智能体技能

Art Directing

divyamohan1993

Use when designing or restyling any UI surface (page, panel, dashboard, landing) or picking its visual identity (palette, type, layout, motion, morphic language). Symptoms: looks templated or AI-generated, must fill every screen size, \"make it unique\", \"what colors\".

Loop Design

Yoliani

Design the task DAG a work loop will walk: turn a spec, plan, or issue list into a `.agent-loop/<effort>/` directory holding the tasks, dependencies, topology decision, and durable shared state files. Use when the user asks to design a loop, plan or decompose work as a graph, or before dispatching parallel agents on a multi-task effort.

Implement Sub Agents

yu-iskw

Create and validate Claude sub-agent definitions with correct frontmatter, tool permissions, and delegation boundaries.

Test Driven Development

jburns24

Use when implementing any feature or bugfix, before writing implementation code

Retirement Plan

joestump

Generate a high-fidelity, durable retirement-plan.html from a Claude Project's financial documents and lifestyle assumptions. Triggers when the project name suggests retirement focus (retire, retirement, FIRE, early retire, freedom), the user invokes /retirement-plan or asks to build/update/refresh the plan, new financial documents are uploaded, the user mentions a money event (inheritance, RSU ve

Deploy:staging

rhuss

Deploy a service to the staging environment with health checks and rollback. Use when asked to deploy, push to staging, release to staging, or test a deployment. Do NOT use for production deployments (use deploy:production instead) or for CI/CD pipeline configuration.

Test:generate

rhuss

Generate unit tests for a source file. Analyzes the code and creates test cases covering public functions, edge cases, and error paths. Use when you need test coverage for new code or when tests are missing.

Self Report

joestump

File GitHub issues against joestump/claude-skills when another skill in this repo hits friction during a run. Other skills in this repo delegate their self-evaluation reporting to this skill rather than implementing their own filing logic. Triggers when another skill explicitly invokes self-report after detecting that its trip thresholds were exceeded (tool-call budget, repeated bug retries, mater

Pr:review

rhuss

Review a pull request for code quality, test coverage, and architectural alignment. Use when asked to review a PR, check code quality, provide feedback on changes, or audit a diff. Do NOT use for creating PRs (use pr:create) or for merging (use pr:merge).

Bank Audit Lfar

eurth

Assist with bank branch audit and Long Form Audit Report (LFAR). Covers NPA classification, income recognition, advances review, concurrent audit findings, stock audit, and LFAR questionnaire responses. Covers RBI guidelines on income recognition and asset classification (IRAC).

Decodo Serp Rank Tracking

therealityreport

Plan Decodo SERP scraping, rank tracking, AI Overview citation monitoring, and search feature analysis across geo, device, and locale settings.

Pythonista Reviewing

gigaverse-app

Code review best practices for Python projects. Use when reviewing code, PRs, or diffs. Triggers on "review", "code review", "PR", "pull request", "diff", "check this", "look at this code", "quality", "refactor", or when examining code for issues.

Pythonista Testing

gigaverse-app

Python testing best practices with pytest, TDD, and mocking. ALWAYS use this skill BEFORE writing or modifying any test code. Triggers on "test", "tests", "testing", "TDD", "test-driven", "pytest", "add tests", "write tests", "test this", "unit test", "integration test", "test coverage", "bug fix", "fix bug", "mock", "fixture", "assert", or when about to create/edit files in tests/ directory.

Pythonista Testing

gigaverse-app

Use when writing or modifying tests, fixing bugs with TDD, reviewing test code. Triggers on "test", "tests", "testing", "TDD", "test-driven", "pytest", "add tests", "write tests", "unit test", "integration test", "test coverage", "bug fix", "fix bug", "mock", "fixture", "assert", "conftest", "parametrize", "async test", or when editing files in tests/ directory.

Db:migrate

rhuss

Run database migrations against the target environment. Use when applying schema changes, running pending migrations, or checking migration status. Do NOT use for seed data insertion or database backups.

Implement Agent Teams

yu-iskw

Set up and validate Claude agent team configurations, collaboration flows, and operator guidance for team-based execution.

Implement Claude Extensions

yu-iskw

Choose and implement the right Claude extension type by comparing hooks, skills, sub-agents, agent teams, and plugin packaging patterns.

Pythonista Typing

gigaverse-app

Python type annotations and Pydantic best practices. Use when working with types, models, or data structures. Triggers on "type", "types", "typing", "Pydantic", "BaseModel", "dict", "list", "tuple", "annotation", "hint", "Any", "TypedDict", "dataclass", "model", "schema", or when defining function signatures or data models.

Implement Agent Skills

yu-iskw

Implement and maintain Claude Agent Skills with valid SKILL.md frontmatter, focused instructions, and progressive disclosure.

Implement Plugin

yu-iskw

Package and distribute Claude Code plugins with schema-safe manifests, canonical layout, component wiring, and release-ready validation.

Terraform AI Skills

anmolnagpal

Use when bulk-managing Terraform modules at scale — upgrading providers across AWS, GCP, Azure, or DigitalOcean repositories, standardizing GitHub Actions workflows, automating semantic releases, running security scans, or performing end-to-end maintenance cycles across 10–200+ module repositories

Terraform AI Skills

anmolnagpal

Multi-cloud Terraform module management skills for GitHub Copilot - automate provider upgrades, testing, CI/CD, and releases across AWS, GCP, Azure, and DigitalOcean modules at scale

Writing Style

Yoliani

Full prose style for anything Edgardo reads as writing - docs, READMEs, PR descriptions, posts, emails, long design answers. Use when drafting or revising prose, or when a reply grew past a few paragraphs. AGENTS.md carries the short version for ordinary chat replies.

Implement Hooks

yu-iskw

Implement and validate Claude Code hook configurations and hook scripts for command, prompt, and agent workflows.