CtrlK
BlogDocsLog inGet started
Tessl Logo

repo-visuals

Create hero visuals — animated GIF, static PNG, or animated SVG — for GitHub repositories. Runs a structured discovery conversation (scan repo → recommend format → propose creative scenarios → agree on a brief), then designs bespoke HTML/SVG, previews it in the browser, and exports. Use when the user asks for a README hero, repo banner, README image, GitHub header, social preview card, repo demo GIF, hero image, OG image, project screenshot, repository showcase, or any "image at the top of the README".

71

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The skill body is an exceptionally actionable, well-sequenced workflow with strong validation gates. Its two weak spots are verbosity in the rationale/anecdote prose and a progressive-disclosure structure whose craft/*.md reference targets are missing from the bundle.

Suggestions

Ship the referenced craft/ files (headlines.md, rules.md, export.md, ship.md, evaluate.md, reference-gallery.md, redesign.md, svg-animation.md, operating-mode-question.md) or inline their essential content — the body repeatedly delegates to files that do not exist in the bundle.

Tighten the gate rationale paragraphs (e.g. §1.8, §1.8b, §2.6) by collapsing the repeated 'scope is deliberately narrow…' justifications into a single stated principle; the current restatements pad the token budget.

Consolidate the scattered incident anecdotes (VeloxDB, clawd-on-desk, obsidian-skills, Terminal.Gui) into a single 'past failures' reference file so the main flow stays lean while retaining the lessons.

DimensionReasoningScore

Conciseness

The body (~570 lines) is dense with rationale and incident anecdotes — e.g. multi-paragraph explanations of why each gate's scope is narrow and repeated restatements of the same craft rules. Most of the craft knowledge is non-obvious and earns its place, but there is visible prose padding that could be tightened without losing meaning.

2 / 3

Actionability

Highly executable: concrete commands ('ffmpeg -i recording.mov -vf "fps=0.5,scale=1400:-1"'), exact Puppeteer flags ('deviceScaleFactor: 2', explicit clip), a 6-section index.html structure, and precise file-path conventions. Copy-paste ready guidance throughout.

3 / 3

Workflow Clarity

A clearly sequenced five-phase pipeline with explicit validation gates (Gate A §1.8, Gate B §2.6), a convergence checklist (§1.6), an entry gate before export (§4.0), and a defined one-retry feedback loop on failure — matching the level-3 anchor with checkpoints and error-recovery loops.

3 / 3

Progressive Disclosure

The body is well-organized by phase and signals one-level-deep references to craft/*.md files (headlines.md, rules.md, export.md, ship.md, evaluate.md, reference-gallery.md, redesign.md, svg-animation.md), but the craft/ directory is absent from the actual bundle — only scripts/ exists. Per the guideline to score against the actual bundle structure, a large share of the promised detailed material points at non-existent files, which is a broken reference structure rather than clean one-level disclosure.

2 / 3

Total

10

/

12

Passed

Description

100%

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, action-oriented, and uses third person throughout. It pairs concrete capability statements with an explicit, broad 'Use when' trigger list, hitting the top anchor on every dimension.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across three formats — 'Create hero visuals — animated GIF, static PNG, or animated SVG', 'scan repo', 'designs bespoke HTML/SVG', 'previews it in the browser, and exports' — matching the level-3 anchor.

3 / 3

Completeness

Explicitly answers both what it does and when to use it via an explicit 'Use when...' clause, hitting the level-3 anchor.

3 / 3

Trigger Term Quality

Broad natural-language trigger coverage ('README hero, repo banner, README image, GitHub header, social preview card, repo demo GIF, hero image, OG image, project screenshot, repository showcase, or any "image at the top of the README"') — terms users would actually say.

3 / 3

Distinctiveness Conflict Risk

A clear niche (GitHub repo hero visuals) with distinct, specific triggers unlikely to fire for unrelated design skills.

3 / 3

Total

12

/

12

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.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (580 lines); consider splitting into references/ and linking

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
livlign/claude-skills
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.