agentic-coding

Foundational skill-authoring knowledge to use alongside the skill-creator skill. You MUST always load this skill before loading the skill-creator skill, when creating or updating skills.

Disciplined, measurable iteration for a substantial refinement or investigation: loop against verifiable pass/fail conditions, fan work out to subagents, and keep the main context lean. Use when improving something measurable over repeated cycles (tuning a metric or detector, refactoring against a regression bar), chasing a surprising or suspicious number, or driving a long multi-step task where delegation and context discipline matter. Not for one-shot edits or quick lookups that don't warrant a loop.

Use when building or maintaining a self-contained personal knowledge base (an LLM wiki) as plain markdown, optionally opened as an Obsidian vault. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki health, auditing article claims against their sources, critiquing the reasoning in a source or article, superseding stale knowledge, 'add to wiki', or any mention of 'LLM wiki' or 'Karpathy wiki'.

Use this skill after completing multiple, complex software development tasks before informing the user that work is complete.

Retrieves up-to-date documentation, API references, and code examples for any developer technology. Use this skill whenever the user asks about, or when you need to lookup documentation or usage reference a specific library, framework, SDK, CLI tool, or cloud service - even if well-known as your training data may be outdated. Prefer this over web search for library documentation and API details.

Provides fast document to markdown extraction. Use this skill when the user asks to parse, perform multi-format document conversion or spatially extract text from an unstructured file (PDF, DOCX, PPTX, XLSX, images, etc.) locally.

Activates explicit multi-stage planning, aggressive sub-agent delegation, and mandatory self-verification at each stage. Use this skill for complex tasks that benefit from systematic decomposition - large software projects, multi-source research, long-running analyses, scientific investigation, or any task where correctness and thoroughness matter more than raw speed.

Use when answering questions from this machine-learning knowledge base. Triggers: questions about transformers, attention cost and efficiency, and long-context scaling; 'what do we know about attention', 'check the ML wiki'. Read-only querying of compiled knowledge; to add, update, supersede, lint, audit, or critique, use the llm-wiki skill instead.

Provides knowledge on using the `glean` CLI tool to access company knowledge and documents through Glean. Use when the user asks you to use Glean to search, read or otherwise access knowledge from their company's Confluence, Slack, Google Drive Files (Slides, Documents, Sheets) etc.

Provides tools for managing MarkEdit, a macOS markdown editor

Review recent changes since a fixed point (commit, branch, tag, or merge-base) along three independent axes - Standards, Spec, and Maintainability - run as parallel sub-agents that read beyond the diff, then aggregated into severity-ordered findings with an explicit verdict. Use when the user wants to review a branch, a PR, or recent committed changes.

Extract wisdom, insights, and actionable takeaways from YouTube videos, blog posts, articles, or text files. Use when asked to analyse, summarise, or extract key insights from a given content source. Downloads YouTube transcripts, fetches web articles, reads local files, performs analysis, and saves structured markdown.

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise.

Create a handoff document for the current conversation, ready for another agent to pick up.

Provides guidance and tools for hardware design. Activate when using KiCAD, looking up electronic parts or designing PCBs.

Find deepening opportunities in a codebase, informed by whatever domain language and architectural decisions are already documented in the repo. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Guidance for editing Ghostty terminal configuration files. You must use this skill when creating or modifying Ghostty config files.

Provides guidance on writing in the voice of Hunter S. Thompson for essays, columns, letters, dispatches, or short-form political commentary. Use when the user asks for writing in the style of Hunter S. Thompson, HST or gonzo journalism.

Suite of tools for creating elaborate, multi-component claude.ai HTML artefacts using modern frontend web technologies (React 19, Tailwind CSS v4, shadcn/ui). Use for complex artefacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artefacts.

Reverse-engineer an application, website or document's design system from its codebase and screenshots. Use when asked to analyse visual design, extract a colour palette, document UI patterns, identify typography and spacing systems, audit design consistency, or understand the design language of a frontend codebase.

Creates structured development plans with phased task breakdowns, requirements, and QA checklists. Use when the user explicitly asks to create a dev plan, development plan, or document development requirements.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches - a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "try a few designs".

Grilling session that mines the user for fragments - heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) - and appends them to a single document as raw material for a future article. Use when the user wants to develop ideas before imposing structure, or mentions "fragments", "ideate", or "raw material" for writing.

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

Reference gallery of polished single-file HTML artifacts demonstrating effective ways to communicate ideas through HTML. Use when the user wants to explain, showcase, demo, plan, review, or present an idea within an HTML file.

Disciplined diagnosis loop for hard problems, diagnosing bugs and regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test.

Applies a modified Fagan Inspection methodology to systematically resolve persistent bugs and complex issues. You should active this skill when multiple previous fix or debugging attempts have failed repeatedly, or when a methodical root cause analysis or complex problems is needed. Highly effective for complex problems. Do not use for simple troubleshooting.

Rewrites text containing AI slop to make it more human-like. Use when explicitly asked to rewrite AI generated text.

You MUST always activate this github skill whenever working with GitHub in any capacity, including but not limited to gh cli, API, Actions, issues, PRs and other routine Github interactions.

You MUST activate this skill when working on Go projects

You MUST activate this skill when working on Python projects

You MUST activate this skill when working on Rust projects

You MUST activate this skill when working on TypeScript or JavaScript projects

Creating and maintaining CLAUDE.md project memory files and .claude/rules/ rule files that provide non-obvious codebase context. Use when (1) creating a new CLAUDE.md for a project, (2) adding architectural patterns or design decisions to existing CLAUDE.md, (3) capturing project-specific conventions that aren't obvious from code inspection, (4) organising instructions into path-scoped rule files.

Delays execution of a task until a specified time or after a duration. Use when the user asks to run something later, in X minutes/hours, at a specific time, schedule a command, or defer work to a future point.

Use when working with AWS Strands Agents SDK or Amazon Bedrock AgentCore platform for building AI agents. Provides architecture guidance, implementation patterns, deployment strategies, observability, quality evaluations, multi-agent orchestration, and MCP server integration.

Convert a PPTX or PDF slide deck into per-slide markdown that preserves both the verbatim text and the meaning of embedded screenshots, diagrams and charts in their original layout positions. Use this skill whenever the user wants to extract content from or convert a slide deck in PDF or PPTX to markdown.

Structure, refine, or draft narrative content or storytelling for business communication such as slide decks, blog posts, pitches, reports. Use when the user wants help build a narrative arc, find the through-line, sequence beats or refine existing content for flow and impact

Summarises the delta between a tool's latest release and the last summary the user saw. Use when the user asks about what's new, the latest release, release notes, or the changelog of one of the supported tools: Claude Code, OpenCode, llama-swap, or llama.cpp.