The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires the execution of a provided utility script, scripts/ci-timings.sh, which uses the gh (GitHub CLI) to perform authenticated API calls. This script is used to fetch CI run and job performance data for analysis.
[DATA_EXFILTRATION]: The skill instructs the agent to analyze CI step logs to identify performance bottlenecks. This process may expose sensitive information or credentials to the agent's context if they were inadvertently leaked and not properly masked in the CI logs.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests and processes untrusted data from external sources.
Ingestion points: The agent reads output from scripts/ci-timings.sh, metadata from GitHub API responses (such as job names), and detailed CI step logs.
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within the logs are provided.
Capability inventory: The agent is granted the capability to modify repository workflow files (e.g., GitHub Actions YAML files) and execute CLI tools including gh and jq.
Sanitization: The skill lacks mechanisms for sanitizing or validating the content of the CI logs or job names before they are used to inform workflow modifications.

ci-speedup