The Agent Skills Directory

[SAFE]: The skill implements a professional QA workflow for documenting validated behaviors in a Tracking Management System (TMS). It uses a structured Subagent Dispatch Strategy to manage bulk operations efficiently.
[EXTERNAL_DOWNLOADS]: The skill references and interacts with official Atlassian Jira and Xray REST/GraphQL APIs and CLI tools (acli, xray-cli). These are well-known technology services, and the interactions are documented neutrally as standard functionality.
[DATA_EXFILTRATION]: Authentication tokens and configuration settings (e.g., JIRA_API_TOKEN, XRAY_CLIENT_SECRET) are retrieved from local .env files. This follows standard secure practice for secret management in development tools and does not constitute unauthorized exposure.
[PROMPT_INJECTION]: The skill processes untrusted content from Jira User Stories, Epics, and comments to generate test cases. While this provides a surface for indirect prompt injection, the risk is inherent to the primary purpose of the skill and is mitigated by the structured analysis and validation phases described in the instructions.
Ingestion points: Reads User Story descriptions, Acceptance Criteria, and Jira comments (SKILL.md §Phase 1).
Boundary markers: Not explicitly defined in the prompt instructions.
Capability inventory: Uses [ISSUE_TRACKER_TOOL] and [TMS_TOOL] for searching, creating, updating, and transitioning Jira issues.
Sanitization: The skill emphasizes validating design assumptions against implementation source code (SKILL.md §Source-code validation), providing a manual verification step before documentation.

test-documentation