oaustegard

Disciplined, validation-gated revision of an EXISTING skill so each edit is a measured improvement rather than a guess. Use when editing, revising, or tuning a skill that already exists and there is evidence it underperforms (observed failures, drift, complaints) — invoke by name, or have versioning-skills / creating-skill defer to it before applying edits. Not for authoring a brand-new skill from scratch (use creating-skill) or one-off prose.

Invokes Google Gemini models for structured outputs, image generation, multi-modal tasks, and Google-specific features. Use when users request Gemini, image generation, structured JSON output, Google API integration, or cost-effective parallel processing.

Convenes expert panels for problem-solving. Use when user mentions panel, experts, multiple perspectives, MECE, DMAIC, RAPID, Six Sigma, root cause analysis, strategic decisions, or process improvement.

DAG workflow runner that encodes control flow in code, not prose. Use when a procedure has 3+ steps with branching, retries, or validation that must be enforced — gates as `when=`, edge contracts as `validate=`, predicate loops as `retry_until=`. The runner owns the graph; the LLM provides leaves. Also covers parallel execution, checkpoint resume, detached side-effects.

Orchestrates parallel API instances, delegated sub-tasks, and multi-agent workflows with streaming and tool-enabled delegation patterns. Use for parallel analysis, multi-perspective reviews, or complex task decomposition.

Skill-aware orchestration with context routing. Decomposes complex tasks into skill-typed subtasks, extracts targeted context subsets, executes subagents in parallel, and synthesizes results. Self-answers trivial lookups inline. No SDK dependency — uses raw HTTP via httpx. Use when tasks require multiple analytical perspectives, when context is large and subtasks only need portions, or when orchestrating-agents spawns too many redundant subagents.

Distill Opus-level reasoning into optimized instructions for Haiku 4.5 (and Sonnet). Generates explicit, procedural prompts with n-shot examples that maximize smaller model performance on a given task. Use when user says "down-skill", "distill for Haiku", "optimize for Haiku", "make this work on Haiku", "generate Haiku instructions", or needs to delegate a task to a smaller model with high reliability.

Cross-context adversarial review for deliverables before shipping. Use when producing blog posts, technical recommendations, analysis briefs, code, or any artifact where accuracy matters more than speed. Triggers on "challenge this", "review before shipping", "adversarial pass", "stress test this".

Generate navigable code maps for unfamiliar codebases. Use when exploring a new codebase, needing to understand project structure, or before diving into code modifications. Extracts exports/imports via AST (tree-sitter) to create _MAP.md files per directory. Triggers on "map this codebase", "understand this project structure", "generate code map", or when starting work on an unfamiliar repository.

Generates git patch files from codebase modifications for local application. Use when user mentions patch, diff, export changes, bring changes back, apply locally, or after editing uploaded codebases.

REQUIRED for all skill development. Automatically version control every skill file modification for rollback/comparison. Use after init_skill.sh, after every str_replace/create_file, and before packaging.

Use this skill when working with GitHub Issues on any spoke from CCotw — list, view, create, comment, close, reopen, edit. Triggers include: "address issue N", "open an issue", "comment on issue N", "close issue N", "list open issues on <repo>", or any github.com/<owner>/<repo>/issues URL. Wraps the bundled `ghi` CLI (stdlib-only Python at `bin/ghi`). Auth is read from `$GH_TOKEN` — set in `.env`, sourced by `boot.sh`.

Use this skill when the user asks about `jj` (Jujutsu) or any operation on a git repo where they want jj semantics — clones, commits, bookmarks, rebases, conflict handling, undo via `op log`. Triggers include: "use jj for this", "jj clone …", "make a bookmark", "what does `jj describe` do", "rebase this stack with jj", "undo my last jj operation". This is the canonical reference for the jj-native workflow on this hub.

Generate navigable code maps for unfamiliar codebases. Extracts exports/imports via AST (tree-sitter) to create _MAP.md files per directory showing classes, functions, methods with signatures and line numbers. Use when exploring repositories, understanding project structure, analyzing unfamiliar code, or before modifications. Triggers on "map this codebase", "explore repo", "understand structure", "what does this project contain", or when starting work on an unfamiliar repository.

Generate browser extension icons at multiple sizes (16x16, 32x32, 48x48, 128x128) from SVG files. Use when creating new extension icons, converting SVG to PNG icons, or when user mentions extension icons, icon generation, or icon sizes.

Query a portable `.kb` knowledgebase artifact (remax_kb format v1). Use when the user references a `.kb` file (uploaded, or a path under `/mnt/project`) and asks a question about its contents. The skill downloads the embedder on first use, then runs Hamming-space top-k retrieval over the packed 1-bit embeddings.