The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute standard development utility commands including git status, git checkout, lint, typecheck, and build. These commands are integral to the skill's purpose of implementing and verifying code changes and are executed within their expected operational context.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it reads and processes data from external specification files. Ingestion points: Markdown files located in docs/specs/user-stories/, docs/specs/work-items/, and docs/specs/migrations/. Boundary markers: No explicit delimiters or instruction-ignoring warnings are defined for the ingested content. Capability inventory: Git operations, file system access, and project-specific build/lint tool execution. Sanitization: No specific sanitization or validation is applied to the content of the specifications. This risk is minimized by the skill's requirement for human confirmation at every step.
[SAFE]: The skill exhibits high operational security standards by mandating a clean working tree before starting work, enforcing a strict 'one unit per confirmation' workflow, and delegating specialized tasks like UI and testing to dedicated sub-specialist agents.

work-implement