agent-configs

Use before shipping high-stakes output (pre-tapeout RTL, verification infra, production scripts) that needs independent adversarial review. Requires reviewer backends configured in santa-method.json — if none are configured, do not use.

Use before shipping high-stakes output (pre-tapeout RTL, verification infra, production scripts) that needs independent adversarial review. Requires reviewer backends configured in santa-method.json — if none are configured, do not use.

Use this skill when in plan mode. It ensures all assumptions are resolved through an interview process.

Use when context is getting heavy, at natural breakpoints between subtasks, or when the user asks to checkpoint — writes the agent's full working context to a recoverable file before compaction

Audit the Obsidian vault for organizational health — broken links, naming violations, misplaced notes, sync status, stale content, and connection quality

Use when taking notes, recalling context, building connections, or treating the Obsidian vault as Claude's persistent memory across sessions

Required rules for working with the Obsidian vault — tool selection decision tree, quality gates, frontmatter schema, filename conventions, archival, content integrity. Load whenever vault notes are read, written, or referenced.

Audit the Obsidian vault for organizational health — broken links, naming violations, misplaced notes, sync status, stale content, and connection quality

Use when taking notes, recalling context, building connections, or treating the Obsidian vault as Claude's persistent memory across sessions

Use when the user wants user-facing documentation for a code module or package. Hierarchically composes a docs/ folder — a hub README plus per-submodule API guides (signatures, parameters, usage, interactions) extracted strictly from source. The outward-facing counterpart to project-archaeology.

Use when the user wants to outline an academic research paper. An interview-driven scribe — elicits all content from the user as terse fragments (zero inference, zero filler) and structures it into a story-driven markdown outline written to the working directory.

Required behavioral guidelines for all coding tasks — think before coding, simplicity first, surgical changes, goal-driven execution. Load at the start of any task that involves writing or modifying code.

Systematically reverse-engineer an existing codebase and produce trustworthy Obsidian vault documentation with evidence-tagged claims