judging guidelines, a missing 'Use when' clause caps completeness at 3, and it does not reach 4 because the 'when' is not stated at all, not merely under-specified.	3 / 5
Trigger Term Quality	Natural user terms are well covered: "summarize", "text", "transcripts", "URLs", "YouTube videos", "podcasts", "local files" — phrases a user would plausibly say. It falls short of 5 because common synonyms and variations are missing (e.g., "article", "transcribe", ".pdf", "links").	4 / 5
Distinctiveness Conflict Risk	The combination of transcripts, YouTube videos, and podcasts carves out a mostly distinct niche with low trigger ambiguity relative to general summarization skills. Minor overlap risk remains with any generic 'summarize this text/article' skill, keeping it below the clear-niche level 5.	4 / 5
	Total	14 / 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
Revision: 9adbcc2

Reviewed: 3 days ago

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.

summarize

Table of Contents

Is this your skill?