The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on several shell commands for its core functionality.
Executes npx hyperframes for project lifecycle tasks including initialization, updates, linting, and final checks.
Runs node scripts for internal logic such as frame-packets.mjs and prefs.mjs.
Instructs the agent to relay output from npx hyperframes auth status verbatim to the user, which is a standard diagnostic step for this toolset.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-controlled files which serve as an injection surface for both the primary agent and its sub-agents.
Ingestion points: Reads STORYBOARD.md, BRIEF.md, and design truth files (frame.md, design.md).
Boundary markers: Absent. The content from these files is parsed and inlined into sub-agent packets without explicit delimiters or "ignore instructions" warnings.
Capability inventory: The skill has the ability to write files, execute shell commands, and spawn sub-agents with delegated tasks.
Sanitization: No sanitization is performed on the text content of storyboard blocks before they are passed to sub-agents.
[DYNAMIC_EXECUTION]: The skill orchestrates sub-agents by generating their instructions and roles at runtime.
Concatenates frame-worker-core.md and sub-agents/frame-worker.md to create a worker role definition (_role.md).
Inlines storyboard blocks and motion recipes into individual frame packets for worker consumption.
Executes scripts from computed paths, such as node <MEDIA_DIR>/scripts/prefs.mjs.
[EXTERNAL_DOWNLOADS]: The skill interacts with remote registries and update services associated with the hyperframes ecosystem.
npx hyperframes skills update fetches the latest version of the skill code.
npx hyperframes catalog queries a hosted registry of video components and visual treatments.

general-video