summarize

Fetch a URL or convert a local file (PDF/DOCX/HTML/etc.) into Markdown using `uvx markitdown`, optionally it can summarize

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

70%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-organized with clear, mostly executable commands and a clean summarize workflow, but it leans on a `to-markdown.mjs` wrapper that is not bundled and carries minor verbosity. Providing or removing the missing script dependency would most improve it.

Suggestions

Bundle `to-markdown.mjs` in a `scripts/` directory (or replace the `node to-markdown.mjs` examples with the underlying `uvx`/`pi` commands) so all examples are executable as written.

Trim the introductory "Turn 'things' ..." sentence and condense the Tip paragraph to the essential behavior (always writes a temp .md and prints its path).

Clarify the `pi --model claude-haiku-4-5` invocation in step 3 with a concrete example command so the summarize path is fully copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and command-driven, but the opening "Turn 'things' ... into Markdown so they can be inspected/quoted/processed like normal text" and the verbose Tip explanation include mild padding that could be trimmed.	2 / 3
Actionability	The primary `uvx --from 'markitdown[pdf]' markitdown <url-or-path>` command is executable, but several examples rely on `node to-markdown.mjs`, a wrapper script that is not present in any scripts/ bundle, so the guidance is incomplete rather than fully copy-paste ready.	2 / 3
Workflow Clarity	The convert path is a single unambiguous action and the summarize path is laid out as a clear numbered 1-2-3 sequence; no validation checkpoints are needed since this is non-destructive conversion.	3 / 3
Progressive Disclosure	Content is organized into clear sections (When to use, Quick usage, Convert + summarize) with no nested references and no bundle files to navigate; for a small single-file skill this is well-structured.	3 / 3
	Total	10 / 12 Passed

Description

75%

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 specific and uses natural trigger terms, but it omits any explicit "when to use" guidance, which limits its completeness and distinctiveness. Adding a Use-when clause would raise both.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user wants to turn a URL or a PDF/DOCX/HTML file into Markdown, or wants a quick summary of a long document."

Add common keyword variations ("web page", "Word", "PowerPoint", ".pdf") to broaden natural trigger coverage.

Tighten the trailing "optionally it can summarize" into a parallel action ("and optionally summarize the result") for cleaner third-person voice.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Fetch a URL", "convert a local file (PDF/DOCX/HTML/etc.) into Markdown", and "optionally it can summarize" — matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	It clearly answers "what" (fetch/convert to Markdown, optionally summarize) but has no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Covers natural terms users would say — "URL", "PDF", "DOCX", "HTML", "Markdown", "summarize" — giving good coverage of common input-type keywords.	3 / 3
Distinctiveness Conflict Risk	The markitdown/Markdown-conversion niche is somewhat specific, but "convert a local file into Markdown" could still overlap with other document-processing skills, so it is not a fully distinct niche.	2 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mitsuhiko/agent-stuff
Path: skills/summarize/SKILL.md
Commit: d265b8e

Reviewed: 5 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.