The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides a manual command for the user to execute (npx skills add FuDesign2008/open-skills -g --skill '*' --yes) in the event that a required dependency is missing. This is a printed instructional step rather than an automated background execution.
[EXTERNAL_DOWNLOADS]: The skill references an external dependency (report-output-discipline) and provides an installation path for the author's own skill library on GitHub (FuDesign2008/open-skills). These resources are associated with the skill's author.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external platform settlements and analytics tools, creating a potential surface for indirect prompt injection if those sources contain malicious instructions.
Ingestion points: External platform settlement reports, analytics data, and the local file docs/reports/evolution/ledger.md.
Boundary markers: No specific delimiters or safety instructions are defined for the ingested data.
Capability inventory: The skill performs local file writing to update the reporting ledger at docs/reports/evolution/ledger.md.
Sanitization: No explicit sanitization or filtering logic is described for the processed metrics.

evolution-review