CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

vault-artifact-toolchain

Use when the user wants agent-friendly vault artifacts or source ingest with text-first tools: Mermaid .mmd diagrams rendered with mmdc, Marp Markdown decks compiled to PDF/PPTX, Obsidian Excalidraw Markdown sketches, notebooklm-py summaries, yt-dlp talk metadata/captions, markitdown document conversion, or Makefile targets that wrap these workflows.

Quality

84%

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

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 body is an efficiently written, well-structured policy layer with explicit preflight and verification checkpoints. Its main gap is actionability: it names the tools and the rules of engagement but never provides the actual render, compile, or download commands an agent would run.

Suggestions

Add one copy-paste-ready command per tool (e.g., mmdc -i diagram.mmd -o diagram.png, marp deck.md --pdf --pptx, markitdown file.pdf) in each Tool Defaults section.

Add an explicit feedback loop in Verification for failed renders/compiles: inspect the error, fix the source, and re-run the command before regenerating dependent outputs.

Consider moving per-tool command details and flag references into short one-level-deep reference files (e.g., references/mermaid.md) to keep the overview tight while restoring executable depth.

DimensionReasoningScore

Conciseness

The body is uniformly lean bullets with no concept explanations or padding ('Store editable diagrams as .mmd files', 'Verify required tools with command -v'), assuming Claude's competence at every step.

5 / 5

Actionability

Policy guidance is concrete but the core execution details are missing: no mmdc render command, no marp compile command, no yt-dlp or markitdown invocations appear anywhere, so only the preflight and check commands are actually executable.

3 / 5

Workflow Clarity

'Before You Start' sequences a 5-step preflight and 'Verification' supplies explicit checkpoints ('Do not claim an artifact was regenerated unless the render or compile command succeeded', 'make check'), but there is no explicit validate-fix-retry loop to reach the top anchor.

4 / 5

Progressive Disclosure

Sections are well-organized with no nested references and no bundle files, but at ~75 lines across six tools the per-tool command details that belong in one-level-deep reference files are simply omitted rather than split out.

4 / 5

Total

16

/

20

Passed

Description

88%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.

A strong description that explicitly states both what the skill does and when to use it, with concrete tool names, actions, and file extensions throughout. Its main weaknesses are missing common synonyms (slides, presentation, transcript) and mild overlap risk on the more generic tools like markitdown and yt-dlp.

Suggestions

Add natural synonyms such as 'slide decks/presentations', 'slides', and 'transcripts' to the trigger phrasing so users' everyday wording matches.

Sharpen the 'when' clause with user-facing outcomes (e.g., 'when the user wants a diagram, deck, or sketch they can regenerate from text source') to reduce reliance on internal jargon like 'vault artifacts' and 'text-first tools'.

DimensionReasoningScore

Specificity

Enumerates concrete actions across the whole toolchain — 'Mermaid .mmd diagrams rendered with mmdc', 'Marp Markdown decks compiled to PDF/PPTX', 'notebooklm-py summaries', 'yt-dlp talk metadata/captions', 'markitdown document conversion' — matching the comprehensive-coverage anchor rather than the minor-gaps level below.

5 / 5

Completeness

Opens with an explicit 'Use when the user wants...' trigger clause and pairs it with an explicit, concrete what-list covering every wrapped tool, which fits the both-what-and-when anchor with concrete triggers.

5 / 5

Trigger Term Quality

Good natural keyword coverage including file extensions ('.mmd', 'PDF/PPTX', 'captions', 'Makefile'), but common user phrasings like 'presentation', 'slides', and 'transcript' are absent, so it falls short of the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

The combined niche of these text-first CLIs plus vault artifacts is clearly distinct, but individual items like 'markitdown document conversion', 'yt-dlp', and 'Makefile targets' carry minor overlap risk with generic document-conversion, video, and build skills.

4 / 5

Total

18

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

saski/arnesto

Path

.agents/skills/vault-artifact-toolchain/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.