Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
e3
East Execution Engine (e3) - durable dataflow execution for East programs. Use when: (1) Authoring e3 packages with @elaraai/e3 (e3.input, e3.task, e3.package, e3.export), (2) Running e3 CLI commands (e3 repo create, e3 start, e3 watch, e3 get, e3 set), (3) Working with workspaces and packages, (4) Content-addressable caching and dataflow execution.
elaraai/east-plugin 1
-
east
East programming language - a statically typed, expression-based language embedded in TypeScript. Use when writing East programs with @elaraai/east. Triggers for: (1) Writing East functions with East.function() or East.asyncFunction(), (2) Defining types (IntegerType, StringType, ArrayType, StructType, VariantType, etc.), (3) Using platform functions with East.platform() or East.asyncPlatform(), (4) Compiling East programs with East.compile(), (5) Working with East expressions (arithmetic, collections, control flow), (6) Serializing East IR with .toIR() and EastIR.fromJSON(), (7) Standard library operations (formatting, rounding, generation).
elaraai/east-plugin 1
-
warning-example
I am a skill that has some quality issues but is technically valid.
intent-solutions-io/create-agent-skill-md 1
-
My_Invalid_SKILL-With-CAPS
intent-solutions-io/create-agent-skill-md 1
-
pdf-processor
Extracts text and tables from PDF documents. Use when working with PDF files or when the user needs document analysis.
intent-solutions-io/create-agent-skill-md 1
-
docs-and-release
Keep documentation, versioning, and release artifacts consistent for eo-processor. Use when changing public APIs, adding features, updating performance claims, or preparing a release (align README/QUICKSTART/docs, stubs, changelog, and pyproject/Cargo versions).
BnJam/eo-processor 1
-
test-and-quality-gates
Run and interpret eo-processor quality gates (Rust+Python) and add the right tests for changes. Use when verifying work, fixing CI failures, or before committing PR-ready changes (fmt/clippy, ruff/mypy, pytest/tox, coverage, and minimal regression tests).
BnJam/eo-processor 1
-
python-api-surface
Maintain the public Python API for eo-processor, including exports, __all__, docstrings, and type stubs. Use when adding/renaming functions, changing signatures/behavior, or ensuring Python typing and user-facing docs stay consistent with the Rust/PyO3 core.
BnJam/eo-processor 1
-
project-intake
Build a fast, accurate mental model of the eo-processor repo and the user’s task. Use when starting work, when requirements are unclear, or before making multi-file changes (Rust+PyO3+Python packaging/tests/docs).
BnJam/eo-processor 1
-
benchmark-and-perf
Measure, compare, and improve eo-processor performance safely. Use when adding/changing Rust compute kernels, refactoring hot paths, or making performance claims. Provides a repeatable benchmark protocol with correctness checks, profiling hints, and reporting guidelines.
BnJam/eo-processor 1
-
examples-and-smoke-tests
Create and maintain runnable examples under examples/ for onboarding and smoke testing. Use when adding/changing public APIs, when you need a quick “does it work end-to-end?” script, or when updating examples/README.md to match the current eo-processor API.
BnJam/eo-processor 1
-
rust-pyo3-function
Implement or modify a Rust function exposed to Python via PyO3 in eo-processor. Use when adding new compute kernels, fixing numerical/shape bugs in the Rust core, or wiring Rust functions into the Python module safely and consistently.
BnJam/eo-processor 1
-
issue-labeler
Analyze unlabeled GitHub issues and generate label recommendations for review. Supports batch submission after approval.
patniko/skills 2
-
scorecard-update
Review Azure Data Explorer dashboards for Copilot CLI metrics and update Google Sheets scorecard. Connects to existing Chrome session for authentication.
patniko/skills 2
-
canvas
Spawn interactive terminal TUI components (calendars, documents, flight bookings) with real-time IPC communication. Display rich content and collect user selections in tmux split panes.
patniko/skills 2
-
shipment-tracker
Generate a visual report of what was shipped in GitHub repositories over a specified time period by analyzing merged PRs and closed issues.
patniko/skills 2
-
meeting-to-issues
Parse meeting transcripts to extract action items and create GitHub issues after user confirmation. Converts discussions into trackable work items.
patniko/skills 2
-
issue-triage
Fetch GitHub issues and use LLM judgment to prioritize them based on importance, clarity, delegation potential, and urgency. Helps identify what to work on next.
patniko/skills 2
-
competitive-analysis
Compare local codebase capabilities against competitor products by researching competitor features via web search and documentation, analyzing local code patterns, and generating an interactive HTML comparison report.
patniko/skills 2
-
global-intelligence-search
企业级全局情报搜索网关。支持 PubMed 医学文献检索和通用网页抓取。这是 Investigator Agent 唯一合法的外部信息获取武器。
timoxue/LingNexus
-
pull-request-format
Validate pull request source/target rules and draft standardised PR titles and Markdown descriptions that match repository GitHub Actions enforcement.
diey/codex-agent-skills
-
terminal-driven-fix-loop
Use a terminal-first feedback loop where the user runs tools manually and provides output for fixes.
diey/codex-agent-skills
-
boost-search-docs-first
Use Laravel Boost search-docs to verify the correct, version-specific approach before implementing Laravel ecosystem features.
diey/codex-agent-skills
-
minimal-file-changes
Prefer small, local edits. Avoid creating new files or folders unless required by Laravel conventions or explicitly requested by the user.
diey/codex-agent-skills