skills.homes logoskills.homescapability registry
запрос активен

Поиск skills

Найдите подходящую возможность для вашего агента.

Популярные запросы
pythonaiweb scrapermcppdfgitdockertypescript
Результаты
53,183
skills, соответствующие запросу
Страница
843
из 2660
Запрос
ai
ищите по названию, тегу или описанию
automation-tools
210

git-worktree

Manages git worktrees including listing, creating, removing, and switching between worktrees. Use when the user mentions creating worktrees, create a work tree, create worktree, new worktrees, parallel branches, or working on multiple branches simultaneously. CRITICAL - PROACTIVE BRANCH PROTECTION - Before starting ANY development work (implementing features, fixing bugs, writing code, making changes), check the current branch. If on main/master branch, IMMEDIATELY suggest creating a feature branch worktree to prevent accidental commits to main. This is mandatory for all development requests.

codemie-ai
codemie-ai
tools
open
education
210

update-typst-grammar-authoring

Use when maintaining the portable typst-grammar-authoring skill from this repository's canonical Typst grammar source.

typst-doc-cn
typst-doc-cn
documentation
open
technical-docs
210

report-issue

This skill should be used when the user wants to report a bug, file an issue, or suggest a feature for the CodeMie Code CLI tool (codemie-ai/codemie-code repository on GitHub). Trigger phrases include: "report a bug", "open an issue", "submit an issue", "file a bug report", "something is broken in CodeMie", "report to GitHub", "create a GitHub issue", "suggest a feature for CodeMie", "request an enhancement", "I have a feature idea", "codemie is not working", or any mention of filing a report for CodeMie. This skill automatically collects diagnostic context (OS, Node.js, CLI version, installed agents, active profile, codemie doctor output, recent debug logs) and creates a structured GitHub issue via `gh issue create` with a user-confirmed preview step before submission.

codemie-ai
codemie-ai
documentation
open
real-estate-legal
209

verification-mastery

Evidence before claims, always. No completion claims without fresh verification. The final gate before declaring success.

xenitV1
xenitV1
business
open
cicd
209

maestro

Use when you need to act as an Elite Software Architect (Maestro) to manage complex repositories. It enforces a "Why over How" philosophy, maintains a persistent project memory (Brain), and orchestrates specialized sub-skills through a Plan-Act-Verify lifecycle.

xenitV1
xenitV1
devops
open
technical-docs
209

dev

Develop and maintain the PWAFire PWA utilities library. Use when working on pwafire package, adding PWA APIs, fixing modules, writing tests, or contributing to the PWAFire codebase.

pwafire
pwafire
documentation
open
automation-tools
209

taffybar-nixos-flake-chain

Use when doing NixOS rebuilds involving taffybar, or when flake.lock updates are needed after changing taffybar ecosystem packages. Also use when debugging stale taffybar versions after `just switch`.

colonelpanic8
colonelpanic8
tools
open
automation-tools
209

bump-overlay-versions

Use when user asks to bump, update, or upgrade claude-code or codex versions in overlay.nix, or when checking if newer versions are available

colonelpanic8
colonelpanic8
tools
open
testing
208

test-driven-development

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first

brobertsaz
brobertsaz
testing-security
open
design
208

visualize

Render rich interactive visuals — SVG diagrams, HTML widgets, Chart.js charts, interactive explainers — directly inline in chat using the render_visualization tool. Use whenever the user asks to visualize, diagram, chart, draw, map out, or illustrate something, or when a topic has spatial, sequential, or systemic relationships a diagram would clarify better than prose. Also use proactively for data comparisons, metrics, architecture, processes, or mechanisms that benefit from a visual.

Classic298
Classic298
content-media
open
machine-learning
208

add-model-server

Add a new VLA model server to the evaluation harness. Use this skill whenever the user wants to integrate, create, or add a new model — e.g. 'add OpenVLA server', 'integrate RT-2', 'hook up my model', 'write a model server'. Also use when they ask how model servers work or want to understand the server interface.

allenai
allenai
data-ai
open
machine-learning
208

run-evaluation

Run a VLA model evaluation against a simulation benchmark. Use this skill whenever the user wants to evaluate, benchmark, test, or run a model on a sim environment — even if they say it casually like 'try OpenVLA on LIBERO' or 'get me CALVIN scores'. Covers the full workflow: serving the model, launching the benchmark, sharding for speed, merging results, and interpreting output.

allenai
allenai
data-ai
open
ecommerce-development
208

pharmacy-dev

Pharmacy module development guide for the HMIS project. Use when working on pharmacy features including GRN, purchase orders, stock transfers, disbursements, retail sales, pharmacy reports, stock management, item substitution, or pharmacy billing workflows.

hmislk
hmislk
development
open
frontend
208

jsf-ajax

JSF AJAX update rules for the HMIS project. Use when working on AJAX updates, p:commandButton update attributes, PrimeFaces AJAX callbacks, partial page rendering, or debugging AJAX update failures. Also covers JSF navigation patterns: why f:viewAction must not be used on @SessionScoped beans, and how initialization belongs in navigation methods. Critical rules to prevent silent AJAX failures and refresh/back-button state corruption.

hmislk
hmislk
development
open
cicd
208

verify-persistence

Verify persistence.xml configuration before git push. Use before pushing code to ensure persistence.xml uses environment variables instead of hardcoded JNDI names. Prevents QA deployment failures.

hmislk
hmislk
devops
open
academic
207

convergence-debugger

Expert debugging guide for AI Counsel's convergence detection system. Use when deliberations aren't converging as expected, early stopping fails, semantic similarity seems wrong, or voting vs semantic status conflicts occur.

blueman82
blueman82
research
open
backend
207

config-schema-migrator

Expert at evolving Pydantic configuration schemas with backward compatibility and automated migrations

blueman82
blueman82
development
open
gaming
207

core-brainstorm

Collaborative brainstorming mode for thinking through problems, ideas, and features before planning. Use when the user wants to discuss, explore ideas, or think through a problem without writing code.

LukeRenton
LukeRenton
development
open
academic
207

academic-paper-composer

Systematic writing framework for philosophy and interdisciplinary academic papers from optimized outline to submission-ready manuscript. Use when users want to: (1) write a paper from a detailed outline, (2) ensure quality control during writing, (3) maintain consistency across chapters, (4) prepare a submission-ready manuscript, or (5) systematically execute a planned paper. Triggered by phrases like 'write the paper from this outline,' 'compose the full manuscript,' 'execute the outline,' or when users have completed strategic planning (academic-paper-strategist skill) and are ready to write. Takes optimized outline as input; outputs complete manuscript with iterative quality checks.

lishix520
lishix520
research
open
design
206

render

Use when the user says '/render', 'render this', 'render diagrams', 'generate SVG', 'mdview render', or wants to render markdown files with ASCII art diagrams to HTML via mdview. This skill generates DiagramSpec JSON for ASCII art blocks, embeds specs as HTML comments in the markdown, and calls mdview to produce themed SVG output. The AI provides the structural intelligence that makes asciisvg rendering accurate.

Nubaeon
Nubaeon
content-media
open
Назад
Страница 843 / 2660
Вперёд