CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

document-authoring

Create, inspect and deliver charts, PDFs, Word documents and spreadsheets, and open animated browser presentations.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/agent/document-authoring/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%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 highly actionable, well-sequenced workflow with explicit validation checkpoints and fix-and-retry feedback loops, grounded in exact tool names and parameters. Its main weaknesses are the monolithic Presentations paragraph, which should be split into a reference file and deduplicated against steps 4–5, and the absence of any literal example calls.

Suggestions

Move the Presentations guidance (animation, inspect/check flow, present server, exports) into a references/presentations.md file and keep a concise routing bullet inline pointing to it, e.g. "Presentations: use document.slidev.create; see PRESENTATIONS.md for animation, check, present and export details."

Break the remaining format bullets into sub-bullets and deduplicate verification guidance between the Presentations bullet and steps 4–5 so each rule appears once.

Include one concrete example per major format (a minimal echarts.render options JSON or a minimal slides.md skeleton) to make the guidance copy-paste ready and lift actionability to 5.

DimensionReasoningScore

Conciseness

Almost every clause is actionable rather than explanatory, but the Presentations bullet is a ~1,800-character run-on paragraph ("Treat the scaffold as editable... omit that archive unless requested") mixing authoring, animation, verification, presenting and export policy, and verification requirements are repeated between the bullet and steps 4–5. Mostly efficient, but more than minor tightening is needed, so it sits below anchor 4.

3 / 5

Actionability

Concrete tool names and parameters appear throughout ("document.echarts.render", "document.typst.compile", "format=docx", "require scope=full, complete=true and ok=true", "content.sections[].images with caption and altText"), with concrete success criteria. It falls short of anchor 5 because no literal call examples or code snippets are given — argument structures must be inferred from the tools' own schemas.

4 / 5

Workflow Clarity

A clear numbered 1–6 sequence (establish criteria → choose tool → author → inspect → reconcile/fix → attach) with explicit validation gates ("Run `inspect`, then `check`", "Render PDF pages with `readPdf` and compare layout with supplied references") and fix-and-retry feedback loops ("fix missing content or layout defects before delivery", "A provider's success response alone is not a quality check"). This matches anchor 5's explicit validation, feedback loops and checklist-like coverage.

5 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/ or assets/), so all guidance is inline; the ~1.8KB Presentations sub-workflow (animation, checks, present server, exports, ZIP handling) clearly belongs in a separate reference file with a one-line pointer. The per-format routing and numbered steps give some structure, but content that should be separate is inline, matching anchor 3.

3 / 5

Total

15

/

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 clearly states what the skill does across five specific output formats using natural trigger terms, in third-person style without padding. Its main gap is the complete absence of "use when" guidance, which caps completeness, plus missing synonyms and file extensions that would sharpen triggering.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to create, convert or deliver charts, PDFs, Word documents, spreadsheets, or slide presentations."

Add common synonyms and file extensions to the trigger terms: .pdf, .docx, .xlsx, Excel, PowerPoint, slides, decks.

Replace generic verbs ("inspect and deliver") with per-format concrete actions (e.g. "compile Typst sources to PDF", "render editable DOCX") to sharpen specificity.

DimensionReasoningScore

Specificity

"Create, inspect and deliver charts, PDFs, Word documents and spreadsheets, and open animated browser presentations" lists several actions across five named output formats, exceeding anchor 3's 1–2 concrete actions. It does not reach anchor 5 because the verbs remain generic ("inspect and deliver") with no per-format concrete actions like "fill forms" or "merge documents".

4 / 5

Completeness

The "what" is clearly answered (create, inspect and deliver documents in the listed formats, open animated presentations), but there is no "Use when..." clause or any equivalent explicit trigger guidance, which the judging guidelines state should cap completeness at 3.

3 / 5

Trigger Term Quality

Natural user terms are present across all formats — "charts", "PDFs", "Word documents", "spreadsheets", "presentations" — giving good coverage well beyond anchor 3's single keyword. It falls short of anchor 5 because common synonyms and file extensions are missing (.pdf, .docx, .xlsx, Excel, PowerPoint, slides, decks).

4 / 5

Distinctiveness Conflict Risk

The enumerated formats make it mostly distinct as the document-authoring suite, but spanning charts, PDFs, Word documents, spreadsheets and presentations creates minor overlap risk with closely related format-specific skills (e.g., a dedicated chart or presentation skill). It is clearly more specific than anchor 3's "Works with document files" but not a minimal-conflict niche.

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

leon-ai/leon

Path

skills/agent/document-authoring/SKILL.md

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.