The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses various shell commands to inspect the repository environment and interact with issue trackers. Specifically, it executes git rev-parse --show-toplevel and git remote -v to identify repository roots and remotes. It also provides instructions for using platform-specific CLIs such as gh (GitHub), glab (GitLab), and wp (Workplan) to manage issues, pull requests, and dependencies.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data that could theoretically be manipulated by an attacker to influence agent behavior.
Ingestion points: Data is ingested from repository configuration files (.git/config), git remote information, and outputs from the wp CLI tool.
Boundary markers: The process includes a human-in-the-loop verification step (Step 3 in SKILL.md), requiring the user to approve the exact text of the proposed configuration files before they are written to the repository.
Capability inventory: The skill has the capability to write to documentation files (e.g., docs/agents/issue-tracker.md, docs/agents/triage-labels.md) and modify root-level instruction files (AGENTS.md or CLAUDE.md). It also performs writes to external issue trackers via CLI tools.
Sanitization: While no programmatic escaping is detailed, the skill relies on templates and user review to ensure the integrity of the generated instructions.

ai-setup-skills