CtrlK
BlogDocsLog inGet started
Tessl Logo

document-converter

Use for reading, analyzing, summarizing, and converting complex documents into Markdown artifacts or other supported document formats.

61

Quality

71%

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 ./backend/super-magic/agents/skills/document-converter/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

The skill is highly actionable with executable examples and clearly sequenced workflows, but its length is inflated by repeated helpers and rules, and the entire tool reference plus examples live inline in SKILL.md with no progressive disclosure to bundle files.

Suggestions

Factor the repeated document_output_dir helper and the output-directory naming rule into a single shared snippet or a referenced file instead of reproducing them in every example.

Add an explicit validate→fix→retry feedback loop for the batch-conversion workflow (e.g., on a failed export, record the error, retry once, then mark the row failed) to lift workflow_clarity past the batch cap.

Move the per-tool API reference (the Tools section) and/or the full code examples into references/ files, leaving SKILL.md as a concise overview with clearly signaled one-level-deep links.

DimensionReasoningScore

Conciseness

The body is dense operational guidance Claude would not already know, but the document_output_dir helper is reproduced in full three times and the office-like-documents list and extension-naming rule are repeated across sections, so it is mostly efficient but could be tightened rather than earning 'every token earns its place'.

2 / 3

Actionability

It provides fully executable run_sdk_snippet examples with real tool.call invocations, concrete parameters, and result.ok error checks, plus per-tool parameter lists that are copy-paste ready.

3 / 3

Workflow Clarity

Sequences are clearly numbered (Default Approach, summary steps, reuse-artifact decision flow) with result.ok checks, but the batch-conversion flow records errors without a validate→fix→retry feedback loop, and the rubric caps batch/destructive workflows at 2 when such loops are missing.

2 / 3

Progressive Disclosure

No bundle files exist and the ~490-line body keeps the full Tools API reference and all code examples inline in one file; sections are well-organized, but content that should be split into referenced files is inline, so it sits at the 'could be better organized' anchor rather than the under-50-line exception at 3.

2 / 3

Total

9

/

12

Passed

Description

77%

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 cleanly states what the skill does and when to use it with an explicit trigger clause, but it relies on generic verbs and omits the concrete file-format terms (PDF, docx, pptx, xlsx) that would sharpen both trigger matching and distinctiveness.

Suggestions

Add the concrete file formats users mention (PDF, Word, PowerPoint, Excel, .docx, .pptx, .xlsx) so the trigger matches natural phrasing like 'convert this PDF to Markdown'.

Sharpen the verbs beyond generic 'reading/analyzing' (e.g., 'extract text and tables, build chunk indexes, render pages to images') to reduce overlap with general summarization skills.

Tighten the 'when' clause to call out the large/complex-document and batch-conversion scenarios that are the skill's true niche.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ("reading, analyzing, summarizing, and converting") with explicit output targets ("Markdown artifacts or other supported document formats"), matching the multi-action anchor rather than the single-action anchor at 2.

3 / 3

Completeness

The "Use for ..." clause is an explicit trigger answering when, and the action list plus output formats answer what, so it satisfies both halves and is not capped at 2.

3 / 3

Trigger Term Quality

Uses natural terms ("documents", "Markdown", "summarize", "convert") but omits the file-format keywords users would actually say (PDF, Word, docx, pptx, xlsx), so it has relevant keywords while missing common variations.

2 / 3

Distinctiveness Conflict Risk

The Markdown-artifact and supported-document-format niche is specific, but the broad verbs ("reading, analyzing, summarizing") could overlap with general document-reading or summarization skills, so it is not clearly conflict-free.

2 / 3

Total

10

/

12

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
dtyq/magic
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.