CtrlK
BlogDocsLog inGet started
Tessl Logo

summarize

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

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/summarize/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

The content is lean, well-structured, and gives executable commands for the common cases, but it depends on a to-markdown.mjs wrapper script that is not present in any bundle directory.

Suggestions

Ship the referenced to-markdown.mjs wrapper in ./scripts/ (or remove references to it) so the documented commands actually work.

Briefly note what the pi tool is and how it is invoked, or replace it with a self-contained summarization command.

Tighten the repeated mention of the temp-file Hint behavior to a single statement to improve token efficiency.

DimensionReasoningScore

Conciseness

The body is efficient and does not over-explain concepts Claude already knows, with only minor redundant restating of the temp-file Hint behavior that could be trimmed.

4 / 5

Actionability

Provides concrete, copy-paste-ready commands (uvx --from 'markitdown[pdf]' markitdown, node to-markdown.mjs --summary --prompt), but references to-markdown.mjs (not present in any bundle dir) and the unexplained pi tool leave minor gaps.

4 / 5

Workflow Clarity

The summarize path is laid out as a clear numbered 3-step sequence; this is not a destructive/batch operation so the missing validation cap does not apply, though no error-recovery feedback loops are given.

4 / 5

Progressive Disclosure

Sections are well-organized (When to use, Quick usage, Convert, Convert+summarize) and the skill is under 50 lines, but it references to-markdown.mjs which does not exist in the bundle, a broken one-level reference.

4 / 5

Total

16

/

20

Passed

Description

66%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 specific and names a concrete tool and file types, but it omits an explicit 'Use when...' trigger clause, which caps completeness and weakens when-to-use guidance.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers (e.g. 'Use when converting PDFs, DOCX, HTML pages, or URLs to Markdown, or when summarizing a long document').

Include explicit file extensions and common synonyms (e.g. .pdf, webpages, slides) to broaden trigger-term coverage.

Make the summarize capability less vague than 'optionally it can summarize' by stating what kind of summary it produces.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('Fetch a URL or convert a local file (PDF/DOCX/HTML/etc.) into Markdown', 'optionally it can summarize') backed by a specific tool (uvx markitdown), with only minor gaps in coverage.

4 / 5

Completeness

Has a clear 'what' (fetch/convert to Markdown) but no explicit 'Use when...' trigger clause, so per the rubric guideline completeness is capped at 3 with 'when' only weakly implied.

3 / 5

Trigger Term Quality

Includes natural terms users would say (URL, PDF/DOCX/HTML, Markdown, summarize) with file-type coverage, though a few common synonyms/explicit extensions are missing.

4 / 5

Distinctiveness Conflict Risk

The specific tool (uvx markitdown) and concrete niche (document-to-Markdown conversion) make it mostly distinct from other skills with only minor overlap risk.

4 / 5

Total

15

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mitsuhiko/agent-stuff
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.