The Agent Skills Directory

[COMMAND_EXECUTION]: The skill performs standard shell operations for repository management, including git pull, git add, git commit, and git push to synchronize project state with remote repositories. It also utilizes npx to run js-yaml for validating the syntax of local configuration files.\n- [DYNAMIC_EXECUTION]: A validation utility described in references/yaml-guardrails.md employs npx tsx -e to execute a targeted JavaScript snippet. This code uses the vendor-provided @agentic-engineering-patterns/api library to perform schema validation on project metadata.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests content from local project files which could potentially contain untrusted data if modified by external actors.\n
Ingestion points: Content is read from product-context.yaml, product/index.yaml, and calibration/*.yaml to populate briefs and session context.\n
Boundary markers: No explicit delimiters or instruction-ignore blocks are used when interpolating file data into the agent's prompts.\n
Capability inventory: The skill is capable of performing file system writes and executing version control commands.\n
Sanitization: The skill mitigates risks by validating all input files against YAML schemas and using a dedicated loader for data processing.

aep-calibrate