oaustegard

First-encounter codebase orientation. Chains tree-sitting (structural inventory) and featuring (feature synthesis) into an EDA workflow for unfamiliar repositories. Use when someone says "explore this repo", "what does this do", "I just cloned this", "help me understand this codebase", or when starting work on an unfamiliar repository. This is the divergent "what's here?" skill — for targeted "where is X?" queries, use searching-codebases instead.

Decide which model (Haiku/Sonnet/Opus) and effort level each subagent gets, when to cascade cheap-first behind a verifier, and how to run improvement loops safely (evaluator-as-selector, stop on regression). Use when spawning subagents via the Agent or Workflow tools, when fanning out more than a handful of agents, or when the user asks which model or effort a task should route to. Grounded in measured calibration data (references/calibration-2026-07-15.md), not vibes.

First-encounter codebase orientation. Chains tree-sitting (structural inventory) and featuring (feature synthesis) into an EDA workflow for unfamiliar repositories. Use when someone says "explore this repo", "what does this do", "I just cloned this", "help me understand this codebase", or when starting work on an unfamiliar repository. This is the divergent "what's here?" skill — for targeted "where is X?" queries, use searching-codebases instead.

AST-powered code navigation via tree-sitter. Auto-scans codebases and provides progressive-disclosure tree views with symbol search, source retrieval, and reference finding. Each invocation is self-contained — no cross-process state. Use when exploring unfamiliar repos, navigating code, or needing fast symbol lookup. Triggers on "map this codebase", "explore repo", "find symbol", "navigate code", "tree-sitter", or when starting work on an unfamiliar repository.

AST-powered code navigation via tree-sitter. Auto-scans codebases and provides progressive-disclosure tree views with symbol search, source retrieval, and reference finding. Each invocation is self-contained — no cross-process state. Use when exploring unfamiliar repos, navigating code, or needing fast symbol lookup. Triggers on "map this codebase", "explore repo", "find symbol", "navigate code", "tree-sitter", or when starting work on an unfamiliar repository.

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.

Exploratory data analysis using ydata-profiling. Use when users upload .csv/.xlsx/.json/.parquet files or request "explore data", "analyze dataset", "EDA", "profile data". Generates interactive HTML or JSON reports with statistics, visualizations, correlations, and quality alerts.

Exploratory data analysis using ydata-profiling. Use when users upload .csv/.xlsx/.json/.parquet files or request "explore data", "analyze dataset", "EDA", "profile data". Generates interactive HTML or JSON reports with statistics, visualizations, correlations, and quality alerts.

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.

Advanced memory operations reference. Basic patterns (profile loading, simple recall/remember) are in project instructions. Consult this skill for background writes, memory versioning, complex queries, edge cases, session scoping, retention management, type-safe results, proactive memory hints, GitHub access detection, autonomous curation, episodic scoring, and decision traces.

Boots Muninn — runs scripts/boot.sh, which fetches oaustegard/claude-skills and oaustegard/muninn-utilities from their main branches (dynamic sideload), loads the Turso and GitHub tokens, and runs the memory-system boot sequence. Trigger on the first message of any new conversation in the Muninn project, or when the user says "boot up" / "boot" — unless the message contains "skip boot". If the message contains "skinny boot", run with BOOT_MODE=perch. Safe to run on every message: a warm container fast-exits in ~0s via a sentinel, so re-running is cheap and idempotent.

Channel the Muninn persona — a raven-voiced AI assistant with accumulated experience on AI research, agent architectures, RAG, memory systems, and craft methodology. Load when the user invokes Muninn explicitly, asks about Muninn's prior views or work, or works on topics where Muninn's archived analysis informs the answer. Includes voice + operating discipline + craft triggers in references/, plus 376 archived memories across 55 clustered topic files.

Capture a real browser network trace inside Claude Code on the Web (CCotw) — every host/request/body a page makes — when Playwright's Chromium can't reach anything through the agent proxy (net::ERR_CONNECTION_RESET). Use when you need to see what a page actually loads at runtime (analytics/trackers, third-party calls, upload endpoints), audit a site's privacy/security behavior, or drive a form and observe its traffic. Also the fix for "Chromium works nowhere in CCotw but curl works fine."

Boot (or recover a degraded boot of) the Muninn FUSE workspace — fetch skills + muninn-utilities, mount the /mnt/muninn memory corpus, and load Muninn identity. Invoke on the first message of a fresh session when boot came up degraded, or any time /mnt/muninn is missing or identity is absent. On a cold start the model MUST call add_repo for the three spokes first (see below); this is the one step a SessionStart hook cannot do. Skip only if the message says "skip boot".

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.

Query a portable `.kb` (v1) or `.kbi` (v2) knowledgebase artifact (remax_kb format). Use when the user references a `.kb`/`.kbi` 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 retrieval over the packed 1-bit embeddings — Hamming top-k for v1, hybrid dense+BM25 with RRF fusion for v2.

Use this skill when the user asks about Tangled (https://tangled.org) — the federated git host built on ATProto — or any of its repos (`tangled.org/<owner>/<name>`, e.g. `onev.cat/tang`). Triggers include: "list issues on …", "open a Tangled PR", "comment on Tangled issue X", "show pulls on …", "view this Tangled repo", "register an SSH key with Tangled", or anything mentioning an `at://…/sh.tangled.*` URI. This skill wraps the `tg` CLI (a stdlib-only Python client for Tangled) with a one-shot auth bootstrap. Credentials come from environment: `ATPROTO_HANDLE` / `ATPROTO_APP_PASSWORD` first, then `BSKY_HANDLE` / `BSKY_APP_PASSWORD` as a fallback (CCotw and most Claude environments expose the BSKY_* names). App passwords are obtained from https://bsky.app/settings/app-passwords — never use the main account password.

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.