hjewkes
- 35 skills
- 0 followers
- 9 hours ago last updated
- ▌ Workflow Improvement · hjewkes bundleStart background observation that watches your session for friction and implements improvements. Use when you say "start workflow improvement", "/workflow-improvement", or "watch for friction".
- ▌ Brain · hjewkesSearch and manage your second brain knowledge base. Use when the user asks about their notes, wants to find information, or needs to add/organize knowledge. Also use proactively before research, brainstorming, or planning tasks to pull relevant prior work, and after completing research or making decisions to deposit findings.
- ▌ Repo CI · hjewkes bundleUse when setting up CI/CD workflows, auditing repo CI health, adding GitHub Actions, configuring branch protection, or scaffolding release pipelines for Node.js or Python projects.
- ▌ Tailwind · hjewkes bundleTailwind CSS v4 with shadcn/ui — setup, configuration, component patterns, dark mode, and troubleshooting. Use when setting up Tailwind v4, building UI components, fixing Tailwind errors, migrating from v3, or styling with utility classes.
- ▌ Atlassian · hjewkes bundleJira and Confluence integration for Atlassian Cloud. Use when the user needs to search issues, manage sprints, read Confluence docs, create/update pages, work with epics and backlogs, or any Atlassian workflow. Triggers include "jira", "confluence", "sprint", "backlog", "ticket", "issue", "epic", or references to Atlassian content.
- ▌ Buildkite · hjewkes bundleBuildkite CI/CD integration. Use when the user needs to check build status, trigger builds, read build logs, debug failures, manage pipelines, or any Buildkite workflow. Triggers include "buildkite", "build", "pipeline", "CI", "deploy", "build log", "build failed".
- ▌ Github Pr · hjewkes bundleGitHub PR workflow — creating PRs, posting automated review comments, managing PR feedback cycles. Use when code is reviewed and ready for GitHub.
- ▌ Humanizer · hjewkes bundleUse when writing or editing text intended for other humans — READMEs, emails, Slack messages, commit messages, documentation, PR descriptions. Cleans AI-generated text patterns and applies context-appropriate tone.
- ▌ Md Render · hjewkes bundleUse when asked to render, preview, or view a markdown file in the browser. Triggers on "render markdown", "preview this", "show me this document", "open in browser".
- ▌ Sdk Verify · hjewkes bundleVerify Claude Agent SDK applications. Use after creating or modifying TypeScript or Python Agent SDK apps to check configuration and best practices.
- ▌ Code Review · hjewkes bundleUnified code review system — dispatches the right review agents for the situation. Use when reviewing code for quality, bugs, compliance, or before merging.
- ▌ Git Workflow · hjewkes bundleUse when committing, branching, splitting changes, managing stacks, creating worktrees, or cleaning up branches — detects Graphite or Git and guides the agent through best-practice workflows via CLI.
- ▌ Self Improve · hjewkes bundleUse when a session produced reusable insights, when the user says "learn from this", "remember this", or "improve yourself", or after completing a complex task where patterns were discovered
- ▌ Agent Browser · hjewkes bundleBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
- ▌ Brainstorming · hjewkes bundleUse when designing features, planning components, or exploring approaches before implementation. Explores user intent, requirements and design through collaborative dialogue.
- ▌ Context Audit · hjewkes bundleAudit context window composition and identify optimization targets. Use when performance feels sluggish, context warnings appear, after installing new skills, or for periodic context health checks.
- ▌ Writing Plans · hjewkes bundleUse when you have a spec or requirements for a multi-step task, before touching code
- ▌ Plan Execution · hjewkes bundleExecute implementation plans and coordinate parallel agents. Handles in-session subagent dispatch, batch execution, parallel task coordination, and team orchestration.
- ▌ Frontend Design · hjewkes bundleCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
- ▌ Skills Management · hjewkes bundleUse when creating, finding, installing, reviewing, or managing Claude Code skills — covers skill authoring, discovery, conventions, and lifecycle management
- ▌ Research · hjewkesUse when the user asks to research a topic, investigate options, compare technologies, analyze a problem space, or gather information before making a decision — for both coding and non-coding work
- ▌ Using Git Worktrees · hjewkes bundleUse when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
- ▌ Coordinator · hjewkes bundleUse when the user says "vm", "voice mode", "team", "coordinate", or needs to orchestrate multiple agents working on related tasks in parallel
- ▌ Managing Github Issues · hjewkesUse when starting a session to find work, creating/triaging issues, or completing work and updating issue status
- ▌ Code Simplify · hjewkes bundleSimplify and refine code for clarity, consistency, and maintainability. Use after writing or modifying code to clean it up while preserving all functionality.
- ▌ Feature Agents · hjewkes bundleSpecialized feature development agents. Use for deep codebase exploration and architecture design during feature development.
- ▌ Executing Plans · hjewkes bundleUse when you have a written implementation plan to execute in a separate session with review checkpoints
- ▌ Using Superpowers · hjewkes bundleUse when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
- ▌ Systematic Debugging · hjewkes bundleUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes
- ▌ Finishing A Development Branch · hjewkes bundleUse when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
- ▌ Receiving Code Review · hjewkes bundleUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
- ▌ Test Driven Development · hjewkes bundleUse when implementing any feature or bugfix, before writing implementation code
- ▌ Dispatching Parallel Agents · hjewkes bundleUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
- ▌ Subagent Driven Development · hjewkes bundleUse when executing implementation plans with independent tasks in the current session
- ▌ Verification Before Completion · hjewkes bundleUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always