CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

visuals

Draw the image that proves a claim at a glance: a screenshot ringed on the point, a diagram, or a chart. Use when a PR change needs a before/after, a finding needs its cause shown, a system or flow needs explaining, or a result is in numbers.

Quality

89%

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

92%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.

An exceptionally well-crafted body: lean and free of known-concept explanation, rich in concrete commands and named primitives, and structured as a five-step workflow with explicit validation checkpoints, escalation rules, and a failure fallback. The only notable gap is the unexplained ASD-STE100 requirement, which is only partially actionable without the spec or a pointer to it.

DimensionReasoningScore

Conciseness

The body is dense and telegraphic with essentially no explanation of concepts Claude already knows — it uses Mermaid, Vega-Lite, git worktrees, and file: script restrictions without elaboration — and every line prescribes ("Bright fills on white, by meaning", "A mark on each part of the claim, and on nothing else"). Matches the lean, every-token-earns-its-place anchor; the version notes in Gotchas/Requirements each teach a distinct non-obvious failure mode rather than padding.

5 / 5

Actionability

Concrete commands (`gh-attach shot ... frame.html ... .png`, `git fetch origin <base> && git worktree add ...`, `gh pr view --json baseRefName -q .baseRefName`), an HTML skeleton, and named CSS classes (`.panel pair`, `side before`, `mark`, `kicker`) make the workflow executable. Not 5 because "Words in ASD-STE100 Simplified Technical English" invokes a proprietary standard with no rules or pointer, and `<skill-dir>` resolution is left implicit; well above 3 since the core path is copy-paste ready modulo placeholders.

4 / 5

Workflow Clarity

Five sequenced steps with a "Done when" exit criterion for the brief, an explicit pass/fail checklist in step 4 ("Proves the claim", "Makes sense", "The headline reads clearly"), feedback loops ("fix it at the level it lives at and render again", "When the same shape fails twice, switch shape"), and a defined fallback when no shape can prove the claim. Matches the explicit-validation-with-error-recovery anchor exactly.

5 / 5

Progressive Disclosure

A routing table maps each claim type to one of four clearly signaled, one-level-deep reference files ([screenshots.md], [diagrams.md], [charts.md], [freeform.md]) plus frame.css and render.js, keeping the body a navigable overview of the method. Note: no bundle files were present in the review directory to verify the referenced files exist, so this is scored on the reference structure as written; that structure matches the anchor's clear-overview, well-split, easy-navigation pattern.

5 / 5

Total

19

/

20

Passed

Description

83%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 pairs a clear, concrete purpose statement with four explicit 'Use when' trigger scenarios. Its weaknesses are minor: a somewhat spare list of concrete actions and modest overlap risk with generic chart/diagram skills.

DimensionReasoningScore

Specificity

"Draw the image that proves a claim at a glance: a screenshot ringed on the point, a diagram, or a chart" names the domain and three concrete deliverables, but the action list is spare and omits other artifacts the skill covers (pinning user images, tables, stat cards). Not 5 because coverage is thinner than the comprehensive-action anchor; clearly above 3 because multiple concrete artifacts and the ring/annotate action are explicit.

4 / 5

Completeness

"Draw the image that proves a claim at a glance: a screenshot ringed on the point, a diagram, or a chart" states what, and "Use when a PR change needs a before/after, a finding needs its cause shown, a system or flow needs explaining, or a result is in numbers" gives four explicit trigger scenarios. This matches the anchor that clearly and explicitly answers both what and when with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural phrases like "a PR change needs a before/after", "a finding needs its cause shown", "diagram", "chart", and "a result is in numbers" match what users would actually say. Not 5 because common synonyms such as "visual", "graph", "figure", or "evidence" are missing; above 3 because several genuinely natural trigger phrases are present.

4 / 5

Distinctiveness Conflict Risk

The niche — evidence images that prove claims for PRs, findings, and results — is distinct, but generic terms like "diagram", "chart", and "a system or flow needs explaining" overlap with general diagramming/dataviz skills. Not 5 due to that overlap risk; above 3 because the PR/finding/result triggers are quite specific.

4 / 5

Total

17

/

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

relative_links

Relative link issues: 23 missing

Warning

Total

14

/

16

Passed

Repository

aabuhijleh/abed-hub

Path

skills/visuals/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.