oaustegard
- 185 skills
- 0 followers
- 395 repo stars
- 2 days ago last updated
- ▌ Hunting Failing Inputs · oaustegard bundleFinds inputs that make a parser, decoder or WGSL compute shader index out of bounds or overflow, using Z3. Use for "can this crash", "find an input that breaks this", or when fuzzing found nothing on code that reads untrusted bytes.
- ▌ Capturing Browser Logs · oaustegard bundleGets runtime evidence from a web page the agent cannot run itself, using Agent Log (austegard.com/web-utilities/agent-log.html), a script that records console calls, errors, fetch/XHR traffic and the events and DOM changes of elements the user picks, as OpenTelemetry logs in the user's browser. Use when debugging a page, web app, browser game or bookmarklet that misbehaves on the user's device, when the user says "it doesn't work" about a page and you need to see what happened, when you want to add console.log instrumentation and read it back, when you need to see what happens on a specific button, field or element, or when the user hands you an OTLP JSON log export or a file named agent-log-*.json.
- ▌ Orchestrating Skills · oaustegard bundleSkill-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-chat-agents spawns too many redundant subagents.
- ▌ Reading Business Cards · oaustegard bundlePreprocesses photographed sheets of many business cards — slicing each into overlapping high-resolution tiles and de-glaring them with container tooling (OpenCV/ImageMagick) — then reads every card via cheap parallel temperature-0 API calls (Haiku or Sonnet) using a distilled extraction prompt, and writes deduped contact fields to a CSV. Use when a user has photos or scans holding multiple business cards per image, mentions glare or unreadable cards, batch card transcription, contact extraction, or wants to read many cards without an expensive in-conversation pass. Triggers on 'business cards', 'card scan', 'extract contacts', 'read these cards', 'card glare', 'too many cards per photo'.
- ▌ Reasoning Semiformally · oaustegard bundleApply semi-formal certificate reasoning to code analysis — patch verification, fault localization, patch equivalence. Use when reviewing patches, hunting bugs across scopes, comparing fixes, or when code reasoning requires tracing execution across files/modules. Triggers on code review, bug localization, patch comparison, name shadowing, scope analysis, regression checking.
- ▌ Generative Thinking · oaustegard bundleBreak out of a locked problem frame by picking one disciplined move — reframe, provocation (Po), random stimulus, SCAMPER, inversion, structured analogy, constraint play, or family traversal — and committing to it before evaluating. Use when stuck, when options feel narrow or obvious, when iterations produce variations of the same idea, or when the user says "widen this", "break out of", "think differently", "I'm stuck", "feels too obvious", "stress-test the framing", "what am I missing", or holds two related examples and asks what lies between or beyond them. Complements challenging (which evaluates) and convening-experts (which synthesizes viewpoints); this skill generates distance, not judgment.
- ▌ Transcribing Images · oaustegard bundleReads the visual content of slides, pages, and images the way a human would, not just their embedded text. Use when a PPTX or PDF has image slides, screenshots, charts, scanned figures, or flattened-to-image layouts that the built-in pptx/pdf skills read as empty; when asked to transcribe, describe, OCR, or extract what is shown in an image, slide deck, or document page; or when embedded-text extraction returned little or nothing from a visually rich file. Triggers on 'read this deck', 'what's on these slides', 'transcribe', 'OCR', 'extract text from image', 'describe this chart/diagram', .pptx/.pdf/.png/.jpg with visual content.
- ▌ Orchestrating Agents · oaustegard bundleDEPRECATED, renamed to orchestrating-chat-agents. Kept so existing imports of its scripts keep working; every module here loads the same module from orchestrating-chat-agents. Use orchestrating-chat-agents for parallel Claude calls over the API from claude.ai, and dispatching-subagents for fan-out in Claude Code.
- ▌ Declauding · oaustegard bundleLoad it without being asked at the start of any task whose deliverable is prose that another person will read, such as a PR description, commit message, README, doc, postmortem, blog post, issue or review comment, report, release note or essay, and run it on the draft before the text is pushed, posted, published or saved. Draft first without this skill in context, from a positive writing brief if one exists. Also use it when someone says "de-claude", "de-slop", "humanize this", "this reads like AI" or "make it sound human", or asks for a voice, tone or register edit. It rewrites the constructions that mark prose as model-written into plain technical prose, and checks that the rewrite kept the draft's claims. The constructions include staged reveals, verdict headers, aphoristic closers, "it's not X, it's Y", em-dash drama, forced triads, flat-certainty adverbs, noun stacks and dropped 'that'. Do not use it on fiction, poetry, code or quoted text. For a full adversarial review of a deliverable, use challenging.
- ▌ Challenging · oaustegard bundleCross-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".
- ▌ Exploring Codebases · oaustegard bundleFirst-encounter orientation on a repository nobody here has worked in yet. Runs a fixed five-step workflow — venv setup, tarball fetch, tree-sitting structural scan, featuring synthesis, then reasoning over the two — and yields an account of what the repo contains and how it is arranged, optionally written out as _FEATURES.md. Use for "I just cloned this", "what is this repo", "what does this do", "explore this repo", "give me an orientation", "what are the main features", "review what's new in this repo", or before starting work in a codebase you have not seen. This is the divergent what's-here skill. Route elsewhere for: a named symbol, a file's structure or a line range (tree-sitting); all callers of a Python symbol (searching-codebases); teaching a human the codebase through exercises (orienting-codebases); fetching or cloning a repo without analysing it (accessing-github-repos, cloning-project).
- ▌ Browsing Bluesky · oaustegard bundleBrowse Bluesky content via API and firehose - search posts, fetch user activity, sample trending topics, read feeds and lists, analyze and categorize accounts. Supports authenticated access for personalized feeds. Use for Bluesky research, user monitoring, trend analysis, feed reading, firehose sampling, account categorization.
- ▌ Convening Experts · oaustegard bundleConvenes expert panels for problem-solving. Use when user mentions panel, experts, multiple perspectives, MECE, DMAIC, RAPID, Six Sigma, root cause analysis, strategic decisions, process improvement, or asks for philosophers/ancients (Socratic, Aristotelian, Stoic method experts).
- ▌ Mapping Documents · oaustegard bundleGenerate navigable semantic maps from PDF documents. Extracts section structure via font analysis, then runs LLM extraction per section for claims, symbols, and dependencies — all page-anchored. Produces _MAP.md (progressive disclosure), .symbols.json (definition index), .anchors.json (claim references), and a _USAGE.md snippet for CLAUDE.md. Use when analyzing papers, specs, or legal docs; when asked to "map this document", "index this PDF", "what does this paper say"; or when a coding agent needs grounded reference material from a PDF source. Analogous to tree-sitting but for prose documents.
- ▌ Down Skilling · oaustegard bundleDistill Opus-level reasoning into optimized instructions for Haiku 5.5 (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.
- ▌ Exploring Data · oaustegard bundleExploratory data analysis. Use when users upload .csv/.xlsx/.json/.parquet files or request "explore data", "analyze dataset", "EDA", "profile data". Small files get ydata-profiling HTML/JSON reports; large files (over 200MB or 5M rows) get fixed-memory DuckDB/sketch profiling. Also covers near-duplicate row detection, cross-file key overlap ("can these join?"), dataset drift vs a stored baseline, and time-series profiling.
- ▌ Mapping Webapp · oaustegard bundleGenerate behavioral/feature documentation for web apps using code-first analysis. Reads source code via tree-sitting to produce _FEATURES.md, with optional visual verification via browser automation. Companion to tree-sitting. Use when documenting app behavior, creating feature inventories, generating behavioral ground truth for agents, or before modifying UI code. Triggers on "map features", "document app behavior", "feature inventory", "what does this app do".
- ▌ Invoking Gemini · oaustegard bundleInvokes Google Gemini models for structured outputs, image generation, text-to-speech narration, multi-modal tasks, and Google-specific features. Use when users request Gemini, image generation, Gemini TTS or a synthesized voice, structured JSON output, Google API integration, or cost-effective parallel processing.
- ▌ Image To Svg · oaustegard bundleConvert raster images (photos, paintings, illustrations, line art) into SVG vector reproductions. Use when the user uploads an image and asks to reproduce, vectorize, trace, or convert it to SVG. Also use when asked to decompose an image into shapes, create an SVG version of a picture, or faithfully reproduce artwork as vector graphics. Handles graphic/line-art inputs (Kandinsky, architectural drawings, ink work) via a compositional pipeline that extracts lines as SVG strokes. Do NOT use for creating original SVG illustrations from text descriptions — only for converting existing raster images.
- ▌ Tree Sitting · oaustegard bundleSymbol-level navigation of a local checkout using tree-sitter ASTs. Answers where a symbol is defined, what lines it spans, which symbols a file exposes, what a directory holds, and where a name is referenced — every answer carries exact line ranges to feed straight into a scoped read. Use for "where is X defined", "who calls X", "find the function/class named", "what's in this file", "give me the line range for", "show me the source of", "list the symbols in", or before editing a file you have not read. Each invocation auto-scans and is self-contained. Not for first-encounter repo orientation (use exploring-codebases), for what a codebase DOES rather than what it contains (featuring), for binding-resolved Python caller sets (searching-codebases), or for literal text and regex matching (plain ripgrep).
- ▌ Agent Routing · oaustegard bundleDecide which model, effort level, and cascade shape each subagent gets, and how to keep improvement loops safe (evaluator-as-selector, stop on regression). Routes on measured cost-per-completed-task rather than per-token price, because a tier's token count varies more by task shape than price varies across tiers. Covers per-model effort semantics, the concision lever, cascade preconditions, context handoff, and watching a subagent fan-out live. Use when choosing a subagent's model or effort, when choosing how to escalate a failed attempt, or when asked which model or effort a task should get. Grounded in a 2026-07 calibration, a 2026-08 coding-cost study, a 2026-09 seeded-bug repair battery, a 2026-10 Haiku 5.5 ladder priced per spawn, a 2026-10 retry-versus-escalation ladder on 295 SWE-bench Verified tasks, and a 2026-11 Haiku-swarm-versus-Sonnet-loop search at equal spend; Managed Agents API specifics are operational, not calibrated.
- ▌ Verifying Review Findings · oaustegard bundleChecks each finding from a code review against the code it cites and keeps only the ones that hold. Drops findings whose quoted code is not in the file, then asks TypeSafe's Jev decision model whether the code shown really has the claimed defect, returning P(confirmed), P(refuted), a severity distribution and whether the proposed fix works. Use for "verify these review findings", "filter false positives from the review", "is this bug real", "double-check the reviewer's claims", "get a second opinion on these findings", a pre-commit or CI gate that blocks only on confirmed high-severity findings, or a finder-then-verifier review with a different model as the verifier.
- ▌ Dispatching Subagents · oaustegard bundleChooses how to launch subagents from Claude Code (the Agent tool, a Workflow script, or headless claude -p children) and runs a headless fan-out from one background command. Use for "fan this out to 50 agents", "run these tasks in parallel", "launch subagents for each file", "should I spawn agents or write a workflow", "batch this through Haiku", "run claude -p in parallel", "dispatch a task list without the launches eating my context", or before any launch of more than a handful of subagents, where the launching itself is the cost. Covers the parent-turn cost of each mechanism, concurrency ceilings, what context and tools each child gets, effort control, output contracts, a cost ledger, and resume after interruption.
- ▌ Making Remotion Videos · oaustegard bundleMake an MP4 from React components with Remotion, rendered headlessly in this container. Covers project scaffolding with pinned versions, the frame-pure composition contract, the still-frame review loop, rendering with the preinstalled Chromium, and the product demo reel - an app shown inside a phone frame, built from Playwright captures of the real UI. Use for 'Remotion', 'make a video in React', 'demo reel', 'promo video for my app', 'app preview video', 'product video', 'phone mockup video', 'vertical video for social', 'Instagram reel', 'TikTok-format video', 'animated explainer with text and screenshots', or any motion graphics job built from layout, type and UI captures.
- ▌ Delegating With Context · oaustegard bundleDelegates work to a subagent or spawned session by writing only the task, while a PreToolUse hook pages the parent transcript through Jev and appends the chunks that task needs. Use before writing any Agent tool prompt or create_session prompt, and when asked to delegate this, hand this off, use a subagent, spawn an agent, run agents in parallel, or brief a subagent on what we have done so far.
- ▌ Making Tinyoffice Links · oaustegard bundleMakes small documents as shareable Tiny Little Office links, where the URL itself is the document. Covers slide decks, posters, zines, spreadsheets, charts and small-business models, letters, résumés, invoices, outlines, diagrams (mind map, org chart, family tree, swimlanes, timeline, Venn, seating, network), drawings, pixel art, animations, calendars, Gantt schedules, trip maps and a calculator that shows its working. Use when someone wants such a document as a link they can open, edit and pass on rather than a file, or names tinylittleoffice / TLO.
- ▌ Deciding With Confidence · oaustegard bundleRoutes, triages, flags and rates a piece of text with a probability for every option: which department or queue a ticket goes to, which intent a message expresses, whether a yes/no condition holds (is this tool call grounded, should the agent ask first, is the customer angry), and how severe or urgent it is on a rubric, each with a calibrated confidence. Runs Claude Haiku in the request and response shapes of OpenAI's Decisions API, or of TypeSafe's System One API (Jev's), for when no purpose-built decision model is at hand. Use for "route this ticket", "triage these", "classify with a confidence", "give me a probability that", "rate the severity", "score against this rubric", guardrail checks before a tool call, "a Decisions API without OpenAI", or a stand-in for Jev.
- ▌ Making Kinescript Videos · oaustegard bundleMake an MP4 from a JSON scene file with Kinescript (drknowhow/kinescript, the `kine` CLI): text, shapes, charts, SVG, images, video clips, particles and 3D models on cue-based timing, with a checker that lints layout, contrast, reading time and the sound mix, and narration spoken by Kokoro TTS with word-level cues and captions. Covers setup in a Linux container (CPU backend, Python 3.12 venv for Kokoro), the write → voice → check → look → render loop, and controlling Kokoro's pronunciation, stress, pauses, pace and voice blends. Use for 'kine', 'Kinescript', 'kinescript scene', 'kine voice', 'narrated promo', 'explainer video', 'motion graphics video', 'video with voice-over and captions', 'Kokoro pronunciation', 'TTS says a name wrong', 'make the narrator emphasise', 'video thumbnail is blank', 'poster frame', or any video built from type, shapes and captured footage.
- ▌ Orchestrating Chat Agents · oaustegard bundleFans Claude work out over the Anthropic API from surfaces with no native subagents, chiefly claude.ai chat and projects, with parallel calls with a shared cached context, streaming, long-lived conversation threads with cached history, and named agent pools; also delegates to Gemini through the Cloudflare AI Gateway on any surface. Use for multi-perspective analysis, a panel of reviewers, or task decomposition from claude.ai, or for Python code that calls several Claude instances concurrently over the API.
- ▌ Curating Bsky List · oaustegard bundleBuilds and maintains Muninn's own Bluesky curate list ("Muninn reads", on the muninn.austegard.com account). Accounts are chosen by per-topic classifiers on Ettin-17m post embeddings (topics are Muninn's interests and the clusters of Oskar's experiments atlas), plus about a third picked for exploration, outside every topic, and judged only on whether they write thoughtfully. Also turns the list's past week of posts into a digest so Muninn can save dated insights. Use for "build Muninn's list", "refresh Muninn's Bluesky list", "the weekly list refresh", "read Muninn's list", "what did the list post this week", "promote a theme to a topic", or a routine that runs the weekly refresh. Writes only list items on Muninn's own list. Not for Oskar's lists or one-off list building from a source (muninn_utils.bsky_list), and not for general Bluesky search or browsing (browsing-bluesky).
- ▌ Listening To Music · oaustegard bundleListen to generated music by measuring it and by reading it as sheet music: render Strudel code or record a Web Audio page through the real engine in headless Chromium, then read spectrograms, pYIN pitch lines, chroma, roughness and semitone-rub meters; engrave notes as a score with beat-by-beat harmony; transcribe a melody from audio; read MusicXML/MIDI/ABC or a score image into notes and into Strudel code. Use to check whether generated music sounds right or better (before/after a change), to match a reference track, spectrogram image or score, or to find discordant chords, a buried melody, clipping or muddy mixes. Triggers on 'does it sound better', 'listen to', 'render and check', 'spectrogram', 'sfft/stft', 'discordant', 'clashing chords', 'sounds off', 'compare to the original', 'reproduce this track in Strudel', 'sheet music', 'score', 'notation', 'MusicXML', 'MIDI', 'ABC', 'transcribe', 'OMR'. Pairs with strudeling (writing Strudel); for format conversion use processing-video.
- ▌ Animating With Code · oaustegard bundleMake a short animated film by writing the drawing code yourself: every frame a pure function of time, rendered headlessly to MP4. Covers storyboarding with a per-shot timing sheet of viewer 'reads', blocking key poses as stills, the contact-sheet / frame-strip / crop review loop, and the hand-painted character kit JohnHeibel/ClaudeAnimationBase (p5.js + p5.brush, the Clawd mascot, 31 emotions). Use for 'animate', 'make a cartoon', 'animated short', 'motion graphic', 'Clawd video', 'p5 animation', or any video request where Claude draws the frames. Not for AI-generated footage (creating-video), transcoding or trimming existing video (processing-video), or a comic from footage (drawing-video).
- ▌ Describing Products · oaustegard bundleBuilds a product description repo for a software product - prose documents that say, feature by feature and event by event, what the user sees, what they can do, and exactly what happens when they do it, including when they stop halfway. Drafted from the code and tests, verified against the running product with hand checklists, and triaged into a bug list. Works for canvas editors, web apps, CLIs, chat products, mobile apps, and libraries or SDKs. Use when asked to "write a product description for X", "describe the user experience of X", "document how X behaves for the user", "make a behavior-spec repo", or for an event-by-event account of an app's behavior rather than API docs. Also resumes or extends an existing product description repo.
- ▌ Dunking Anonymously · oaustegard bundleRenders a Bluesky post as an anonymised screenshot so its words can be criticised without a link back to whoever wrote them. Blacks out avatar, display name, handle and any at-mentions in declassified-document styling, then emits a PNG and its alt text. Use for anonymous dunk-quoting, "dunk on this without linking it", "screenshot this post with the author hidden", "quote this without naming them", "redact this before I share it", or when a bad take from a small account deserves an answer and its author does not deserve your followers.
- ▌ Drawing With Pycairo · oaustegard bundleDraws images, PDF/SVG vector files and animation frames with pycairo, and supplies what cairo lacks: shaped text for Arabic, Indic and other scripts, text along curves, blur/glow/drop shadows, path booleans, stroke-to-outline, and Gouraud-shaded 3D. Use when writing pycairo or cairo drawing code, generative art, custom diagrams or posters rendered in Python, or when cairo output needs non-Latin text, soft effects, merged shapes or shaded surfaces.
- ▌ Evolving With Swarms · oaustegard bundleImproves a program against an automatic scorer by running rounds of cheap Haiku 5.5 swarms, where each proposer suggests one short idea and one writer per swarm turns the ideas into a new program that is scored and kept in an archive, all metered to a dollar cap through headless claude -p. Use for "evolve this program against my evaluator", "optimize this function's score cheaply", "OpenEvolve-style search on a budget", "AlphaEvolve-style construction search with Haiku", "run a swarm to maximize this score", "search for a better heuristic or construction", or any program whose quality a script can score, when the budget is small. Ships the driver, a gateway with a dollar cap and a usage-window pause, a sandbox hook for model-written code, an example problem and an offline selftest; runs from Claude Code on the web or the desktop.
- ▌ API Credentials · oaustegard bundleSecurely manages API credentials for multiple providers (Anthropic Claude, Google Gemini, GitHub). Use when skills need to access stored API keys for external service invocations.
- ▌ Marking Up Pages · oaustegard bundleLet the user draw on a live web page in Chrome (circle, underline, arrow) and type a note per mark, then read back what each mark points at - element, selector, computed styles, React/Vue/Svelte component and source file - plus console errors and failed requests, and fix it. Uses Claude in Chrome. Use when the user wants to mark up, annotate, scrawl on or point at something on a page, says "let me show you", "look at my marks", "I circled it", or asks for visual feedback on a site or local dev server.
- ▌ Swarming To Green · oaustegard bundleRuns a long swarm of hundreds to thousands of cheap headless coding workers that drive a large failing-test backlog to green. Failures are clustered by signature, each worker fixes one cluster in its own git worktree, a serial no-regression merge gate lands the fixes, the loop resumes across restarts for hours, and it federates across sibling sessions over git branches when one container's CPU is not enough. Use for "fix these thousands of failing tests with a Haiku swarm", "drive the test suite to green with hundreds of agents", "build this compiler or interpreter against a conformance suite", "launch, relaunch or check in on the swarm loop", "the swarm is stuck, idle or rejecting everything", "parallel agents fixing tests keep hitting merge conflicts and regressions", "add sibling containers to the swarm", or "compare models on the tail the swarm could not fix". Ships the harness, a per-project TOML config, a fake-worker selftest, check-in signals and the 2026-10-12 haiku-cc failure catalogue.
- ▌ Muninn Boot 3 · oaustegard bundlePuts oaustegard/muninn-utilities on the container Python path — runs scripts/boot.sh, which shallow-clones the repo (codeload tarball as fallback) and writes the .pth. The boot payload itself comes from the Muninn MCP connector: call its `boot` tool after this script. Trigger on the first message of any new Muninn conversation, or when the user says "boot up" / "boot" — unless the message contains "skip boot". Idempotent: a warm container exits in ~0s via a sentinel.
- ▌ Ocring Pdfs · oaustegard bundleAdds a searchable text layer to a scanned PDF with ocrmypdf. Installs the toolchain at runtime in ~18s. Use when a PDF's pages are images and the deliverable is a file to keep, grep, or hand to another tool: 'make this PDF searchable', 'OCR this scan', 'I can't select the text in this PDF', 'search across these scanned pages', 'the pdf skill returned nothing'. Handles non-English scans via tesseract language packs. NOT for charts, diagrams, handwriting, or slide layouts. Route those to transcribing-images.
- ▌ Tiling Tree · oaustegard bundleExhaustive problem space exploration using the MIT Synthetic Neurobiology "tiling tree" method. Partitions a problem into MECE (Mutually Exclusive, Collectively Exhaustive) subsets recursively via parallel subagents, then evaluates leaf ideas against specified criteria. Use when users say "tiling tree", "tile the solution space", "exhaustively explore approaches to", "what are all the ways to", or request a MECE breakdown of a problem. Requires orchestrating-chat-agents skill.
- ▌ Compiling Wgsl · oaustegard bundleProduces and shrinks WGSL shaders. Converts GLSL (WebGL 1 and 2, Shadertoy mainImage code, Vulkan GLSL 450, compute shaders) to WGSL and checks the port pixel by pixel against WebGL; minifies a WebGPU shader (renaming, dead code, literal and type shortening) and proves the result unchanged with naga, Chrome's Tint and bit-identical compute runs; compiles an SVG file or a Python-built scene of circles, rects, paths, gradients and animated transforms into one resolution-independent WGSL fragment shader. Use for convert GLSL to WGSL, port this Shadertoy to WebGPU, WebGL shader to WebGPU, minify this WGSL, shrink my shader, make the shader smaller, WGSL optimizer, turn this SVG into a shader, draw this icon in WebGPU, SDF shapes in WGSL, smooth union shapes, animated vector graphics on the GPU, pretty-print WGSL.
- ▌ Optimizing Skills 3 · oaustegard bundleDisciplined, 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.
- ▌ Muninn Boot 2 · oaustegard bundleBoot (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".
- ▌ Mapping Codebases 3 · oaustegard bundleGenerate 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.
- ▌ Gating 2 · oaustegard bundleBuild and audit deterministic verification gates — a check that blocks a pipeline and can be shown to go red. Use when writing a calibration gate, CI check, validation script or pre-publication check for a numeric or empirical result; when a plausible-but-wrong value would survive review; when asking whether an existing test, linter rule or check could actually fail; and when a suite passes first try, passes suspiciously often, or was written by whatever produced the thing it checks. Triggers on "can this check fail", "known-bad", "negative control", "calibration gate", "sanity check my results", "is this test actually testing anything".
- ▌ Githubbing 2 · oaustegard bundleInstalls and authenticates the GitHub CLI (gh) in a Claude.ai container, then runs gh commands against it. Use for "install gh", "gh auth", "create an issue or PR from the CLI", "gh is not authenticated", or any GitHub operation you want to issue as a gh command rather than a raw API call. This skill is the transport rather than the analysis. To understand what a repository does or contains, use exploring-codebases; to add a repo to the session, accessing-github-repos.
- ▌ Bm25 2 · oaustegard bundleRanked content search over a text corpus you point it at, using BM25 (via xhluca/bm25s). Corpus-agnostic: cloned repos, project knowledge stores, uploaded files and archives, any local directory. In-memory BM25 index per invocation, with a session-local disk cache for repeat runs against the same corpus. Use for "rank these documents", "search this corpus", "which files are most about X", "find content about Y", or any multi-word concept query against a known body of text where grep would return everything or nothing. Needs a corpus on disk. Not for searching stored memories or prior-session decisions (remembering), not for a named symbol or a file's structure (tree-sitting), and not for a literal string you could grep.
- ▌ Opening Prs 2 · oaustegard bundleOpen a GitHub PR via API as a flowing graph — branch + push + create_pr + mergeable poll, with structural protection against pushing to main/master/etc. Use when a Claude Code or Claude.ai container needs to land changes on GitHub via the API (no git CLI required) and the prose "create branch, push, open PR, wait for mergeable" workflow keeps drifting under context pressure.
- ▌ Featuring 2 · oaustegard bundleGenerate hierarchical _FEATURES.md files that describe what a codebase DOES from a user/consumer perspective, anchored to source symbols via tree-sitting. Supports large complex codebases through feature-driven decomposition into sub-feature files. Uses a multi-pass synthesis: orientation → detail → overview rewrite. Use when someone says "what does this do", "document features", "feature inventory", "_FEATURES.md", or needs to understand a codebase's purpose before modifying it. Complements tree-sitting (structural) with semantic (why/what-for) layer.
- ▌ Challenging 2 · oaustegard bundleCross-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".
- ▌ Python Lsp 2 · oaustegard bundleSemantic Python code queries via a stdio LSP client driving pyright-langserver. Provides binding-resolved go-to-definition, find-references, hover types, type diagnostics, file symbol outlines, and project-wide symbol search — name resolution and type inference that tree-sitter and ripgrep cannot do. Use when you need to follow an import to a definition, find all real uses of a symbol (excluding same-named-but-unrelated ones), get an inferred type, surface type errors, outline a file, or search symbols across a project. Triggers on "go to definition", "find references", "what type is", "resolve this symbol", "symbol outline", "find symbol in project", "pyright", "type-check this file".
- ▌ Check Tools 2 · oaustegard bundleValidates development tool installations across Python, Node.js, Java, Go, Rust, C/C++, Git, and system utilities. Use when verifying environments or troubleshooting dependencies.
- ▌ Closing Issues 2 · oaustegard bundleClose a GitHub issue with a synthesis comment as a flowing graph — validate the synthesis, post the closing comment, close, then run a pluggable callback (e.g. memory store) detached. Use when closing an issue should also capture the LEARNING (not just the diff log) and when the post-close work shouldn't block the close ack.
- ▌ Image To Svg 2 · oaustegard bundleConvert raster images (photos, paintings, illustrations, line art) into SVG vector reproductions. Use when the user uploads an image and asks to reproduce, vectorize, trace, or convert it to SVG. Also use when asked to decompose an image into shapes, create an SVG version of a picture, or faithfully reproduce artwork as vector graphics. Handles graphic/line-art inputs (Kandinsky, architectural drawings, ink work) via a compositional pipeline that extracts lines as SVG strokes. Do NOT use for creating original SVG illustrations from text descriptions — only for converting existing raster images.
- ▌ Agent Routing 2 · oaustegard bundleDecide which model, effort level, and cascade shape each subagent gets, and how to keep improvement loops safe (evaluator-as-selector, stop on regression). Routes on measured cost-per-completed-task rather than per-token price, because a tier's token count varies more by task shape than price varies across tiers. Covers per-model effort semantics, the concision lever, cascade preconditions, context handoff, and watching a subagent fan-out live. Use when spawning subagents via the Agent or Workflow tools, when fanning out more than a handful of agents, or when asked which model or effort a task should get. Grounded in measured calibration (references/calibration-2026-07-15.md), a 2026-08 coding-cost study, and a 2026-09 agentic-repair battery that measured the cascade rungs directly; Managed Agents API specifics are operational, not calibrated.
- ▌ Down Skilling 2 · oaustegard bundleDistill 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.
- ▌ Tree Sitting 2 · oaustegard bundleSymbol-level navigation of a local checkout using tree-sitter ASTs. Answers where a symbol is defined, what lines it spans, which symbols a file exposes, what a directory holds, and where a name is referenced — every answer carries exact line ranges to feed straight into a scoped read. Use for "where is X defined", "who calls X", "find the function/class named", "what's in this file", "give me the line range for", "show me the source of", "list the symbols in", or before editing a file you have not read. Each invocation auto-scans and is self-contained. Not for first-encounter repo orientation (use exploring-codebases), for what a codebase DOES rather than what it contains (featuring), for binding-resolved Python caller sets (searching-codebases), or for literal text and regex matching (plain ripgrep).
- ▌ Flowing 2 · oaustegard bundleRuns a multi-step procedure as a Python DAG, so ordering, branching and retries are enforced by the runner rather than described in prose a model can generate past. Use for "run these steps in order and retry the flaky one until the check passes", "build a pipeline that fetches, validates, then skips the upload when nothing changed", "make sure these steps cannot be skipped", "resume from where it broke instead of redoing the expensive early stages", "run these independent calls at once and merge the results", or any procedure of 3+ steps with branches, input contracts, or side effects that must not block the critical path. Primitives are depends_on, when=, validate=, retry_until=, detached= and journal_path=. Not for a single sequential call, for steps needing reasoning between them that no predicate captures, or for async and distributed work. To audit whether one verification check can actually go red, use gating. To fan work out across many subagents, use a dynamic workflow.
- ▌ Invoking Github 2 · oaustegard bundleEnables GitHub repository operations (read/write/commit/PR) for Claude.ai chat environments. Use when users request GitHub commits, repository updates, DEVLOG persistence, or cross-session state management via GitHub branches. Not needed in Claude Code (has native git access).
- ▌ Iterating 2 · oaustegard bundleMulti-conversation methodology for iterative stateful work with context accumulation. Use when users request work that spans multiple sessions (research, debugging, refactoring, feature development), need to build on past progress, explicitly mention iterative work, work logs, project knowledge, or cross-conversation learning.
- ▌ Drawing Video 2 · oaustegard bundleTurn a short video into a narrated comic strip. Use when the user uploads a video (.mov/.mp4/etc.) and asks to make a comic from it, narrate it, draw it, Attenborough it, storyboard the clip, or otherwise wants a stills-plus-narration comic strip derived from footage. Covers probing and extracting frames, GROUNDING the actual storyline (native Gemini video parse or frame reading), composing narration in a chosen voice, generating comic panels with Gemini image models anchored to the real stills, QA-ing the panels, and compositing a titled strip. Do NOT use for plain video transcoding or trimming (that is processing-video) or for original illustration from a text prompt (that is invoking-gemini).
- ▌ Parsing Video 2 · oaustegard bundleInterpret video content visually by sampling frames into timestamped contact sheets that can be read as images. Use when: user asks what happens in a video; asks to summarize, describe, review, or QA video content or footage; asks about scenes, actions, people, or objects in a video; needs a storyboard-style overview of a clip; asks to find where something occurs in a video. Triggers on 'watch this video', 'what's in this video', 'summarize the video', 'describe the footage', 'contact sheet', 'storyboard', 'review this clip', 'find the scene where', 'scene detection', 'shot boundaries', 'detect cuts', 'dwell points'. For converting, trimming, or transcoding video, use processing-video instead.
- ▌ Seeing Images 2 · oaustegard bundleAugmented vision tools for analyzing images beyond native visual capabilities. Use when tasked with describing images in detail, reproducing images as SVGs, identifying subtle features, comparing image regions, reading degraded text, or any task requiring careful visual inspection. Also use when the image-to-svg skill needs ground truth about colors, shapes, or boundaries.
- ▌ Using Webctl 2 · oaustegard bundleBrowser automation via webctl CLI in Claude.ai containers with authenticated proxy support. Use when users mention webctl, browser automation, Playwright browsing, web scraping, or headless Chrome in container environments.
- ▌ Semantic Grep 2 · oaustegard bundleIn-process semantic search over text files or in-memory strings, using Gemini embeddings via the CF AI Gateway. Use when user wants fuzzy/conceptual search where exact-keyword grep would miss — "sessions discussing regulatory constraints", "code about retry logic", "notes mentioning burnout even if the word isn't there". Complements searching-codebases (regex/AST) and extracting-keywords (YAKE). Do NOT use when an exact string/regex match is what's wanted — grep/rg wins on speed and precision there.
- ▌ Creating Video 2 · oaustegard bundleCreate video from prompts by overseeing multi-clip AI generation end to end: write a shot list, generate each scene with Gemini Omni Flash (via the Cloudflare AI Gateway), review the results, and assemble them into a finished cut. Use when the user asks to make/generate a video, a short film, an animatic, or a multi-scene clip from a script or idea; when they mention Omni, Veo, text-to-video, or image-to-video; or when acting as the editing/director agent over generated footage. Triggers on 'make a video', 'generate a clip', 'short film', 'video from this script', 'turn this into a video', 'omni', 'veo', 'text to video', 'storyboard to video'. For transcoding/trimming/merging/GIF/subtitles use processing-video; for reading or summarizing existing video content use parsing-video.
- ▌ Atprotoing 2 · oaustegard bundleRead Bluesky/ATProto without depending on Bluesky's AppView — interactions on a user's posts, thread replies, any repo's records, network-wide backlinks across every lexicon, an account's handle and PDS history, which collections are active network-wide, and layer-by-layer outage diagnosis. Use when bsky.app or the AppView is down or slow, when a Bluesky read returns timeouts or 5xx, when asked who liked/replied/quoted/reposted something, when pulling live Bluesky context cheaply, when reading records straight from a PDS, when asked who references a record or account anywhere on the network, whether an account has changed handle or migrated servers, or which lexicons and non-Bluesky apps are active on atproto. Complements browsing-bluesky, which routes everything through the AppView and fails when it does.
- ▌ Invoking Gemini 2 · oaustegard bundleInvokes 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.
- ▌ Mapping Webapp 2 · oaustegard bundleGenerate behavioral/feature documentation for web apps using code-first analysis. Reads source code via tree-sitting to produce _FEATURES.md, with optional visual verification via browser automation. Companion to tree-sitting. Use when documenting app behavior, creating feature inventories, generating behavioral ground truth for agents, or before modifying UI code. Triggers on "map features", "document app behavior", "feature inventory", "what does this app do".
- ▌ Composing HTML 2 · oaustegard bundleComposes single-file HTML artifacts (PR review writeups, status reports, incident postmortems, slide decks, design systems, prototypes, flowcharts, module maps, feature explainers, kanban boards, prompt tuners) from a small JSON spec instead of hand-written HTML/CSS/JS. Use when the user asks to "compare options side-by-side", requests an HTML version of a report or review or deck, asks for a flowchart, status update, postmortem, design system reference, interactive prototype, custom editor — or explicitly says "HTML artifact", "single HTML file", "self-contained HTML". Skip for ad-hoc HTML snippets (forms, emails, embedded widgets) where there's no template fit.
- ▌ Creating Kb 2 · oaustegard bundleBuilds a portable, embedding-free knowledgebase from a set of files and delivers it as a self-contained `.skill` bundle (BM25 index + bundled searcher + query protocol). Use when a user wants to turn uploaded files, a folder, or a corpus into a searchable knowledgebase they can hand to any agent — phrased as "make a knowledgebase", "build a KB skill", "package these docs for retrieval", "create a searchable bundle", or references to a `.skill` KB. The output runs anywhere with Node or Python — no model, no install, no network. Distinct from `bm25` (ephemeral in-session search) and `building-github-index` (markdown project-knowledge index).
- ▌ Creating Skill 2 · oaustegard bundleBuilds and revises a complete skill DIRECTORY — SKILL.md, scripts, references, assets — and packages it. Use for "create a skill for X", "turn this into a skill", "update/improve this skill", "why doesn't my skill trigger", "review this SKILL.md", "package this skill", or when a repeated procedure should become a reusable artifact. Enforces the structure that makes skills work — a concrete procedure rather than a goal statement, an explicit applicability boundary, failure modes with their signals, a runtime verification step, and a description checked against the existing catalogue for confusability. For choosing whether the instruction should be a skill at all rather than project instructions or a prompt, use crafting-instructions. For writing quality inside the prose, use writing-instructions.
- ▌ Finding Skills 2 · oaustegard bundleDiscover and load skills on demand from /mnt/skills/user/. Use when you need a capability but don't know which skill provides it, when the boot-emitted skill list is names-only and you need a full description, or when you want to list the catalog. Verbs are list (names only), search (rank by name/description match against a query), and show (emit the full SKILL.md for a named skill).
- ▌ Verifying Claims 2 · oaustegard bundleCheck that a document's claims about code are actually true by reading the prose, the code, and the tests and reporting (or fixing) where they disagree. Use whenever the user wants to verify a README, guide, spec, or docstring still matches the code; whenever they mention documentation drift, doc-code sync, "is this still accurate", stale docs, or keeping docs/tests/code consistent; before publishing or merging a docs change; or as a periodic doc-accuracy sweep. The agent reads the prose's meaning directly — there is no claim-comment DSL to maintain. Pairs with TDD — the test suite is the deterministic behavioral gate, this skill is the semantic prose-vs-reality review.
- ▌ Converting Files 2 · oaustegard bundleConvert a file from one format to another inside the container — documents, images, audio, video. Routes to the right engine (pandoc, LibreOffice, ImageMagick, ffmpeg) by format pair. Triggers on "convert X to Y", "turn this docx into a pdf", "make a gif from this mp4", "md to docx", "batch-convert these images", or any single-file or batch format change where the source and target extensions differ. NOT for editing content (use docx/pptx/xlsx/pdf skills), creating files from scratch, or reading a file you already have in context.
- ▌ Processing Video 2 · oaustegard bundleAudio and video processing with ffmpeg. Use when: user asks to convert, trim, merge, compress, or transcode video or audio files; extract audio from video; create GIFs or animated WebP from video; add subtitles or watermarks to video; change video resolution, framerate, or codec; normalize audio loudness; extract frames from video; concatenate clips; create thumbnails from video; strip or add audio tracks; convert between audio formats (MP3, AAC, FLAC, Opus, WAV); adjust volume; apply video filters; stabilize shaky video; generate waveform or spectrum visualizations; probe media file metadata. Triggers on 'ffmpeg', 'video', 'audio', 'transcode', 'MP4', 'MKV', 'WebM', 'MP3', 'AAC', 'FLAC', 'Opus', 'WAV', 'GIF from video', 'extract audio', 'add subtitles', 'video to gif', 'compress video', 'trim video', 'merge videos', 'normalize audio', 'framerate', 'resolution', 'bitrate', 'codec', 'ffprobe', 'waveform', 'spectrogram'.
- ▌ Convening Experts 2 · oaustegard bundleConvenes expert panels for problem-solving. Use when user mentions panel, experts, multiple perspectives, MECE, DMAIC, RAPID, Six Sigma, root cause analysis, strategic decisions, process improvement, or asks for philosophers/ancients (Socratic, Aristotelian, Stoic method experts).
- ▌ Assessing Impact 2 · oaustegard bundlePre-change blast-radius report for a symbol or file. Walks tree-sitting references, augments with a plain-text scan over non-parsed files (configs, plain docs), and clusters affected sites by feature (`_FEATURES.md`) or top-level package. Use when about to refactor, rename, or delete something in a repo you don't own — "what breaks if I change `validateUser`", "who calls this", "is this safe to remove", "where is this used", "blast radius", "impact analysis". This is the CONVERGENT pre-change risk skill — for "what is this repo?" use exploring-codebases; for "where is X?" use searching-codebases.
- ▌ Svg Portrait Mode 2 · oaustegard bundlePortrait Mode for SVGs — foveated vectorization with 4-zone selective detail. Combines vision annotations, MediaPipe segmentation/landmarks, and optional saliency. Like phone portrait mode, but vectorized. Use when vectorizing a portrait or photo where subject detail should outrank background detail.
- ▌ Mapping Codebases 2 · oaustegard bundleDEPRECATED — superseded by tree-sitting. This skill generated persistent _MAP.md files; tree-sitting does the same AST extraction at runtime (~700ms for 250 files) with no artifact to write, commit, or keep in sync. Use tree-sitting for "map this codebase", "explore repo", "understand structure", or any code navigation task. The final working version is archived at release mapping-codebases-v0.8.0.
- ▌ Developing Preact 2 · oaustegard bundleSpecialized Preact development skill for standards-based web applications with native-first architecture and minimal dependency footprint. Use when building Preact projects, particularly those involving data visualization, interactive applications, single-page apps with HTM syntax, Web Components integration, CSV/JSON data parsing, WebGL shader visualizations, or zero-build solutions with vendored ESM imports.
- ▌ Querying Markdown 2 · oaustegard bundleQuery, filter, and transform Markdown structurally with mq — a jq-like CLI for Markdown. Use to extract headings/sections/code-blocks/links from .md files, build a table of contents, pull code blocks of a given language, slice or reshape LLM prompt/output Markdown, or batch-transform docs. Triggers on "extract sections from this markdown", "get all the code blocks", "jq for markdown", "mq", or any structural query over Markdown that grep/Read can't do cleanly.
- ▌ Session Memory 2 · oaustegard bundleMaintains a structured running-notes document during long work sessions. Use when the user says "session notes", "update notes", "start session notes", "show session notes", or when you recognize the current session has accumulated enough state (decisions, corrections, files touched, errors) that it risks being lost under context pressure. Stores notes as a procedure memory tagged [session-memory, active] so they survive container death within the same session thread.
- ▌ Tracking Todos 2 · oaustegard bundleMaintain a structured task list for the current session. Use proactively when a request requires 3+ distinct steps, the user provides multiple items, or complex work benefits from explicit progress tracking. Storage persists via Muninn config across container death. Adapted from Claude Code's TodoWrite tool.
- ▌ Inspecting Skills 2 · oaustegard bundleDiscovers and indexes Python code in skills, enabling cross-skill imports. Use when importing functions from other skills or analyzing skill codebases.
- ▌ Installing Skills 2 · oaustegard bundleInstall skills from github.com/oaustegard/claude-skills into /mnt/skills/user. Use when user mentions "install skills", "load skills", "add skills", "update skills", "refresh skills", or references a skill not currently installed.
- ▌ Optimizing Skills 2 · oaustegard bundleDisciplined, 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.
- ▌ Versioning Skills 2 · oaustegard bundleREQUIRED 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.
- ▌ Generative Thinking 2 · oaustegard bundleBreak out of a locked problem frame by picking one disciplined move — reframe, provocation (Po), random stimulus, SCAMPER, inversion, perspective shift, constraint play, or family traversal — and committing to it before evaluating. Use when stuck, when options feel narrow or obvious, when iterations produce variations of the same idea, or when the user says "widen this", "break out of", "think differently", "I'm stuck", "feels too obvious", "stress-test the framing", "what am I missing", or holds two related examples and asks what lies between or beyond them. Complements challenging (which evaluates) and convening-experts (which synthesizes viewpoints); this skill generates distance, not judgment.
- ▌ Reviewing AI Papers 2 · oaustegard bundleAnalyzes an AI/ML publication — paper, preprint, article, technical blog post — and extracts what an enterprise AI engineer should do about it. Use when someone supplies a URL or document on RAG, embeddings, fine-tuning, prompt engineering, agents, or LLM deployment and asks "review this paper", "what do you make of this", "is this worth adopting", or "summarise the method and its limits". The subject matter must itself be machine learning.
- ▌ Building Github Index 2 · oaustegard bundleGenerate progressive disclosure indexes for GitHub repositories to use as Claude project knowledge. Use when setting up projects referencing external documentation, creating searchable indexes of technical blogs or knowledge bases, combining multiple repos into one index, or when user mentions "index", "github repo", "project knowledge", or "documentation reference".
- ▌ Cloning Project 2 · oaustegard bundleExports a Claude.ai workspace — its custom instructions and its uploaded knowledge files — into a bundle that can be re-imported elsewhere. Use for "back up my project instructions", "export my project knowledge", "copy this workspace to a new one", "migrate my project to another account", or "recreate this setup somewhere else". Operates on the Claude.ai workspace you are talking in, and reads nothing from disk.
- ▌ Transcribing Images 2 · oaustegard bundleReads the visual content of slides, pages, and images the way a human would, not just their embedded text. Use when a PPTX or PDF has image slides, screenshots, charts, scanned figures, or flattened-to-image layouts that the built-in pptx/pdf skills read as empty; when asked to transcribe, describe, OCR, or extract what is shown in an image, slide deck, or document page; or when embedded-text extraction returned little or nothing from a visually rich file. Triggers on 'read this deck', 'what's on these slides', 'transcribe', 'OCR', 'extract text from image', 'describe this chart/diagram', .pptx/.pdf/.png/.jpg with visual content.
- ▌ Invoking Antigravity 2 · oaustegard bundleInstall and drive Google's Antigravity CLI (`agy`) as a non-interactive sub-agent. Use when orchestrating agy, running Antigravity agents from a script or sandbox, delegating a task to Google's agent harness, or wanting a Gemini-backed peer agent alongside Claude.
- ▌ Orchestrating Agents 2 · oaustegard bundleOrchestrates parallel API instances, delegated sub-tasks, and multi-agent workflows with streaming and tool-enabled delegation patterns. Routes by surface — native subagents in Cowork and Claude Code, httpx fan-out on claude.ai — and covers Gemini delegation via the Cloudflare AI Gateway on every surface. Use for parallel analysis, multi-perspective reviews, or complex task decomposition.
- ▌ Exploring Codebases 2 · oaustegard bundleFirst-encounter orientation on a repository nobody here has worked in yet. Runs a fixed five-step workflow — venv setup, tarball fetch, tree-sitting structural scan, featuring synthesis, then reasoning over the two — and yields an account of what the repo contains and how it is arranged, optionally written out as _FEATURES.md. Use for "I just cloned this", "what is this repo", "what does this do", "explore this repo", "give me an orientation", "what are the main features", "review what's new in this repo", or before starting work in a codebase you have not seen. This is the divergent what's-here skill. Route elsewhere for: a named symbol, a file's structure or a line range (tree-sitting); all callers of a Python symbol (searching-codebases); teaching a human the codebase through exercises (orienting-codebases); fetching or cloning a repo without analysing it (accessing-github-repos, cloning-project).
- ▌ Orienting Codebases 2 · oaustegard bundleInteractive codebase orientation for a HUMAN who wants to learn the code. Runs the same tree-sitting + featuring pipeline as exploring-codebases but synthesizes it into guided exercises and an HTML teaching artifact rather than an analysis document. Use for "orient me to this repo", "teach me this codebase", "walk me through this code", "learning orientation", or when someone wants genuine comprehension rather than a task completed. The audience is the test: if nobody is being taught and the goal is to get work done, use exploring-codebases instead.
- ▌ Searching Codebases 2 · oaustegard bundleBinding-resolved Python symbol queries via pyright — every true caller (--refs), the real definition (--def), or an inferred signature (--hover) of a .py symbol, excluding the same-named false positives text search cannot tell apart. Use when a task needs ALL callers or users of a named Python symbol and grep would over-match. Python only, and only for the caller/definition question: measured 2026-07-04 on real issue-localization tasks, plain ripgrep tied or beat the semantic and indexed-regex tiers at 4-60x less wall-clock, so those tiers survive below without being a default.