Use when you need Apple's own documentation or a Swift compiler diagnostic explained rather than recalled.
79%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./.claude-plugin/plugins/axiom/skills/axiom-apple-docs/SKILL.mdThe canonical home for this skill is axiom-apple-docs in CharlesWiltgen/Axiom
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The workflow instructs the agent to fetch external web pages and documentation mirrors (sosumi.ai) and WWDC transcripts, which constitutes low-risk ingestion of third-party web content.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The skill references `sosumi.ai` as a third-party documentation mirror for Apple developer documentation, but it directs the agent to use a web-fetch tool at runtime to retrieve content from that external URL as behavioral input and documentation guidance, constituting an unverified third-party operational dependency with medium provenance.
CharlesWiltgen/Axiom
58ae15a
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.