Latest Agent Skills
Everything added to the registry recently, newest first.
- alexderz SkillLang JS TS
use this when writing, reviewing, or testing JavaScript or TypeScript — *.ts, *.tsx, *.js, *.mjs, *.cjs, tsconfig, package.json. TypeScript-strict wins when tsconfig exists. do not use for HTML/CSS-only (lang-web-markup) or Python.
- alexderz SkillUX Design
use this when writing user stories, high-level UX, or UI mockups — designer persona; variants in any attached tool or markdown/HTML/canvas; agent review vs requirements then operator. do not use to implement, apply reviewer taste, or skip the operator gate.
- alexderz SkillLang Rust
use this when writing, reviewing, or testing Rust — Cargo.toml, *.rs, clippy, borrow checker, unsafe, async Tokio. do not use for C, C++, or Go. do not dump Microsoft or leonardomso rule catalogs into context.
- alexderz SkillLang Ruby
use this when writing, reviewing, or testing Ruby — *.rb, Gemfile. do not use for Rails-only architecture; stay on the language. do not use for Python.
- alexderz SkillLang Java
use this when writing, reviewing, or testing Java — *.java, pom.xml, build.gradle. language only; not a Spring skill. do not use for Kotlin (load lang-kotlin).
- alexderz SkillLang Dart
use this when writing, reviewing, or testing Dart — *.dart, pubspec.yaml. language only; Flutter architecture is out of scope unless the file already is Flutter.
- alexderz BundleUI Craft
use this when implementing or reviewing a user interface in code — screens, components, styles, UI states, motion — as the builder's visual-quality rules. load it beside the approved `ux-design` mockups, never in place of ux-design. do not use for user stories or mockups (that is ux-design), or for backend-only work. do not load it when the product repo's root `AGENTS.md` records option 3, neither, under `## UI craft`.
- alexderz SkillLang SQL
use this when writing, reviewing, or migrating SQL — *.sql, schema files, embedded queries in host code. postgres-shaped defaults; name the dialect if it is not postgres. load with the host language skill when the query lives in application code.
- alexderz SkillLang PHP
use this when writing, reviewing, or testing PHP — *.php, composer.json. PHP 8+ types. do not use for JavaScript. not a Laravel architecture skill.
- alexderz SkillLang Lua
use this when writing, reviewing, or testing Lua — *.lua including Neovim, game, and embedded scripts. do not use for JavaScript.
- alexderz SkillLang Cpp
use this when writing, reviewing, or testing C++ — *.cpp, *.cc, *.cxx, *.hpp. do not use for C-only changes (load lang-c) or Rust. do not paste the C++ Core Guidelines.
- alexderz SkillGrok Acp
use this when the operator chooses to offload work to Grok Build — "offload to grok", "have grok build it", "delegate to grok", "resume the grok session" — to run the local Grok CLI as an SDLC worker (builder by default) over ACP, with session resume. do not use on your own initiative, and do not use for a quick read, search, or one-line fix you can do inline.
- alexderz SkillLang Go
use this when the change is Go but it is unclear which Go skill to load — routes to golang-safety, golang-testing, or golang-security. do not use as a fourth Go body. do not use for other languages.
- alexderz SkillLang C
use this when writing, reviewing, or testing C — *.c, *.h without C++ files in the same change. do not use for C++ (load lang-cpp) or Rust.
- alexderz SkillAstryx
use this when a builder implements or reviews UI code in a product whose package.json depends on an @astryxdesign/* package, or whose approved LLD or mockups name Astryx; or when a designer or architect chooses a component library for a React web UI. it says how to get Astryx facts from the project's own CLI, how to build a page from Astryx templates, which delivery checks to run, and what wins on conflict. it loads beside the one language skill, ui-craft and modern-web-guidance, not in place of them. do not use for backend-only work, non-React UIs, or products that do not use or choose Astryx.
- alexderz SkillYagni
use this when scoping a change, adding a helper, or expanding a skill or AGENTS.md, as the builder, the item contrarian or the reviewer — ship the smallest thing that satisfies the current ask; defer speculative generality. do not use on a chunk brief.
- alexderz SkillDebug
use this when a test fails, a bug appears, or behavior is unexpected — find root cause before any fix. default debugging skill. do not use to skip TDD or to land past an open blocker.
- alexderz BundleSdlc
use this for any project, ticket, chunk, or multi-agent run that follows this skills home's process — the SDLC index of names, roles, tracker rule, grain, asking the operator and steps; read the step file its Steps table names. do not use to invent a second process or to skip a gate.
- alexderz SkillTdd
use this when implementing a feature or bugfix, changing behavior, or refactoring — write a failing test first, watch it fail for the right reason, then write the smallest code that passes.
- korsmakolnikov BundleDatadog Experiment Downloader
Download a complete Datadog LLM Observability experiment with pup: summary, every event with its dimensions and metrics, and the agentic loop (reasoning, tool calls, tool results) of every trace. Use before analysing an experiment run offline, comparing runs, or investigating why cases failed.
- korsmakolnikov SkillContainer Scaffold
The project's runtime infrastructure, laid by ford after the architecture scaffold - a Dockerfile for the application, compose.yaml with the services the ADL names (a database, a broker), .dockerignore, the Makefile targets to run them, and the CI's path filter for a project in a folder. Load it in ford's target mode when the ADL has an external system that runs as a service, or the shopping list asks for containers.
- korsmakolnikov SkillPython Scaffold
Creates a new Python project with the scaffold tool - src layout, uv, pytest with Hypothesis, ruff, mypy --strict, a Makefile task runner, GitHub Actions CI, git init with an empty "start." commit and toolchain.yaml. ford loads it on a greenfield Python project, before the architecture; the user can also run it on their own.
- korsmakolnikov SkillElixir Handbook
How to work on an Elixir project in this workflow - toolchain.yaml and the toolchain command (build, the tests to run, the static checks), the testing libraries (ExUnit, StreamData, Mox and Hammox for contract tests), the test layout, and the user's personal style rules. Load it whenever you build, test, check, write or review Elixir code in a project listed in `projects`.
- korsmakolnikov SkillWorkflow Files
The control files of the agentic workflow - .sources/ (ADL, spec, components map, shopping lists), .documentation/, toolchain.yaml and the logs under /tmp - who writes each, who reads it, and why they are versioned on Claude Code and never on Copilot. Load it before reading or writing any of them, or when a project's layout looks out of date.
- korsmakolnikov SkillAdl Interview
Protocol for interviewing the user to build ADL definitions and component interfaces one question at a time, including the ASK_USER relay format used by sub-agents that cannot talk to the user directly. Use when composing or revising .adl files or designing component interfaces with the user.
- korsmakolnikov SkillMinime Sync
Mirrors the live Copilot setup in ~/.copilot (agents, skills, hooks, settings, global instructions), the autonomy settings in ~/.bash_copilot and the kent and argyris launchers into ~/code/minime/copilot/, and the shared linus, spec-check and signal-check commands and signal schemas into ~/code/minime/common/, then records the change as a new commit with the linus command. Use before a /restart and whenever an agent, skill, hook or setting has changed.
- korsmakolnikov SkillAdl Scaffold
Scaffolds the directories, namespace modules and component interfaces (signatures, types and docs, no logic) described by approved ADL files, for Elixir and Python projects. Use after the fitness functions for an ADL file exist.
- korsmakolnikov SkillSave Session
Save kent's session to its progress file before the user interrupts it, so that a later `claude --agent kent` in the same repository resumes from there. Use when the user types /save-session, or asks to save, park or pause the workflow session.
- korsmakolnikov SkillDomain Spec
Reference for the domain spec (.sources/spec.yaml) of this workflow, the structured input next to the ADL that lists the entities, their relations, the system constraints, the contracts of the component operations and the properties to test with property-based tests (StreamData, Hypothesis). Covers the format, the spec-check validator and how each entry becomes a test. Load it before reading, writing or testing against a spec.
- korsmakolnikov SkillAdl Reverse
Reverse-engineers an as-is ADL draft from an existing Elixir or Python codebase by extracting the namespace dependency graph. Use during brownfield analysis, before changing an existing architecture. Read-only on the codebase.
- korsmakolnikov BundleAdl Fitness
Generates architectural fitness functions (ExUnit or pytest tests) from the ASSERT and FOREACH statements of ADL files, using the AdlFitness helpers shipped with this skill. Use after an ADL file is approved, before scaffolding the code it describes.
- korsmakolnikov SkillC Scaffold
Creates a new C project with the scaffold tool - CMake behind a Make wrapper, Unity tests, GitHub Actions CI, git init with an empty "start." commit. ford loads it on a greenfield C project, before the architecture; the user can also run it on their own.
- korsmakolnikov SkillAdl Spec
Reference for the Architecture Definition Language (ADL) by Mark Richards and Neal Ford as used in this workflow, including the .sources/ folder layout and how ADL physical names map to Elixir and Python namespaces. Load it before reading, writing or validating any .adl file.
- digitie BundlePython Krex API
data.ex.co.kr와 data.go.kr로 제공되는 한국도로공사 OpenAPI Python client를 구현, 확장, test, troubleshooting할 때 사용한다.
- karero SkillWebsite Positioning Check
Give an existing website a fast, fresh-eyes positioning check: can the right visitor tell what is on offer, for whom, and why to believe it? Read-only and concise — a one-screen Clear / Blurred / Broken verdict, the single biggest blur, and the three highest-leverage fixes. Use whenever someone asks if a site's offer is clear, differentiated, outcome-led, too technical, or consistent between homepage and offer pages — even without the word "positioning". Trigger phrases: "is our positioning clear", "fresh eyes on the homepage", "what are we actually selling", "is it obvious who this is for", "we sound too technical", "homepage and services page disagree", "positioning sanity check", "does the site make sense to a stranger". Do not use for developing positioning from scratch (website-positioning), a full copy rewrite (copywriting), an SEO audit, or the pre-launch website-review.
- karero BundleSearch Console Insights
Pull and act on Google Search Console DATA for a verified site. Free GSC Search Analytics API (OAuth, read-only): where target keywords rank, striking-distance queries (pos ~8-20), and high-impression/low-CTR pages flagged for snippet/SERP investigation (title/meta rewrite only if the live-SERP check shows a snippet problem you control). Optional add-ons: the live competitor Top-10 via a SERP API, Bing Webmaster Tools query stats, and a weekly check of whether AI engines name the business (GEO). First use runs a guided onboarding for non-technical owners. Trigger phrases: "GSC insights", "Search Console data", "connect GSC", "where do I rank", "top queries", "striking distance keywords", "quick SEO wins", "why is my CTR low", "which pages to optimize", "competitor Top 10", "how do I rank on Bing", "Copilot visibility", "track my rankings over time", "weekly SEO report", "does AI name my business", "weekly AI check", "show me my AI report".