wilbeibi
User16 agent skills for Claude Code and Codex — code review, test writing, docs, planning, codebase onboarding, repo evaluation, paper search, and Obsidian capture/search. Install with npx skills.
Categories
Indexed Skills (23)
grill-me
Interview the user one question at a time until a plan is resolved, capturing durable decisions in CONTEXT.md or ADRs when the repo warrants it. Use when asked to "grill me," stress-test a design, or challenge assumptions before implementation.
dataviz
Design and implement evidence-first charts from real data for technical blogs, reports, READMEs, and product explainers. Use when asked for a benchmark graph, data illustration, performance chart, tradeoff plot, small multiple, or an editorial chart in React/Recharts or a static plotting stack. Do NOT use for text-only diagrams (use show-me), hand-drawn conceptual art (use sketch-concept), or dashboard UI design.
route-skill
Discovers skills in the wilbeibi-skills catalog and loads explicitly selected skills from local files or cache, fetching missing skills. Use when asked to use an unavailable skill by name, find a suitable skill, or when no available skill clearly fits a substantive task. Do NOT treat a question about a skill as permission to use it.
sketch-concept
Generate a playful hand-drawn illustration that explains one technical mechanism or data insight — architecture, concurrency, storage, caching, queues, retries — for a blog post, doc, or slide. Use when asked for an illustration, a hand-drawn or Excalidraw-style visual, or a picture that makes one engineering idea click. Do NOT use for answering in-chat with a text diagram (use show-me) or for charts of real data (use dataviz).
readback
Put a long reply of your own - or a plan, document, or session transcript - on an HTML page the user reads, highlights, and comments on, returning their notes as a follow-up prompt through a waiting local command. Use when your answer is too long to review in a terminal, when the user wants to mark up or annotate a document, or when you want line-level feedback on a plan before implementing it. Do NOT use to collect answers to specific open decisions (use questionnaire) or to interview the user one question at a time (use grill-me).
write-skill
Author or update compact agent skills under skills/<name>/SKILL.md. Use when asked to write, add, or change a skill; not to audit a skill library.
complexity-budget
Assess ownership, coupling, and value before a substantial design change when explicitly requested. Use code-review for completed changes.
karpathy-planning
Develop a scoped implementation plan when explicitly asked to plan a coding task. Use grill-me for a deliberate design interview.
skill-curator
Audit a skill library for duplicated guidance, contradictions, bloat, dead references, and defects. Use when cleaning, consolidating, or de-duplicating a skills tree.
test-writing
Write and repair tests that verify observable behavior, not implementation. Use when writing or reviewing tests, choosing test scope or mocks, fixing brittle tests, or deciding whether a failing test means the code is wrong or the test is.
show-me
Explain code structure, dataflow, or proposed changes with a compact tree, pseudocode, type signature, diff, or diagram. Use when a visual clarifies those relationships; whole-repo briefings belong to grok-repo.
sherlock
Work an open question like a case — graded clues, competing theories in a consistency matrix, eliminate by evidence, backtrack, converge, with a casebook on disk for long cases. Use for puzzling bugs, reverse-engineering how a product works from public signals, or "what actually happened here". Do NOT use for planning (use karpathy-planning), repo tours (use grok-repo), or diff review.
grok-repo
Explain an unfamiliar codebase through a repository briefing, dataflow trace, or reconstruction of why and how a change was made. Use when asked for a repo tour, how something works, where a value comes from, or why a feature changed. Not for repo health (use repo-eval).
code-review
Review a diff, package, or API through one of five lenses (necessity and layering, honest invariants and costs, product-versus-library fit, a complexity gate before a design change, or newcomer clarity). Use when asked to review, audit, or polish code, vet a dependency, judge whether a change is too complex, or find what a new hire would not understand.
hammerspoon
Operate macOS via Hammerspoon, either one-off `hs -c` Lua (launch, quit, or focus apps and browser tabs; volume, wifi, caffeinate, alerts, clipboard) or persistent hotkeys, watchers, and menubar items in ~/.hammerspoon. Use when asked to control an app, tab, or Mac system state, keep the Mac awake, or write a Hammerspoon module. Not for web page content.
obsidian-capture
Append todos, logs, learnings, and reflections to Obsidian daily or weekly notes and run the agent's
paper-search
Find and rank research papers by relevance, recency, field-adjusted impact, venue, and author affiliation. Use when searching AI, agents, runtimes, storage, databases, infrastructure, recent or superseding work, company or lab research, or evidence for technical claims. Do NOT use for general web search or GitHub repository evaluation.
newcomer-lens-review
Review code for rationale, domain terms, constraints, and assumptions missing to a newcomer, and produce a documentation backlog. Use when asked for an onboarding review, what would confuse a new hire, what a handover is missing, or which parts of a codebase need documenting first. Do NOT use to find defects (use code-review) or to build your own understanding of unfamiliar code (use grok-repo).
obsidian-search
Search an Obsidian vault for topics, exact text, tags, recent notes, and tasks. Use when fuzzy, date-aware, due, or overdue note retrieval is needed.
questionnaire
Turn the open decisions from a long discussion into a self-contained offline HTML questionnaire the user fills at their own pace, whose answers come back as markdown keyed by stable question ids. Use when the user wants to finalize or confirm a design, align on accumulated decisions, review assumptions from notes/memory, or asks for a survey or questionnaire. Do NOT use for live one-question-at-a-time interviews (use grill-me).
repo-eval
Evaluate a public GitHub repository's momentum and maintenance health. Use when asked whether a repository is healthy, growing, declining, abandoned, or well maintained, or when vetting dependencies and OSS projects. Do NOT use for code or architecture review.
write-docs
Write or critique prose that ships with a codebase — READMEs, developer guides and runbooks, CLI text, code comments, agent guides, and commit or PR descriptions. Use when drafting, improving, or reviewing these artifacts. Do NOT use for design docs or internal wikis.
web-recap
Search browser history for URLs by topic or visit statistics. Use when asked about visited sites, browsing history, or recent online activity.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.