Latest Agent Skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment.

Creates detailed, bite-sized implementation plans from specs or requirements, with exact file paths, code, and test commands for TDD workflows.

Guides collaborative dialogue to turn ideas into approved designs and specs before any implementation begins.

生成符合《党政机关公文格式》（GB/T 9704—2012）规范、内容严守事实依据、问题直击要害、建议具可操作性的政策类报告；杜绝虚构政策、机构、案例、数据及未验证技术断言；所有文献引用须为2023–2024年正式发布或现行有效版本；输出为纯文本、零格式标记、Word直接可编辑格式。

Creates original educational comics with flexible art style and tone combinations, generating storyboards, character sheets, and sequential images, then merging them into a PDF.

Creates, edits, and analyzes spreadsheet files using pandas and openpyxl, with formula recalculation via LibreOffice.

Creates, reads, edits, and converts PowerPoint (.pptx) files, including extracting text, generating slide images, and applying design guidance.

Creates, reads, edits, and analyzes Word documents (.docx) using pandoc, LibreOffice, and docx-js, including formatting, tables, images, and tracked changes.

Reads, extracts, merges, splits, rotates, watermarks, creates, encrypts, and OCRs PDF files using Python libraries and command-line tools.

Routes documents in the psychological counseling domain to the appropriate family skill based on methodological terms and task goals.

Manages personal local Agent Skill files by detecting reusable material, searching for similar skills, and creating or updating SKILL.md folders after user approval.

Adds a persistent pattern or rule that Ralph will remember and apply to future stories.

Loads one or more predefined role files to focus work on a specific task, activated by commands like "role [name]".

Routes natural-language requests to memory, task, storage, and retrospective operations, and compiles skill extensions.

Analyzes a codebase to create or improve an AGENTS.md file, capturing conventions, constraints, and rationale that are expensive to rediscover.

Spawns GLM-5 powered teammates with thinking mode for coding, review, testing, planning, and research tasks.

Autonomously implements large Elixir/Phoenix features end-to-end: discovers complexity, plans with specialist agents, implements with verification, reviews code, and cycles back on issues.

Establishes a two-party working posture where the user directs and the agent executes, surfacing every genuine fork as a batched single-select question with a recommended default.

Implements a structured problem-solving algorithm that guides every response through observe, think, plan, build, execute, verify, and learn phases toward a defined ideal state.

Provides HR business partner guidance for organizational planning, hiring, performance management, talent reviews, and employee relations, with templates for role design, interview rubrics, onboarding plans, and communication.

Provides consulting workflows for Epic EMR configuration, including ClinDoc, Bridges interfaces, HL7 messaging, provider matching, and orderset builds.

Generates and refactors content optimized for AI Overviews, ChatGPT, and Gemini with a structure that is easy to cite and summarize.

Provides Kelvin Garr's fixed AICA brand identity and Next.js 14 implementation guide for building his personal sites and AICA-branded projects.

Provides scikit-learn compatible algorithms for time series machine learning, including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search.

Installs the Atlassian CLI tool and authenticates it with your Atlassian account.

Implements real-time pub/sub messaging with Ably's edge infrastructure, covering presence, message history, and token authentication.

Generate A2UI 0.8 protocol compliant UI code for agent-driven interfaces, including JSONL messages for surface updates, data model updates, and rendering.

Guides implementation of accessible web interfaces to meet WCAG 2.2 AA, WAI-ARIA 1.2, and WCAG2ICT standards, covering semantic HTML, ARIA patterns, focus management, and automated validation.

Provides common Git commands for syncing forks, stashing changes, managing branches, undoing changes, and rolling back commits.

Index of Odoo 19 development guides covering actions, controllers, data files, decorators, fields, manifests, migrations, mixins, models, OWL components, performance, reports, security, testing, translation, transactions, and views.

Master index of Odoo 18 development guides, covering modules, models, views, security, testing, and more.

Defines when to create Epic, Feature, UserStory, or Task tickets and adds concise guidance to SKILL.md.

Bootstraps a local Python environment for a skill package by creating a venv and installing dependencies with a stdlib-only script.

Updates skill documentation and templates to require agents to use their real identity in worklogs instead of hardcoded placeholders.

Create, extract, flatten, list, test, install, and script tzst CLI workflows for .tzst or .tar.zst archives, including compression levels, streaming mode, extraction filters, conflict resolution, and JSON output.

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

Quickly look up concise, community-maintained command examples instead of full man pages.

Turns a natural-language request into one or more coder-eval task YAML files with minimal prompts and weighted success criteria, validated against the coder-eval CLI.

Runs project tests, stages and commits changes with a conventional message, then rebases and pushes to the current branch, stopping on any failure.

Run SQL queries and psql meta-commands against PostgreSQL databases via the psql CLI, with options for file execution, tuples-only output, and timeouts.

Persists context across sessions by compiling sources into a local SQLite store and markdown tree, then retrieves relevant memory via embedding search.

Mines SpecStory coding histories from any agent into a persistent corpus, surfaces reproducible workflows with corroborated evidence, and interactively forges chosen ones into skills installed across agent harnesses.

Scaffolds a coder-eval task suite in a repository by scanning for testable components, writing one real task, and validating it.

Guides using the Fish interactive shell, covering autosuggestions, universal variables, web configuration, and best practices for interactive use.

Locates files by name, type, size, permissions, and modification time, with options to execute commands on results.

Runs the CASS operator skill in a Codex environment, using the local shell and referencing the source skill for domain behavior.

Runs the casr operator skill in a Codex environment, reading the source skill for behavior and using the local shell with JSON/NDJSON command surfaces.

Runs the CAAM operator skill using Codex and the local shell, following the source skill's domain behavior and output expectations.

Reference for writing idiomatic, safe Bash and shell scripts with quoting, conditionals, loops, pipes, functions, and error handling.

Manage GraphQL schemas and federation with Apollo Rover CLI, covering publishing, fetching, composing, validating, and local supergraph development.

Generates type-safe TypeScript clients from OpenAPI specs using Orval, covering configuration, React Query/SWR hooks, custom mutators, and MSW mocks.

Build, deploy, and interact with Juicebox V5 projects, including revnets, hooks, and omnichain deployments, with API references, implementation details, UI generation, and GraphQL queries.

Provides Python code patterns for making HTTP requests with httpx, covering sync and async clients, authentication, streaming, timeouts, retries, and WebSocket support.

Search and retrieve book details, author information, and bibliographies via the Open Library API from the command line.

Makes HTTP requests from browser or Node.js with support for interceptors, error handling, and TypeScript.

Fine-tune instruction-following LLMs with Unsloth's optimized SFTTrainer, covering dataset formatting, chat templates, training configuration, and thinking-model patterns.

Annotates single-cell RNA-seq data by scoring marker genes, transferring labels with CellTypist, or reasoning over cluster markers with an LLM.

Scales Python ML workloads across clusters using Ray's distributed tasks, actors, data, and serving capabilities.

Builds Retrieval-Augmented Generation systems with document chunking, embedding generation, vector storage, and retrieval pipelines, including evaluation and optimization.

Debriefs recent work by probing understanding of the codebase with four questions, tracking concepts in a local ledger to help retain ownership.