nibzard
- 37 skills
- 0 followers
- 6 hours ago last updated
- ▌ Git Xray · nibzard bundleRun diagnostic git commands to assess a codebase's health before reading any code. Use this skill whenever the user asks you to understand a new codebase, audit a repo, assess technical debt, find risky code, check project health, figure out where to start reading, identify bus factor risks, or explore an unfamiliar repository. Also use it when the user asks 'what's going on in this repo', 'where are the problem areas', 'give me a health check', or 'what should I look at first'. If the user wants to understand a codebase at a strategic level before diving into code, this is the skill to use.
- ▌ Steel Org Recon · nibzard bundleReconstruct what a Steel customer organization was actually doing in its browser sessions, and whether it succeeded, from warehouse records plus raw session logs in object storage. Produces an evidence-backed report: inferred tasks, per-session outcomes, what blocked them, agent-quality problems, and what Steel itself cost them. Use this skill whenever someone gives you a Steel organization id (a bare UUID counts) and asks what that org was doing, what they were building, whether their sessions worked, why they failed, why they churned, whether they hit bot walls or CAPTCHAs, what their agent was trying to automate, or asks to investigate / explore / profile / dig into / look at an org, customer, account, or user. Also use it for questions like "did this session succeed", "was a human driving this", "which sites are failing for this customer", or "why does this org look unhealthy" — even when they do not say the words "org recon" or name this skill.
- ▌ CLI Tmux · nibzardUse tmux to run and test our interactive CLI/TUI end-to-end. Includes how to start, send keys, capture output, and cleanly stop (double Ctrl+C).
- ▌ Yt Transcript · nibzard bundleFetch transcripts from YouTube videos. Use when user asks to get, download, extract, or retrieve YouTube video transcripts, captions, or subtitles. Also activates for video content analysis, summarizing YouTube videos, or processing video content.
- ▌ Pentest Toolkit · nibzard bundleAI-Powered Security Testing Toolkit - Professional penetration testing scripts for discovering vulnerabilities, analyzing application structure, and generating context-aware security tests. All scripts return structured JSON for agent consumption.
- ▌ Claude Thread Publisher · nibzard bundlePublish Claude Code conversation threads as static HTML pages hosted on GitHub Gists, with shareable gistpreview links. Use when the user asks to share, publish, or delete a Claude Code thread.
- ▌ Rust Engineer · nibzard bundleWrites, reviews, and debugs idiomatic Rust code with memory safety and zero-cost abstractions. Implements ownership patterns, manages lifetimes, designs trait hierarchies, builds async applications with tokio, and structures error handling with Result/Option. Use when building Rust applications, solving ownership or borrowing issues, designing trait-based APIs, implementing async/await concurrency, creating FFI bindings, or optimizing for performance and memory safety. Invoke for Rust, Cargo, ownership, borrowing, lifetimes, async Rust, tokio, zero-cost abstractions, memory safety, systems programming.
- ▌ Marp Lecture Author · nibzard bundleDraft, revise, and polish Marp-based lecture decks for this repository. Use when editing `lectures/*/lecture.md`, `lecture_annex.md`, or other Marp markdown files, structuring slides, applying Marp directives, pairing generated images with explanations, or preparing a deck for export and presentation.
- ▌ Lecture Image Generator · nibzard bundleCreate, extend, or refactor Python scripts that generate lecture figures for this repository's network science course materials. Use when working on `lectures/*/generate_*.py`, adding or regenerating files in `lectures/*/images/`, adapting the lecture image template, or keeping NetworkX and matplotlib visualizations reproducible, consistent, and easy to link from Marp slides.
- ▌ Todo JSON Manager · nibzardManage project task lists stored in to-do.json and to-do.schema.json, including bootstrapping a backlog, selecting the highest priority task with jq, and updating task statuses. Use when Codex needs to read or update a JSON task list.
- ▌ Git Conventional Commit · nibzardCreate clean git commits using the Conventional Commits format (type(scope): summary). Use when Codex needs to stage changes, craft commit messages, and record completed work in a Git repository.
- ▌ Looper Go Dev · nibzard bundleLooper-Go development workflows: build, test, run, debug, and manage the looper-go project. Use when working on looper-go codebase, running tests, building binaries, or debugging issues.
- ▌ Looper Live Test · nibzard bundleRun a live Looper-Go smoke test by creating a temporary project (PROJECT.md + to-do.json), executing looper for one iteration, observing output, and reporting results. Use when verifying looper-go behavior or demonstrating a live run.
- ▌ Todo Github · nibzardCreate, update, and access task lists as GitHub issues for this repo using GH CLI; use when asked to research repo context and turn a checklist into issues.
- ▌ Doc Maintainer · nibzardMaintain and expand DOCS.MD to cover the full Scribe codebase. Use when asked to update documentation, add missing modules/flows, improve coverage maps, or align docs with code changes in this repo.
- ▌ Release Runbook · nibzardPrepare and publish a GitHub release with semantic versioning, updating PROJECT_VER and CHANGELOG, tagging, and using GH CLI to publish. Use after major changes or when asked to cut a release.
- ▌ Feature Workflow · nibzardWork on a new feature or fix by creating a branch, implementing changes, and submitting a PR with GH CLI. Use when picking up a new todo item.
- ▌ Book PDF · nibzard bundleGenerate and verify a polished PDF containing the full current manuscript of a book in book.db, with title page, ordered parts and chapters, page numbers, metadata, word count, and included text-version IDs. Use for PDF, print copy, reading copy, export book, full manuscript, or compile current version requests. Do not use to edit or approve prose.
- ▌ Book Draft · nibzardWrite or continue new manuscript prose from a plan, idea, fragment, or dictation. Drafts the smallest independently revisable unit (usually a scene or section), stores a recoverable version, extracts consequential planned facts, updates promises and continuity risks, and reports a short save receipt. Does not approve prose.
- ▌ Book Guide · nibzardGuide every conversation about the current book project, writing, story development, or book.db. Always use for start, onboarding, onboard me, help, tour, status, what next, or free-form book brainstorming; orient the author, route to the right specialist skill, and persist durable outcomes without exposing database ceremony. Do not use for unrelated work.
- ▌ Book Design · nibzardDevelop the concept and structure of the book — story contract (reader promise, author advantage, emotional core, book and series engines, constraints), characters and subjects, world or argument, engines, promises, arcs, and a bounded outline of anchors. Use for brainstorming, premise selection, and planning enough to draft confidently without over-outlining.
- ▌ Book Ledger · nibzardNatural-language access to book.db — project status, search, memory and context packs, canon, approvals, threads, continuity, tasks, retcons, and database health. Use to answer “where are we”, find what a character knows, locate open promises, approve a version, retcon a fact, or audit continuity. Translates requests into safe parameterized transactions.
- ▌ Book Revise · nibzardCritique and improve existing prose through separate editorial gates — structural, emotional, pacing, continuity, audio and read-aloud, line, and copy/proof — and create branch alternatives for pivotal scenes. Ties reader feedback to the exact version seen. Never overwrites previous prose; every substantive pass creates a recoverable version.
- ▌ Book Research · nibzard bundleExternal evidence and grounding for the book — market whitespace, comparable titles and reader demand, publishing routes, factual or authenticity research, claim verification, and sources. Use when the author needs evidence rather than invention, a market-opportunity study, comparable-title analysis, subject expertise, or fact-checking. Persist findings into book.db with provenance.
- ▌ Now Writer · nibzardCreate "now" page entries showing current focus areas. Use when the user says "create a now post", "update my now page", "write about what I'm doing now", "now entry", "current status update", or wants to document what they're focused on right now. Triggers for periodic life updates with multiple focus areas.
- ▌ Add Project · nibzardAdd or curate GitHub projects on nibzard-web using the project sidecar and GitHub metadata sync.
- ▌ Idea Writer · nibzardCreate new "idea" entries - product/service concepts with marketing flair. Use when the user says "add an idea", "new idea", "write an idea", or mentions wanting to capture a product or service concept.
- ▌ Image Writer · nibzardCreate new "image" entries - visual content with brief captions. Use when the user says "add an image", "new image", "post an image", or mentions wanting to share a screenshot, photo, or visualization.
- ▌ Article Writer · nibzardCreate new log articles in nibzard.com style. Use when the user says "write an article", "create a blog post", "new log entry", or mentions wanting to write about a topic, experience, or idea. This skill captures the established voice: conversational, narrative-driven, technically deep yet accessible, with authentic personal perspective.
- ▌ Illustrate CLI · nibzard bundleGenerate CLI-style PNG images from structured data. Use when the user wants to create terminal-looking tables, command output visualizations, or any data rendered as a CLI screenshot. Triggers on: 'make a table image', 'render as CLI', 'terminal style table', 'screenshot of table', 'CLI visualization', 'illustrate this data', or when user wants to turn tabular data or command output into a shareable image. Also use when creating images for blog posts or articles that show benchmark results, comparison tables, or structured data in terminal style.
- ▌ Site Analytics · nibzardPull GA4 and Google Search Console data via the read-only service account. Use when the user mentions analytics, GA4, Search Console, GSC, traffic, page performance, search clicks/impressions, or wants to re-evaluate which articles to feature.
- ▌ Thought Writer · nibzardCreate new "thought" entries - quick insights, observations, or reflections. Use when the user says "add a thought", "new thought", "write a thought", or mentions wanting to capture a quick insight or observation.
- ▌ Skillctl · nibzard bundleInspect managed skills, diagnose missing or stale projections, and guide users through skillctl lifecycle commands.
- ▌
- ▌ Create Pattern · nibzard bundleAnalyze sources (blog posts, PDFs, YouTube videos, codebases, pasted text) for agentic patterns, match against 105+ existing patterns, create new patterns or update existing with new sources and insights.
- ▌ Arxiv Pattern Discovery · nibzard bundleSearch arXiv for academic papers describing agentic AI patterns. Use when user asks to find new patterns from academic literature, search arXiv, discover patterns from papers, or review academic sources for pattern extraction.
- ▌ Awesome Agentic Patterns Pr Review · nibzardReview pull requests for the awesome-agentic-patterns repository. Use when asked to validate a PR, assess whether a contribution fits the repo, inspect pattern submissions under patterns/, check merge readiness, repair a small submission issue on top of a contributor branch, draft a polite contributor comment, or apply the repository's pattern-first and non-promotional contribution policy to a GitHub pull request.