Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
delivery.roadmap
Create a delivery roadmap that translates strategy into sequenced releases with milestones and dependencies.
edwardmonteiro/Aiskillinpractice
-
delivery.dashboard_brief
Align analysts and designers on the goals, requirements, and storytelling approach for a new or updated dashboard.
edwardmonteiro/Aiskillinpractice
-
delivery.test_plan
Generate a detailed test plan covering scenarios, environments, data, and reporting for the release.
edwardmonteiro/Aiskillinpractice
-
delivery.design_review
Facilitate a cross-functional design review capturing decisions, feedback, and implementation guidance.
edwardmonteiro/Aiskillinpractice
-
delivery.release_notes
Generate structured release notes tailored to the specified audience and highlighting value, rollout, and risks.
edwardmonteiro/Aiskillinpractice
-
delivery.tech_spec
Produce an implementation-ready technical specification with architecture, sequencing, and validation details.
edwardmonteiro/Aiskillinpractice
-
discovery.risk_assessment
Identify potential quality, security, and delivery risks early in discovery to inform mitigation planning.
edwardmonteiro/Aiskillinpractice
-
discovery.problem_framing
Frame the core customer problem, evidence, and success hypothesis before solutioning.
edwardmonteiro/Aiskillinpractice
-
discovery.market_scan
Analyze the competitive and adjacent solution landscape to surface differentiation opportunities.
edwardmonteiro/Aiskillinpractice
-
discovery.user_research
Plan and structure moderated or unmoderated user research sessions that target the given persona and objectives.
edwardmonteiro/Aiskillinpractice
-
discovery.tech_landscape
Assess technical patterns, integrations, and constraints in the domain to inform feasibility and strategy.
edwardmonteiro/Aiskillinpractice
-
discovery.data_audit
Inventory available datasets, instrumentation gaps, and data quality considerations for the initiative.
edwardmonteiro/Aiskillinpractice
-
pyx
Safe Python code execution using pyx CLI. Use when: running Python, executing scripts, testing code. Triggers: pyx, run python, execute code, test script. Default mode: MANIFEST_IO (file-first with manifest output).
Anudorannador/python-executor
-
setup-react-app-config
Set up configuratin files for the React project (Biome, Shadcn/UI)
yuheitomi/llm-instructions
-
commit
Commits changes in logical chunks with proper commit messages
yuheitomi/llm-instructions
-
set-up-framework
Setup framework development environment using configuration from setup directory
yuheitomi/llm-instructions
-
gh-issue
Creates a new GitHub issue in the current repository
yuheitomi/llm-instructions
-
create-pr
Commits changes in logical chunks and creates a PR
yuheitomi/llm-instructions
-
set-up-llm-docs
Download LLM instruction documents from the repository
yuheitomi/llm-instructions
-
agent-creator
Create Claude Code subagents. Use when user wants to create a subagent, specialized agent, or custom AI assistant for Claude Code.
alexjx/skills
-
skill-creator
Create new Claude Code skills in this repository. Use when user wants to add a new skill, create a skill, implement a skill, or extend Claude's capabilities with a custom workflow.
alexjx/skills
-
commit
Guide for creating atomic commits with conventional commit format. Use when user wants to commit changes.
alexjx/skills
-
crawl4ai
Web crawler that converts URLs to clean markdown. Use when user wants to fetch a webpage, extract web content, convert URL to markdown, or scrape website content.
alexjx/skills
-
agent-harness
Framework for orchestrating multiple AI agent sessions to complete complex, long-running software projects. Use when the user wants to set up or use the long-running agent harness pattern for managing multi-session projects, breaking work into discrete sessions with persistent state tracking, or implementing incremental progress workflows across multiple Claude Code sessions.
alexjx/skills