CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

visualizations-config

Configure visualization location, style presets, and output preferences

Quality

70%

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 ./devflow-plugin/skills/visualizations-config/SKILL.md

The canonical home for this skill is visualizations-config in AndreJorgeLopes/devflow

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 a well-structured, actionable configuration workflow with concrete flags, file paths, and commands, and it respects the token budget. The main weaknesses are unhandled edge cases — no guidance for existing configs and no post-write verification — and underspecified outputs like the README style-guide content.

Suggestions

Specify how to handle an existing configuration in Step 1: whether to merge with preserved user keys, prompt before overwriting, or abort with a message pointing to --show.

Add a validation checkpoint after Step 3, e.g. re-read the written JSON to confirm it parses and display it to the user before creating folders.

Provide concrete content for the README and the devflow preset (e.g. a short style-guide template and the classDef list) or move them to a reference file, so "Style guide based on chosen preset" is executable rather than vague.

DimensionReasoningScore

Conciseness

The body is tight and concrete — flag tables, exact config paths (".devflow/visualizations.json"), a full JSON example, and one-line commands — with no explanations of concepts Claude already knows. It falls short of level 5 only through minor trimmable padding: the opening restates the description ("This sets up where visualizations live, what style to use, and which categories to create by default") and the excalidraw bullet runs long.

4 / 5

Actionability

Mostly executable guidance: concrete flags (--path, --style, --categories, --format, --global, --show), a copy-paste-ready JSON config block, and direct commands ("mkdir -p <path>/{<categories>}", "touch <path>/<category>/.gitkeep"). Minor gaps keep it from level 5: the README spec is a vague item list ("Style guide based on chosen preset") rather than a template, and the devflow preset's "10 classDefs" are referenced but never provided.

4 / 5

Workflow Clarity

A clear 7-step sequence with concrete commands, a pre-check for existing configuration (Step 1), and a final report step. It is not level 5 because checkpoints are incomplete: Step 1 checks for an existing config but never specifies what to do with it (merge vs overwrite vs confirm), and there is no post-write verification of the JSON. It stays above level 3 because the sequence is explicit, the operations are non-destructive, and the report step provides a summary checkpoint.

4 / 5

Progressive Disclosure

Well-organized numbered sections with consistent subsections and no nested or buried references; the skill is appropriately self-contained for a single-purpose configuration task (no bundle files exist, and none are strictly required). It is not level 5 because at ~130 lines it exceeds the simple-skill threshold, and the preset/style-guide details alluded to ("Full color palette with 10 classDefs", "Style guide based on chosen preset") are neither provided inline nor split into a reference file.

4 / 5

Total

16

/

20

Passed

Description

53%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 enough to identify the visualization-configuration niche, but it reads as a bare capability list. It lacks any "Use when..." trigger guidance and misses natural keywords like "diagrams", "mermaid", and "excalidraw", which limits both completeness and discoverability.

Suggestions

Add an explicit trigger clause, e.g. "Use when setting up or changing where diagrams are stored, which style preset to apply, or the output format (mermaid vs excalidraw)."

Enumerate the concrete actions performed: writing the config file, creating category folders, and generating the README — instead of the vague "output preferences".

Include natural trigger terms users would actually say: "diagrams", "mermaid", "excalidraw", "visualization setup", "diagram style".

DimensionReasoningScore

Specificity

The description names the domain with three aspects — "Configure visualization location, style presets, and output preferences" — but "output preferences" is generic, and major actions the skill actually performs (mermaid/excalidraw diagram format selection, category folder creation, config file generation) are absent. Coverage gaps exceed the "minor gaps" of the level-4 anchor, so it sits at 3.

3 / 5

Completeness

It has a clear "what" ("Configure visualization location, style presets, and output preferences") but no "when" clause at all — no "Use when..." or equivalent explicit trigger guidance. Per the judging guidelines, a missing 'Use when...' clause caps completeness at 3.

3 / 5

Trigger Term Quality

"visualization" and "style presets" are relevant keywords a user might say, but common natural variations and synonyms — "diagrams", "mermaid", "excalidraw", "charts" — are missing. It has more than the one or two generic keywords of level 2, but keyword coverage falls short of level 4.

3 / 5

Distinctiveness Conflict Risk

The description is scoped to visualization configuration (location, style, output preferences), clearly distinguishable from closely related sibling skills like diagram creation or rendering referenced in the body ("/devflow:update-visualizations", "devflow visualizations render"). It is not level 5 because a user asking to "set up visualizations" could plausibly intend diagram creation, and no explicit trigger phrases sharpen that boundary.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

AndreJorgeLopes/devflow

Path

devflow-plugin/skills/visualizations-config/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.