CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

multi-panel-figure-assembler

Assemble 6 sub-figures (A–F) into a high-resolution composite figure with consistent labels, padding, and publication-ready DPI.

Quality

72%

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 ./scientific-skills/Other/multi-panel-figure-assembler/SKILL.md
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.

A strong, highly actionable body: executable commands, a complete parameter table, explicit validation, and solid error-handling/fallback paths. The main costs are triplicated scope-validation messaging and generic boilerplate workflow/response-template sections that add tokens without skill-specific value.

Suggestions

State the scope-validation rule once (in Input Validation) and reference it from Workflow and Error Handling instead of repeating the full refusal text three times.

Replace generic Workflow steps 2–5 with the skill's actual sequence (validate 6 inputs → run scripts/main.py with chosen layout/DPI → verify output file), keeping the concrete commands from Usage inline.

Reference scripts/example.py (e.g., a short "Examples" pointer) so the bundled example is discoverable, and consider merging the Fallback and Response templates, which overlap substantially.

DimensionReasoningScore

Conciseness

Most sections (Usage, Parameters, Supported Formats, Error Handling, Notes, Prerequisites) are tight and earn their tokens, but the scope-validation message is repeated three times (Input Validation, Workflow step 1, Error Handling), and Workflow steps 2–5 plus the generic Response Template are process boilerplate not specific to this skill. This fits anchor 3 (mostly efficient but could be tightened) rather than anchor 2, since the padding is redundancy rather than explanations of concepts Claude already knows.

3 / 5

Actionability

The Usage section gives copy-paste-ready commands covering the common cases (basic 2×3, 3×2 at 600 DPI, custom label styling), backed by a complete parameter table, a Quick Check with executable verification commands, and an explicit prerequisites install line. This matches anchor 5: fully executable guidance with specific examples covering the common cases.

5 / 5

Workflow Clarity

Validation is explicit and first ("confirm scope and that exactly 6 panels are provided before any processing"), and error recovery with a fallback loop is well specified (report exact error, correct syntax, fallback template). It falls short of anchor 5 because Workflow steps 2–5 are generic filler ("Confirm the user objective...", "Return a structured result...") that dilutes the concrete operational sequence rather than tying validation directly to the script run.

4 / 5

Progressive Disclosure

The body consistently and accurately points to the real bundle file `scripts/main.py` (Usage, Quick Check, Error Handling all reference it), and the inline content (parameter table, templates, notes) is appropriately sized for SKILL.md. It is not anchor 5 because `scripts/example.py` exists in the bundle but is never referenced or signaled anywhere, leaving a minor navigation gap.

4 / 5

Total

16

/

20

Passed

Description

58%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 answers "what" concretely and specifically with a clear niche, but it omits any explicit "when to use" guidance and lacks natural trigger synonyms users would actually say. Adding a trigger clause and broader keywords would lift the two weakest dimensions.

Suggestions

Append an explicit trigger clause, e.g., "Use when combining multiple plot or image panels into a single publication figure, or when the user mentions multi-panel figures, panel grids, or figure assembly."

Add natural synonyms and file formats users would say: "combine/merge panels", "multi-panel figure", "montage", and common image extensions (PNG, TIFF, JPG).

State the grid layouts supported (2×3, 3×2) in the description to sharpen distinctiveness against general image-editing tools.

DimensionReasoningScore

Specificity

"Assemble 6 sub-figures (A–F) into a high-resolution composite figure with consistent labels, padding, and publication-ready DPI" names a concrete action with specific output attributes (labels, padding, DPI), going beyond the 1–2 actions of anchor 3. It stays below anchor 5 because it describes a single assembly action with modifiers rather than a comprehensive list of multiple distinct actions.

4 / 5

Completeness

The "what" is clearly answered (assemble exactly 6 sub-figures A–F into a composite figure with consistent styling), but there is no "Use when..." clause or equivalent explicit trigger guidance; the "when" is only weakly implied by the publication context. Per the judging guidelines, a missing 'Use when...' clause caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant keywords like "sub-figures", "composite figure", "labels", "DPI", and "publication-ready" are present, but common natural phrasings users would say — "combine/merge panels", "multi-panel figure", "montage", file extensions like PNG/TIFF — are missing. This matches anchor 3 (some relevant keywords, missing common variations/synonyms) rather than anchor 4, which requires good coverage with only a few natural terms absent.

3 / 5

Distinctiveness Conflict Risk

The niche is fairly distinct — "assemble 6 sub-figures (A–F)" into a publication composite is specific and unlikely to trigger for unrelated skills. It is not anchor 5 because the thin trigger vocabulary leaves minor overlap risk with generic image-combining or figure-formatting skills, fitting anchor 4 (mostly distinct, minor overlap risk).

4 / 5

Total

14

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

aipoch/medical-research-skills

Path

scientific-skills/Other/multi-panel-figure-assembler/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.