The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses gh (GitHub) and glab (GitLab) command-line interfaces to interact with issue trackers. These tools are used for searching, listing, viewing, and modifying issues, which is the skill's primary purpose.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, such as issue bodies and comments, which could potentially contain malicious instructions. To mitigate this, the skill implements a comprehensive "Author Authority" framework that verifies the permissions of content authors and requires human confirmation before performing any actions based on external input.
Ingestion points: Processes issue descriptions, comments, repository issue templates, and configuration files (.tituskirch-skills.json).
Boundary markers: Utilizes a mandatory "Plan" preview and human confirmation gate before any write operation. It also documents handling "Unauthorized text" by stopping for human review.
Capability inventory: Includes shell command execution via forge CLIs (gh, glab) and file writes to the local repository.
Sanitization: Includes a specific guardrail to scan for and exclude secrets (like .env content, keys, and tokens) from drafted issue content.
[DYNAMIC_EXECUTION]: The skill dynamically constructs shell commands and uses a bundled script (templates/resolve-config.sh) to merge and resolve JSON configurations. It also supports driving an external "interview engine" skill to refine user requests before drafting issues.
[EXTERNAL_DOWNLOADS]: The skill references a configuration schema at https://raw.githubusercontent.com/TitusKirch/skills/main/tituskirch-skills.schema.json. As this repository belongs to the skill's author, it represents a vendor-owned resource used for validation.

issue