title-card-image

Render a static title / ending card PNG with Pillow. Centered headline + optional subtitle on a solid-colour background. Uses managed or platform CJK fonts with glyph verification and fails actionably instead of rendering tofu. Pure deterministic, no LLM, no network. Used by meta-short-drama for opening and closing cards.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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.

The body is a lean, well-structured overview that defers implementation to scripts/render.py and documents inputs, output, font fallback, and limits concretely. The only minor gap is the absence of an example invocation block, which would make it copy-paste ready.

Suggestions

Add a short example `with:` block (e.g., text + output + subtitle) so a caller can invoke the skill without consulting the entrypoint args.

Optionally cross-reference scripts/render.py from the body so the SKILL.md-as-overview pointer to the implementation is explicit.

Keep the concise section structure; do not expand the Font fallback section with general font/background explanations.

Dimension	Reasoning	Score
Conciseness	The ~47-line body is lean with no concept padding (no explanation of what Pillow or PNG is); the Inputs table and 'Font fallback' / 'Limits' sections each carry non-obvious, decision-relevant information. Not 4 because there are no trimmable over-explanations — every token earns its place.	5 / 5
Actionability	The Inputs table maps each key to required/default/notes and directly corresponds to the entrypoint args, and the Output and Font fallback sections give concrete behavior. Not 5 because there is no example `with:` invocation block showing a complete call, leaving a minor executable gap.	4 / 5
Workflow Clarity	This is a simple single-purpose skill (render one PNG) whose single action is unambiguous, and it includes built-in actionable failure handling for missing CJK fonts; the simple-skill exception applies and the operation is not destructive/batch, so no cap. Not 4 because the action and its error path are explicit and unambiguous.	5 / 5
Progressive Disclosure	Under 50 lines with well-organized sections (Inputs, Output, Font fallback, Limits), and the heavy implementation logic is appropriately split into the provided bundle file scripts/render.py rather than inlined. Not 4 because structure and the SKILL.md-as-overview split are clean with no organization gaps.	5 / 5
	Total	19 / 20 Passed

Description

75%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, distinctive, and rich in concrete behavior, but it lacks an explicit 'Use when...' trigger clause, relying on a 'Used by' provenance line that only weakly implies use cases. Adding a concrete trigger clause would lift completeness.

Suggestions

Add an explicit 'Use when...' clause naming trigger phrases (e.g., 'Use when generating a cover or ending card image for a short-drama clip, or when the user asks for a title card / opening card / closing card PNG').

Include the '.png' file extension and synonyms like 'cover image' or 'intro card' as natural trigger terms.

Keep the existing third-person voice and concrete action list; avoid adding buzzwords.

Dimension	Reasoning	Score
Specificity	Quotes 'Render a static title / ending card PNG with Pillow. Centered headline + optional subtitle on a solid-colour background... glyph verification and fails actionably instead of rendering tofu' — multiple concrete actions (render, center headline/subtitle, CJK font fallback, glyph verification, actionable failure) with comprehensive coverage of the rendering domain. Not 4 because coverage is comprehensive rather than having minor gaps.	5 / 5
Completeness	A clear 'what' is present ('Render a static title / ending card PNG...') but there is no explicit 'Use when...' clause; 'Used by meta-short-drama for opening and closing cards' is provenance/parent-skill context, only weakly implying when, so per the cap guideline completeness cannot exceed 3. Not 4 because explicit trigger guidance is absent.	3 / 5
Trigger Term Quality	Natural terms 'title / ending card', 'PNG', 'CJK fonts', 'opening and closing cards', 'Pillow' are present and would be said by users; not 5 because some natural synonyms (cover, thumbnail, intro card) are missing, and there is no file extension like '.png' as a trigger.	4 / 5
Distinctiveness Conflict Risk	Clear niche — CJK-safe static title/ending card PNG rendering with tofu-avoidance — with distinct triggers and minimal overlap risk with other skills. Not 4 because the niche is sharply defined, not merely 'mostly distinct'.	5 / 5
	Total	17 / 20 Passed

Validation

81%

Warnings & errors only

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

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: TokenRhythm/opensquilla
Path: src/opensquilla/skills/bundled/title-card-image/SKILL.md
Commit: 94ac35e

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.