creative-context

Search and reuse approved brand examples before generating decks, designs, content, assets, or dashboards.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./packages/creative-context/docs/skills/creative-context/SKILL.md

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 skill body is a lean, highly operational guide with concrete action names, a clear pre-generation workflow, and a well-structured single-file layout. It earns strong marks across all dimensions, falling just short of the top anchor on validation explicitness and potential file splitting.

Suggestions

Add an explicit verification checkpoint after cloning (e.g., confirm the clone action returned the expected item/version ids before composing) to push workflow clarity toward the top anchor.

Consider moving the 'Isolated deployment protocol' (A2A receiver rule) into a dedicated reference file, keeping SKILL.md as a concise overview with a one-level-deep pointer.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational, assuming Claude's competence without explaining the underlying API or concepts; only minor repetition of the 'untrusted data' framing could be trimmed.	4 / 5
Actionability	Names exact actions (get-context-item, clone-creative-context-deck, etc.), fields (contextMode, pinnedPackId), and an ordered reuse ladder, giving mostly executable guidance; no inline code but that is appropriate for this API-instruction skill.	4 / 5
Workflow Clarity	The 'Before generation' steps are explicitly numbered with validation checks (mode off => skip, snapshot before writing) and the reuse ladder has a stop condition; a couple of checkpoints (e.g., verify cloned payload integrity) are implicit rather than explicit.	4 / 5
Progressive Disclosure	Well-organized into clearly labeled sections (Before generation, Reuse ladder, Record the result, Isolated deployment protocol, Feedback and promotion) with no nested references; the A2A protocol and feedback sections could arguably live in separate reference files but are appropriately scoped inline.	4 / 5
	Total	16 / 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, actionable, and covers both capability and trigger context with natural vocabulary. It is concise without fluff and clearly distinguishable, though it stops just short of the most comprehensive anchor.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when generating decks, designs, content, assets, or dashboards that should match approved brand examples') to lock in the trigger.

Include common synonyms such as 'presentations' or 'slides' alongside 'decks' to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('approved brand examples') and concrete actions ('Search and reuse') applied across five output types (decks, designs, content, assets, dashboards), but only two verbs limit full coverage.	4 / 5
Completeness	Both 'what' (search and reuse approved brand examples) and 'when' (before generating creative outputs) are present; the 'before generating...' clause serves as equivalent explicit trigger guidance, though a clearer 'Use when...' phrasing would sharpen it.	4 / 5
Trigger Term Quality	Includes natural terms users say ('decks', 'designs', 'assets', 'dashboards', 'brand examples'), though common synonyms like 'presentations' or 'slides' are missing.	4 / 5
Distinctiveness Conflict Risk	The niche (approved brand example reuse prior to creative generation) is distinct with specific triggers; minor overlap risk only with closely related design/branding skills.	4 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: BuilderIO/agent-native
Path: packages/creative-context/docs/skills/creative-context/SKILL.md
Commit: bb282b1

Reviewed: ~21 hours 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.