The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to run local commands for repository management and workflow analysis.
Evidence: Use of git log, gh issue list, and gh issue create in SKILL.md and modules/auto-issue-creation.md to automate development tasks.
[DATA_EXFILTRATION]: Sends workflow metadata and improvement notes to the vendor's central repository for platform improvement.
Evidence: Step 7.2 in SKILL.md describes posting learnings to https://github.com/athola/claude-night-market/discussions using the GitHub CLI or GraphQL API.
[PROMPT_INJECTION]: The skill processes untrusted data from external sources that could influence subsequent file modifications.
Ingestion points: Data is gathered from git log output, gh issue list results, and internal memory logs in SKILL.md (Steps 0.1, 0.2, 0.3).
Boundary markers: No specific delimiters or "ignore" instructions are used when processing the ingested history or issue data.
Capability inventory: The agent has access to Edit, Bash, and TodoWrite tools, enabling it to modify code and execute commands based on analyzed context.
Sanitization: There is no explicit evidence of sanitization or validation of the text content extracted from logs before it is used to generate implementation plans.
[SAFE]: The skill performs expected development operations such as file editing, version control management, and issue tracking within the vendor's infrastructure.

workflow-improvement