The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied backlog items, epics, and team availability data to generate sprint goals and plan deliverables. This external data is later used to perform actions in project management trackers.
Ingestion points: Backlog items and epic descriptions (Required Inputs in SKILL.md) and team member details (via JSON input to scripts/capacity_calculator.py).
Capability inventory: The skill uses scripts to write records to a brain repository and proposes ticket creation/modification in trackers via an action-runner tool.
Boundary markers: The skill defines clear output structures and a quality scoring rubric (Scoring Rubric in SKILL.md) to evaluate the agent's work.
Sanitization: The instructions do not specify sanitization or filtering for the content of user stories before they are processed by the agent.
[COMMAND_EXECUTION]: The skill executes local Python scripts to automate sprint calculations and data management.
Evidence: The SKILL.md documentation instructs the agent to run scripts/capacity_calculator.py for estimation and brain_query.py/brain_write.py for state management.
Context: These scripts are local components of the skill or its peer dependencies, and the capacity calculator is restricted to the Python standard library with no network access.

sprint-planning