The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local shell commands including git rev-parse, git diff, ls, and grep to analyze the repository state and project structure. It also utilizes the gh (GitHub) CLI for issue synchronization.
[CREDENTIALS_UNSAFE]: To facilitate automated Jira updates, the skill sources JIRA_EMAIL and JIRA_API_TOKEN from local configuration files at .jira-config or ~/.config/claude-km/jira.conf. These credentials are used for authenticated requests to the user's Jira instance.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing user-provided task descriptions which are subsequently analyzed by a sub-agent. Ingestion points: User-provided task/feature descriptions (SKILL.md). Boundary markers: Absent. Capability inventory: Local subprocess execution and network API calls (SKILL.md). Sanitization: No explicit sanitization or filtering of task descriptions before sub-agent processing was identified.

planner