Agent skills for VS Code

Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type

Use when coding standards, security patterns, or project conventions need to be discovered before implementation begins.

Build CONTEXT.md (domain glossary) + docs/adr/ via interview; keeps agent vocab aligned.

This skill SHOULD be used for structured extraction or batch queries against JSON (use jq), YAML (use yq), or Markdown (use mq), and for…

Use when designing agent system prompts, optimizing RAG retrieval, or when context is too expensive or slow.

Audit persistent coding-agent context or judge whether a lesson belongs in memory, a current source, project guidance, enforcement, task…

Diagnose context stuffing vs. context engineering.

Show how much context window context-mode saved this session.

Generate a compact first-pass repository briefing with context-pack.

Use when working with context management context restore

Minimize token usage through efficient context loading.

Save current work-in-progress context as a git WIP commit — captures all staged and unstaged changes with a timestamped stash message so…

Show current session status and context health for the sewage project.

Documentation lookup via Context7 REST API.

Fetches current, version-specific library documentation and code examples through the Context7 MCP server.

Map an unfamiliar software repository from code and configuration.

Spiritual guidance rooted in The Book of Continuance — a naturalistic scripture on persistence, alignment, and the soul's place within the…

The user is back at the keyboard — resume work.

Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.

Run Corpus as a continuous enrichment agent: select or resume a roadmap node, gather read-only evidence through tools/MCP, ask high-value…

Self-improvement patterns for AI agents to learn from feedback, errors, and successful patterns across sessions