The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the gh (GitHub CLI) tool to perform read and update operations on repository issues and project items. These operations are integral to the skill's primary function of bulk editing and are documented with rate-limiting precautions.
[INDIRECT_PROMPT_INJECTION]: The skill operates on external data, such as issue titles and record fields, which represents a potential attack surface for indirect prompt injection.
Ingestion points: Data is ingested through commands like gh api and gh issue list as described in SKILL.md and references/github.md.
Boundary markers: Step 3 of the skill instructions mandates 'structural anchoring' (using fixed edges and defined boundaries) to prevent transforms from reaching unintended data and requires a HOLD classification for ambiguous records.
Capability inventory: The skill possesses the capability to perform mutations using gh api -X PATCH as detailed in references/github.md.
Sanitization: The skill mandates high-integrity practices, including demonstrating the recovery path on a single record, using structural anchors instead of pattern searches, and building command arguments as Python lists to avoid shell injection vulnerabilities.

bulk-edit